Research on Surface Defect Detection of Strip Steel Based on Improved YOLOv7.

Surface defect detection of strip steel is an important guarantee for improving the production quality of strip steel. However, due to the diverse types, scales, and texture structures of surface defects on strip steel, as well as the irregular distribution of defects, it is difficult to achieve rapid and accurate detection of strip steel surface defects with existing methods. This article proposes a real-time and high-precision surface defect detection algorithm for strip steel based on YOLOv7. Firstly, Partial Conv is used to replace the conventional convolution blocks of the backbone network to reduce the size of the network model and improve the speed of detection; Secondly, The CA attention mechanism module is added to the ELAN module to enhance the ability of the network to extract detect features and improve the effectiveness of detect detection in complex environments; Finally, The SPD convolution module is introduced at the output end to improve the detection performance of small targets with surface defects on steel. The experimental results on the NEU-DET dataset indicate that the mean average accuracy (mAP@IoU = 0.5) is 80.4%, which is 4.0% higher than the baseline network. The number of parameters is reduced by 8.9%, and the computational load is reduced by 21.9% (GFLOPs). The detection speed reaches 90.9 FPS, which can well meet the requirements of real-time detection.

Recent progress on underwater soft robots: adhesion, grabbing, actuating, and sensing.

The research on biomimetic robots, especially soft robots with flexible materials as the main structure, is constantly being explored. It integrates multi-disciplinary content, such as bionics, material science, mechatronics engineering, and control theory, and belongs to the cross-disciplinary field related to mechanical bionics and biological manufacturing. With the continuous development of various related disciplines, this area has become a hot research field. Particularly with the development of practical technologies such as 3D printing technology, shape memory alloy, piezoelectric materials, and hydrogels at the present stage, the functions and forms of soft robots are constantly being further developed, and a variety of new soft robots keep emerging. Soft robots, combined with their own materials or structural characteristics of large deformation, have almost unlimited degrees of freedom (DoF) compared with rigid robots, which also provide a more reliable structural basis for soft robots to adapt to the natural environment. Therefore, soft robots will have extremely strong adaptability in some special conditions. As a type of robot made of flexible materials, the changeable pose structure of soft robots is especially suitable for the large application environment of the ocean. Soft robots working underwater can better mimic the movement characteristics of marine life in the hope of achieving more complex underwater tasks. The main focus of this paper is to classify different types of underwater organisms according to their common motion modes, focusing on the achievements of some bionic mechanisms in different functional fields that have imitated various motion modes underwater in recent years (e.g., the underwater sucking glove, the underwater Gripper, and the self-powered soft robot). The development of various task types (e.g., grasping, adhesive, driving or swimming, and sensing functions) and mechanism realization forms of the underwater soft robot are described based on this article.

Influence of Rotational Speed on Isothermal Piston Compression System.

An isothermal piston is a device that can achieve near-isothermal compression by enhancing the heat transfer area with a porous media. However, flow resistance between the porous media and the liquid is introduced, which cannot be neglected at a high operational speed. Thus, the influence of rotational speed on the isothermal piston compression system is analyzed in this study. A flow resistance mathematical model is established based on the face-centered cubic structure hypothesis. The energy conservation rate and efficiency of the isothermal piston are defined. The effect of rotational speed on resistance is discussed, and a comprehensive energy conservation performance assessment of the isothermal piston is analyzed. The results show that the increasing rate of the resistance work increases significantly proportional to the rotational speed, and the proportion of resistance work in the total work increases gradually and sharply. The total work including compression and resistance cannot be larger than the compression work under adiabatic conditions. The maximum rotational speed is 650 rpm.

Sputum deposition classification for mechanically ventilated patients using LSTM method based on airflow signals.

A novel sputum deposition classification method for mechanically ventilated patients based on the long-short-term memory network (LSTM) method was proposed in this study. A wireless ventilation airflow signals collection system was designed and used in this study. The ventilation airflow signals were collected wirelessly and used for sputum deposition classification. Two hundred sixty data groups from 15 patients in the intensive care unit were compiled and analyzed. A two-layer LSTM framework and 11 features extracted from the airflow signals were used for the model training. The cross-validations were adopted to test the classification performance. The sensitivity, specificity, precision, accuracy, F1 score, and G score were calculated. The proposed method has an accuracy of 84.7 ± 4.1% for sputum and non-sputum deposition classification. Moreover, compared with other classifiers (logistic regression, random forest, naive Bayes, support vector machine, and K-nearest neighbor), the proposed LSTM method is superior. In addition, the other advantages of using ventilation airflow signals for classification are its convenience and low complexity. Intelligent devices such as phones, laptops, or ventilators can be used for data processing and reminding medical staff to perform sputum suction. The proposed method could significantly reduce the workload of medical staff and increase the automation and efficiency of medical care, especially during the COVID-19 pandemic.

Energy Analysis of Precooling Air Compressor System.

Energy saving is one of the main technique routes for net zero carbon emissions. Air compressor systems take up a large part of energy consumption in the industrial field. A pre-cooling air compressor system was proposed for energy saving by cooling the air before it flows in a compressor. The energy efficiency of the proposed system was analyzed. As additional energy consumption is required for air cooling, the feasibility of the pre-cooling method for energy saving was analyzed. As the efficiency of the pre-cooling air compressor system is mainly influenced by the environment temperature and humidity, applicability of the system in different regions and at different seasons was discussed. A pilot project was performed to verify the technical feasibility and economics of the proposed system. When the precooling temperature of the pilot system was set to 2 °C, the annual pneumatic-electrical ratio of the system can be increased by approximately 2% in several regions of China. This paper shows the pre-cooling air compressor system is feasible for energy saving.

Visual-SLAM Classical Framework and Key Techniques: A Review.

With the significant increase in demand for artificial intelligence, environmental map reconstruction has become a research hotspot for obstacle avoidance navigation, unmanned operations, and virtual reality. The quality of the map plays a vital role in positioning, path planning, and obstacle avoidance. This review starts with the development of SLAM (Simultaneous Localization and Mapping) and proceeds to a review of V-SLAM (Visual-SLAM) from its proposal to the present, with a summary of its historical milestones. In this context, the five parts of the classic V-SLAM framework-visual sensor, visual odometer, backend optimization, loop detection, and mapping-are explained separately. Meanwhile, the details of the latest methods are shown; VI-SLAM (Visual inertial SLAM) is reviewed and extended. The four critical techniques of V-SLAM and its technical difficulties are summarized as feature detection and matching, selection of keyframes, uncertainty technology, and expression of maps. Finally, the development direction and needs of the V-SLAM field are proposed.

Effect of different anesthetic dose of pentobarbital on respiratory activity in rabbits.

Anesthetics inhibit the respiratory muscles and even cause upper airway to collapse. Diaphragm electromyography (EMGdi) and airflow signals are usually extracted to assess the degree of respiration inhibition by anesthetics. However, the ECG interference in EMGdi affects the accuracy of its time domain and frequency domain information extraction. We studied the changes in EMGdi (left EMGdi and right EMGdi) and airflow characteristics under two pentobarbital anesthetic doses. First, we filtered out the ECG in EMGdi based on the combination of stationary wavelet transform and the positioning of ECG to obtain EMGdi without ECG interference (EMGdip). The effectiveness of filtering algorithm was verified by calculating the power spectrum before and after noise reduction. Second, root mean square (RMS), average rectified value (ARV), and fixed sample entropy (fSampEn) were used to quantify EMGdi (left EMGdi, left EMGdip and right EMGdi). Median frequency (MF) and centroid frequency (fc) of EMGdi were calculated. Tidal volume, respiratory cycle duration and peak airflow were calculated from airflow. Finally, the average and standard deviation of these parameters for all rabbits (n = 10) were compared and analyzed under two anesthesia states. Our results indicate that anesthesia induced by an increase in pentobarbital dose leads to decrease in ventilation and EMGdi amplitude. There was no significant change in diaphragm power spectrum (MF and fc) with the increase of anesthesia dose.

Evaluation of Correlation Between Surface Diaphragm Electromyography and Airflow Using Fixed Sample Entropy in Healthy Subjects.

In clinic, the acquisition of airflow with nasal prongs, masks, thermistor to monitor respiratory function is more uncomfortable and inconvenience than surface diaphragm electromyography (EMGdi) using electrode pads. The EMGdi with strong electrocardiograph (ECG) interference affect the extraction of its characteristic information. In this work, surface EMGdi and airflow signals of 20 subjects were collected under 5 incremental inspiratory threshold loading protocols from quiet breathing to maximum forced breathing. First, we filtered out the ECG interference in EMGdi based on the combination of stationary wavelet transform and the positioning of ECG to obtain pure EMGdi (EMGdip). Second, the Spearman's rank correlation coefficients between EMGdi and EMGdip quantified by time series fixed sample entropy (fSampEn), root mean square (RMS), and envelope were compared to verify the robustness of the fSampEn to ECG. A comparative analysis of correlation between fSampEn of EMGdi and inspiratory airflow and the correlation between envelope of EMGdip (EMGdie) and inspiratory airflow found that there was no significant difference between the two, indicating the feasibility of using fSampEn to predict airflow. Moreover, fSampEn of EMGdi was used as characteristic parameter to build a quantitative relationship with the airflow by polynomial regression analysis. Mean coefficient of determination of all subjects in any breathing state is greater than 0.88. Finally, nonlinear programming method was used to solve a universal fitting coefficient between fSampEn of EMGdi and airflow for each subject to further evaluate the possibility of using surface EMGdi to monitor and control respiratory activity.

Paced breathing and respiratory movement responses evoked by bidirectional constant current stimulation in anesthetized rabbits.

Objective: Diaphragm pacing (DP) is a long-term and effective respiratory assist therapy for patients with central alveolar hypoventilation and high cervical spinal cord injury. The existing DP system has some limitations, especially high price, inconvenience preoperative evaluation methods and diaphragm fatigue easily. Our objective was to develop a DP system and evaluated reliability through hardware testing and animal experiments. Methods: A DP system with bidirectional constant current was designed, manufactured and tested. Effects of a wide range of stimulus amplitudes (range: .5-2.5 mA) and frequencies (range: 10-250 Hz) on airflow and corresponding inspired volume were investigated during DP. Differences in airflow characteristics under various stimulation parameters were evaluated using power function. ECG interference in diaphragm electromyography (EMGdi) was filtered out using stationary wavelet transform to obtain pure EMGdi (EMGdip). 80-min period with a tendency for diaphragm fatigue by root mean square (RMS) and centroid frequency (f c ) of EMGdip was studied. Results: The increase of stimulus frequency and amplitude in animals resulted in different degrees of increase in envoked volume. Significant difference in Airflow Index (b) between anesthesia and DP provided a simple, non-invasive and feasible solution for phrenic nerve conduction function test. Increased stimulation duration with the developed DP system caused less diaphragm fatigue. Conclusion: A modular, inexpensive and reliable DP was successfully developed. Its effectiveness was confirmed in animal experiments. Significance: This study is useful for design of future implantable diaphragmatic pacemakers for improving diaphragm fatigue and convenient assessment of respiratory activity in experiments.

Water-Spray-Cooled Quasi-Isothermal Compression Method: Water-Spray Flow Improvement.

Water-spray-cooled quasi-isothermal compressed air energy storage aims to avoid heat energy losses from advanced adiabatic compressed-air energy storage (AA-CAES). The compression efficiency increases with injection water spray. However, the energy-generated water spray cannot be ignored. As the air pressure increases, the work done by the piston and the work converted into heat rise gradually in the compression process. Accordingly, the flow rate of the water needed for heat transfer is not a constant with respect to time. To match the rising compression heat, a time sequence of water-spray flow rate is constructed, and the algorithm is designed. Real-time water-spray flow rate is calculated according to the difference between the compression power and heat-transfer power. Compared with the uniform flow rate of water spray, energy consumption from the improved flow rate is reduced.

Novel assisted cough system based on simulating cough airflow dynamics.

ABSTRACT: Cough is a defensive behavior that protects the respiratory system from infection and clears airway secretions. Cough airflow dynamics have been analyzed by a variety of mathematical and experimental tools. In this paper, the cough airflow dynamics of 42 subjects were obtained and analyzed. An identification model based on piecewise Gauss function for cough airflow dynamics is proposed through the dimensionless method, which could achieve over 90% identification accuracy. Meanwhile, an assisted cough system based on pneumatic flow servo system is presented. The vacuum situation and feedback control are used to increase the simulated peak cough flow rate, which are important for airway secretion clearance and to avoid airway collapse, respectively. The simulated cough peak flow could reach 5 L/s without the external assistance such as manual pressing, patient cooperation and other means. Finally, the backstepping control is developed to generate a simulated cough airflow that closely mimics the natural cough airflow of humans. The assisted cough system opens up wide opportunities of practical application in airway secretion clearance for critically ill patients with COVID 2019 and other pulmonary diseases.

Mechanical ventilation strategy for pulmonary rehabilitation based on patient-ventilator interaction.

Mechanical ventilation is an effective medical means in the treatment of patients with critically ill, COVID-19 and other pulmonary diseases. During the mechanical ventilation and the weaning process, the conduct of pulmonary rehabilitation is essential for the patients to improve the spontaneous breathing ability and to avoid the weakness of respiratory muscles and other pulmonary functional trauma. However, inappropriate mechanical ventilation strategies for pulmonary rehabilitation often result in weaning difficulties and other ventilator complications. In this article, the mechanical ventilation strategies for pulmonary rehabilitation are studied based on the analysis of patient-ventilator interaction. A pneumatic model of the mechanical ventilation system is established to determine the mathematical relationship among the pressure, the volumetric flow, and the tidal volume. Each ventilation cycle is divided into four phases according to the different respiratory characteristics of patients, namely, the triggering phase, the inhalation phase, the switching phase, and the exhalation phase. The control parameters of the ventilator are adjusted by analyzing the interaction between the patient and the ventilator at different phases. A novel fuzzy control method of the ventilator support pressure is proposed in the pressure support ventilation mode. According to the fuzzy rules in this research, the plateau pressure can be obtained by the trigger sensitivity and the patient's inspiratory effort. An experiment prototype of the ventilator is established to verify the accuracy of the pneumatic model and the validity of the mechanical ventilation strategies proposed in this article. In addition, through the discussion of the patient-ventilator asynchrony, the strategies for mechanical ventilation can be adjusted accordingly. The results of this research are meaningful for the clinical operation of mechanical ventilation. Besides, these results provide a theoretical basis for the future research on the intelligent control of ventilator and the automation of weaning process.

A Novel Isothermal Compression Method for Energy Conservation in Fluid Power Systems.

Reducing carbon emissions is an urgent problem around the world while facing the energy and environmental crises. Whatever progress has been made in renewable energy research, efforts made to energy-saving technology is always necessary. The energy consumption from fluid power systems of industrial processes is considerable, especially for pneumatic systems. A novel isothermal compression method was proposed to lower the energy consumption of compressors. A porous medium was introduced to compose an isothermal piston. The porous medium was located beneath a conventional piston, and gradually immerged into the liquid during compression. The compression heat was absorbed by the porous medium, and finally conducted with the liquid at the chamber bottom. The heat transfer can be significantly enhanced due to the large surface area of the porous medium. As the liquid has a large heat capacity, the liquid temperature can maintain constant through circulation outside. This create near-isothermal compression, which minimizes energy loss in the form of heat, which cannot be recovered. There will be mass loss of the air due to dissolution and leakage. Therefore, the dissolution and leakage amount of gas are compensated for in this method. Gas is dissolved into liquid with the pressure increasing, which leads to mass loss of the gas. With a pressure ratio of 4:1 and a rotational speed of 100 rpm, the isothermal piston decreased the energy consumption by 45% over the conventional reciprocation piston. This gain was accomplished by increasing the heat transfer during the gas compression by increasing the surface area to volume ratio in the compression chamber. Frictional forces between the porous medium and liquid was presented. Work to overcome the frictional forces is negligible (0.21% of the total compression work) under the current operating condition.

Numerical Analysis of Airway Mucus Clearance Effectiveness Using Assisted Coughing Techniques.

Cough is a protective respiratory reflex used to clear respiratory airway mucus. For patients with cough weakness, such as chronic obstructive pulmonary disease, neuromuscular weakness disease and other respiratory diseases, assisted coughing techniques are essential to help them clear mucus. In this study, the Eulerian wall film model was applied to simulate the coughing clearance process through a computational fluid dynamics methodology. Airway generation 0 to generation 2 based on realistic geometry is considered in this study. To quantify cough effectiveness, cough efficiency was calculated. Moreover, simulations of four different coughing techniques applied for chronic obstructive pulmonary disease and neuromuscular weakness disease were conducted. The influences of mucus film thickness and mucus viscosity on cough efficiency were analyzed. From the simulation results, we found that with increasing mucus film thickness and decreasing mucus viscosity, cough efficiency improved accordingly. Assisted coughing technologies have little influence on the mucus clearance of chronic obstructive pulmonary disease models. Finally, it was observed that the cough efficiency of the mechanical insufflation-exsufflation technique (MIE) is more than 40 times the value of an unassisted coughing technique, which indicates that the MIE technology has a great effect on airway mucus clearance for neuromuscular weakness disease models.

A Novel Method for Automatic Identification of Breathing State.

Sputum deposition blocks the airways of patients and leads to blood oxygen desaturation. Medical staff must periodically check the breathing state of intubated patients. This process increases staff workload. In this paper, we describe a system designed to acquire respiratory sounds from intubated subjects, extract the audio features, and classify these sounds to detect the presence of sputum. Our method uses 13 features extracted from the time-frequency spectrum of the respiratory sounds. To test our system, 220 respiratory sound samples were collected. Half of the samples were collected from patients with sputum present, and the remainder were collected from patients with no sputum present. Testing was performed based on ten-fold cross-validation. In the ten-fold cross-validation experiment, the logistic classifier identified breath sounds with sputum present with a sensitivity of 93.36% and a specificity of 93.36%. The feature extraction and classification methods are useful and reliable for sputum detection. This approach differs from waveform research and can provide a better visualization of sputum conditions. The proposed system can be used in the ICU to inform medical staff when sputum is present in a patient's trachea.

A Lung Sound Category Recognition Method Based on Wavelet Decomposition and BP Neural Network.

In this paper, a method of characteristic extraction and recognition on lung sounds is given. Wavelet de-noised method is adopted to reduce noise of collected lung sounds and extract wavelet characteristic coefficients of the de-noised lung sounds by wavelet decomposition. Considering the problem that lung sounds characteristic vectors are of high dimensions after wavelet decomposition and reconstruction, a new method is proposed to transform the characteristic vectors from reconstructed signals into reconstructed signal energy. In addition, we use linear discriminant analysis (LDA) to reduce the dimension of characteristic vectors for comparison in order to obtain a more efficient way for recognition. Finally, we use BP neural network to carry out lung sounds recognition where comparatively high-dimensional characteristic vectors and low- dimensional vectors are set as input and lung sounds categories as output with a recognition accuracy of 82.5% and 92.5%.

Coupling Effect of Double Lungs on a VCV Ventilator with Automatic Secretion Clearance Function.

For patients with mechanical ventilation, secretions in airway are harmful and sometimes even mortal, it's of great significance to clear secretion timely and efficiently. In this paper, a new secretion clearance method for VCV (volume-controlled ventilation) ventilator is put forward, and a secretion clearance system with a VCV ventilator and double lungs is designed. Furthermore, the mathematical model of the secretion clearance system is built and verified via experimental study. Finally, to illustrate the influence of key parameters of respiratory system and secretion clearance system on the secretion clearance characteristics, coupling effects of two lungs on VCV secretion clearance system are studied by an orthogonal experiment, it can be obtained that rise of tidal volume adds to efficiency of secretion clearance while effect of area, compliance, and suction pressure on efficiency of secretion clearance needs further study. Rise of compliance improves bottom pressure of secretion clearance while rise of area, tidal volume, and suction pressure decreases bottom pressure of secretion clearance. This paper can be referred to in researches of secretion clearance for VCV.

Classification of Sputum Sounds Using Artificial Neural Network and Wavelet Transform.

Sputum sounds are biological signals used to evaluate the condition of sputum deposition in a respiratory system. To improve the efficiency of intensive care unit (ICU) staff and achieve timely clearance of secretion in patients with mechanical ventilation, we propose a method consisting of feature extraction of sputum sound signals using the wavelet transform and classification of sputum existence using artificial neural network (ANN). Sputum sound signals were decomposed into the frequency subbands using the wavelet transform. A set of features was extracted from the subbands to represent the distribution of wavelet coefficients. An ANN system, trained using the Back Propagation (BP) algorithm, was implemented to recognize the existence of sputum sounds. The maximum precision rate of automatic recognition in texture of signals was as high as 84.53%. This study can be referred to as the optimization of performance and design in the automatic technology for sputum detection using sputum sound signals.

ANSYS-MATLAB co-simulation of mucus flow distribution and clearance effectiveness of a new simulated cough device.

Coughing is an irritable reaction that protects the respiratory system from infection and improves mucus clearance. However, for the patients who cannot cough autonomously, an assisted cough device is essential for mucus clearance. Considering the low efficiency of current assisted cough devices, a new simulated cough device based on the pneumatic system is proposed in this paper. Given the uncertainty of airflow rates necessary to clear mucus from airways, the computational fluid dynamics Eulerian wall film model and cough efficiency (CE) were used in this study to simulate the cough process and evaluate cough effectiveness. The Ansys-Matlab co-simulation model was set up and verified through experimental studies using Newtonian fluids. Next, model simulations were performed using non-Newtonian fluids, and peak cough flow (PCF) and PCF duration time were analyzed to determine their influence on mucus clearance. CE growth rate (λ) was calculated to reflect the CE variation trend. From the numerical simulation results, we find that CE rises as PCF increases while the growth rate trends to slow as PCF increases; when PCF changes from 60 to 360 L/min, CE changes from 3.2% to 51.5% which is approximately 16 times the initial value. Meanwhile, keeping a long PCF duration time could greatly improve CE under the same cough expired volume and PCF. The results indicated that increasing the PCF and PCF duration time can improve the efficiency of mucus clearance. This paper provides a new approach and a research direction for control strategy in simulated cough devices for airway mucus clearance.

Influence of bronchial diameter change on the airflow dynamics based on a pressure-controlled ventilation system.

Bronchial diameter is a key parameter that affects the respiratory treatment of mechanically ventilated patients. In this paper, to reveal the influence of bronchial diameter on the airflow dynamics of pressure-controlled mechanically ventilated patients, a new respiratory system model is presented that combines multigeneration airways with lungs. Furthermore, experiments and simulation studies to verify the model are performed. Finally, through the simulation study, it can be determined that in airway generations 2 to 7, when the diameter is reduced to half of the original value, the maximum air pressure (maximum air pressure in lungs) decreases by nearly 16%, the maximum flow decreases by nearly 30%, and the total airway pressure loss (sum of each generation pressure drop) is more than 5 times the original value. Moreover, in airway generations 8 to 16, with increasing diameter, the maximum air pressure, maximum flow, and total airway pressure loss remain almost constant. When the diameter is reduced to half of the original value, the maximum air pressure decreases by 3%, the maximum flow decreases by nearly 5%, and the total airway pressure loss increases by 200%. The study creates a foundation for improvement in respiratory disease diagnosis and treatment.