Improved YOLOv7 Network Model for Gangue Selection Robot for Gangue and Foreign Matter Detection in Coal.

Coal production often involves a substantial presence of gangue and foreign matter, which not only impacts the thermal properties of coal and but also leads to damage to transportation equipment. Selection robots for gangue removal have garnered attention in research. However, existing methods suffer from limitations, including slow selection speed and low recognition accuracy. To address these issues, this study proposes an improved method for detecting gangue and foreign matter in coal, utilizing a gangue selection robot with an enhanced YOLOv7 network model. The proposed approach entails the collection of coal, gangue, and foreign matter images using an industrial camera, which are then utilized to create an image dataset. The method involves reducing the number of convolution layers of the backbone, adding a small size detection layer to the head to enhance the small target detection, introducing a contextual transformer networks (COTN) module, employing a distance intersection over union (DIoU) loss border regression loss function to calculate the overlap between predicted and real frames, and incorporating a dual path attention mechanism. These enhancements culminate in the development of a novel YOLOv71 + COTN network model. Subsequently, the YOLOv71 + COTN network model was trained and evaluated using the prepared dataset. Experimental results demonstrated the superior performance of the proposed method compared to the original YOLOv7 network model. Specifically, the method exhibits a 3.97% increase in precision, a 4.4% increase in recall, and a 4.5% increase in mAP0.5. Additionally, the method reduced GPU memory consumption during runtime, enabling fast and accurate detection of gangue and foreign matter.

Hazard source detection of longitudinal tearing of conveyor belt based on deep learning.

Belt tearing is the main safety accident of belt conveyor. The main cause of tearing is the doped bolt and steel in the conveying belt. In this paper, the bolt and steel are identified as the Hazard source of tear. In this paper, bolt and steel are defined as the risk sources of tearing. Effective detection of the source of danger can effectively prevent the occurrence of conveyor belt tearing accidents. Here we use deep learning to detect the hazard source image. We improved on the SSD(Single Shot MultiBox Detector) model. Replace the original backbone network with an improved Shufflenet_V2, and replace the original position loss function with the CIoU loss function. Additionally, it compares this new approach to previous methods. The proposed model has surpassed other state-of-art methods with more than 94% accuracy. In addition, when deployed without GPU acceleration, the detection speed can reach 20fps. It can meet the requirements of real-time detection. The experimental results show that the proposed model can realize the online detection of hazard sources, so as to prevent longitudinal tearing of conveyor belt.

Respiratory fabric sensor based on the side luminescence and photosensitivity mechanism of polymer optical fibers.

It is significant to monitor respiration conveniently and in real time for people suffering from respiratory diseases. Polymer optical fibers (POFs) have the advantages of flexibility and light weight, which is highly desirable for wearable respiratory monitoring. However, in most current applications, the POFs are stitched on the textile substrates in the form of macro-bending. This method is complex to fix the bending with certain curvatures and uncomfortable compared with the POF sensors woven into the textile. In this paper, a respiratory fabric sensor based on the side luminescence and photosensitivity mechanism of POF is proposed and demonstrated. The 750µm-diameter POFs were woven into a fabric as warp and laser marking was performed at their designed positions to make them release or couple light. The spacing change between the POFs caused by the respiratory movement accordingly makes the light intensity change in the photosensitive fiber. We chose four fabric widths (10cm, 8cm, 6cm and 4cm) and four fabric weaves (plain weave, honeycomb weave, 1/3 right twill weave and 8/3 warp satin weave) to implement the full-factor experiment for exploring the measurement effect of the respiratory fabric sensor. The result is that the fabric with width of 4cm and weave of 8/3 warp satin is optimal. The calm and deep respiratory tests of the human chest and abdomen in sitting and standing posture were carried out and the test performance of the fabric sensor is almost comparable to that of the medical monitor. The proposed respiratory fabric sensor is comfortable, easily woven and high in precision, which is expected to realize industrialized scale production.

Speed regulation strategy and algorithm for the variable-belt-speed energy-saving control of a belt conveyor based on the material flow rate.

As an important transportation, the belt conveyor has been widely used and researched. It is urgent to solve the problem of energy saving and consumption reduction of belt conveyor. Aiming at reducing high energy consumption in the rated-speed operation of a belt conveyor, the present paper establishes an energy-saving belt-speed model of a belt conveyor using a polynomial regression-fitting algorithm and a small number of sample observations, and proposes a speed regulation strategy and particle swarm optimization-proportional-integral-derivative algorithm for the variable-belt-speed energy-saving control of a belt conveyor based on the material flow rate. The control strategy and algorithm adjust the running speed of the belt conveyor accurately according to changes in the material flow rate, thus reducing damage of frequent speed regulation to the belt conveyor and saving energy. Simulation analysis of a practical case shows that energy-saving belt-speed model, speed regulation strategy, and algorithm effectively reduce the energy consumption of a belt conveyor, and they thus have high application value in coal, ports, power, mine, metallurgy, chemical, and other industries. Further work in this field can be focused on the prediction of material flow rate of belt conveyor, the controllable adjustment duration of algorithm and the reduction of overshoot.

Research on the energy-saving control strategy of a belt conveyor with variable belt speed based on the material flow rate.

Aiming at solving the problem of high energy consumption in the rated belt speed operation of a belt conveyor system when the material flow rate is reduced, the power consumption of the frequency converter, motor, and belt conveyor is analyzed, a power consumption model of the belt conveyor system is established, the relationship between the power consumption of the belt conveyor system and belt speed is obtained, and a energy-saving control strategy of the belt conveyor with variable belt speed based on the material flow rate is put forward. The energy consumption of the belt conveyor is analyzed for a practical case. Results show that the power consumption model is accurate and the control strategy effectively reduces energy consumption. The model has high application value in coal, ports, power, mine, metallurgy, chemical, and other industries.

Label-free assessment of replicative senescence in mesenchymal stem cells by Raman microspectroscopy.

Here, Raman microspectroscopy was employed to assess replicative senescence of mesenchymal stem cells (MSC). A regular spectral change related to the cell senescence was found in the ratio of two peaks at 1157 cm(-1) and 1174 cm(-1), which are assigned to C-C, C-N stretching vibrations in proteins and C-H bending vibrations in tyrosine and phenylalanine, respectively. With the cell aging, the ratio I1157 / I1174 exhibited a monotonic decline and showed small standard deviations, so that it can statistically distinguish between cells having slight changes in terms of aging. We propose that I1157 / I1174 can act as a characteristic spectral signature for label-free assessment of MSC senescence.

[Research on the Method of Blood Pressure Monitoring Based on Multiple Parameters of Pulse Wave].

In order to improve the accuracy of blood pressure measurement in wearable devices, this paper presents a method for detecting blood pressure based on multiple parameters of pulse wave. Based on regression analysis between blood pressure and the characteristic parameters of pulse wave, such as the pulse wave transit time (PWTT), cardiac output, coefficient of pulse wave, the average slope of the ascending branch, heart rate, etc. we established a model to calculate blood pressure. For overcoming the application deficiencies caused by measuring ECG in wearable device, such as replacing electrodes and ECG lead sets which are not convenient, we calculated the PWTT with heart sound as reference (PWTT(PCG)). We experimentally verified the detection of blood pressure based on PWTT(PCG) and based on multiple parameters of pulse wave. The experiment results showed that it was feasible to calculate the PWTT from PWTT(PCG). The mean measurement error of the systolic and diastolic blood pressure calculated by the model based on multiple parameters of pulse wave is 1.62 mm Hg and 1.12 mm Hg, increased by 57% and 53% compared to those of the model based on simple parameter. This method has more measurement accuracy.

Large-area binary blazed grating coupler between nanophotonic waveguide and LED.

A large-area binary blazed grating coupler for the arrayed waveguide grating (AWG) demodulation integrated microsystem on silicon-on-insulator (SOI) was designed for the first time. Through the coupler, light can be coupled into the SOI waveguide from the InP-based C-band LED for the AWG demodulation integrated microsystem to function. Both the length and width of the grating coupler are 360 µm, as large as the InP-based C-band LED light emitting area in the system. The coupler was designed and optimized based on the finite difference time domain method. When the incident angle of the light source is 0°, the coupling efficiency of the binary blazed grating is 40.92%, and the 3 dB bandwidth is 72 nm at a wavelength of 1550 nm.

Preliminary investigation of an SOI-based arrayed waveguide grating demodulation integration microsystem.

An arrayed waveguide grating (AWG) demodulation integration microsystem is investigated in this study. The system consists of a C-band on-chip LED, a 2 × 2 silicon nanowire-based coupler, a fiber Bragg grating (FBG) array, a 1 × 8 AWG, and a photoelectric detector array. The coupler and AWG are made from silicon-on-insulator wafers using electron beam exposure and response-coupled plasma technology. Experimental results show that the excess loss in the MMI coupler with a footprint of 6 × 100 µm(2) is 0.5423 dB. The 1 × 8 AWG with a footprint of 267 × 381 µm(2) and a waveguide width of 0.4 µm exhibits a central channel loss of -3.18 dB, insertion loss non-uniformity of -1.34 dB, and crosstalk level of -23.1 dB. The entire system is preliminarily tested. Wavelength measurement precision is observed to reach 0.001 nm. The wavelength sensitivity of each FBG is between 0.04 and 0.06 nm/dB.

[Research on demodulation system for human body temperature measurement of intelligent clothing based on arrayed waveguide grating].

A system for demodulating distributed fiber Bragg grating sensors of the intelligent clothing was researched and realized, which is based on arrayed waveguide grating. The principle of demodulation method based on arrayed waveguide grating was analyzed, intensity--demodulating method was used to interrogate the wavelength of the fiber Bragg grating based on the building up of an experimental platform, and demodulation experiment of pre and post series of fiber Bragg grating was completed. The results show that the wavelength demodulation of the system has high linearity for fiber Bragg grating, the system gives a wavelength accuracy of 0.001 nm, and demodulation error caused by crosstalk between different sensors is 0.0005 nm. The measurement error of human body temperature is +/- 0.16 degrees C. It can be applied to the human body temperature measurement.