Abstract: The present disclosure provides a risk assessment method of water inrush in tunnels constructed in water-rich grounds. The method includes the following steps: simulating a tunnel excavation process by finite element software MIDAS GTS NX and fluid-structure interaction; according to a research method of control variables, analyzing effects of a groundwater level, an elastic modulus and advanced pipe shed grouting on the stability of surrounding rock, and improving an algorithm of a radial basis function (RBF) neural network using a Grey Relation Analysis (GRA)-based Partitioning Around Medoid (PAM) clustering algorithm to assess risks of water inrush occurring in Qingdao area.

Abstract: The present invention provides a digital load cell with redundancy design, the digital load cell including: at least one force measuring element that measures a load force applied to the digital load cell, where each force measuring element converts the load force into one analog signal; and one or more analog-to-digital conversion modules, where each force measuring element is connected to at least one analog-to-digital conversion module, and the analog-to-digital conversion module converts the analog signal into a digital signal. According to the digital load cell of the present invention, redundancy design is provided at least for both the force measuring element and the analog-to-digital conversion module, which can effectively ensure the proper operation of the digital load cell.

Abstract: The disclosure belongs to the technical field of additive manufacturing, and discloses a flexible piezoelectric sensor based on 4D printing and a preparation method thereof. The sensor includes a magnetic part and a conductive part, wherein: the conductive part includes two substrates disposed opposite to each other and a spiral structure disposed between the two substrates. Both the two substrates and the spiral structure are made of conductive metal materials. The magnetic part has a flexible porous structure and is arranged between the two substrates to generate a magnetic field. When the substrate is subjected to external pressure, the spiral structure and the magnetic part are compressed simultaneously, the magnetic flux passing through the spiral structure changes, and the voltage of the two substrates changes, by measuring the voltage change of the two substrates to reflect the change of external pressure, the pressure measuring process is achieved.

Abstract: A digital load cell includes: a strain bridge including a Wheatstone bridge formed by connecting four resistive strain gauges and a temperature sensing resistance element connected in series to the Wheatstone bridge. An analog-to-digital conversion circuit excites the strain bridge, and includes a plurality of input channels and an output terminal. The input channels receive feedback signals from the strain bridge, and the output terminal outputs the feedback signals after analog-to-digital conversion. A signal processor includes a load force calculation unit and a state information matrix calculation unit. The load force calculation unit calculates a differential voltage and a compensation function based on the feedback signals obtained from the output terminal, and calculates a load force value based on the differential voltage and the compensation function. The digital load cell and related weighing system; can provide comprehensive and effective real-time health state monitoring for the digital load cell.

Abstract: A freestyle acquisition method for a high-dimensional material, belonging to the field of computer graphics and computer vision. The learning of material information is transformed into a geometric learning problem on an unstructured point cloud, and a plurality of acquisition results in different lighting and view directions form a high-dimensional point cloud, each point in the point cloud being a vector formed by an image measurement value and pose information of an object during image capture. According to the method, information of unstructured views can be effectively aggregated from the high-dimensional point cloud which is disordered, irregular, uneven in distribution and limited in precision, and the material attribute with high quality is reconstructed.

Abstract: A method for obtaining a normal vector, a geometry and a material of a three-dimensional object based on a neural network is provided. The present disclosure provides, based on an idea of “actively irradiating an object with a number of specific patterns, capturing photos at the same time, and obtaining a normal vector of an object by calculating the obtained photos”, an acquisition method combined with a neural network. Further, the method uses the obtained normal vector to optimize a model of the object. This method can also obtain material feature information while obtaining the normal vector. Finally, a high-quality geometric result and a high-quality material acquisition result are obtained jointly. The number of illumination patterns obtained by using this method is small, and the normal vector obtained by the method has high accuracy and the method is not limited to a specific acquisition device.

Abstract: The disclosure belongs to the technical field of additive manufacturing, and discloses a flexible piezoelectric sensor based on 4D printing and a preparation method thereof. The sensor includes a magnetic part and a conductive part, wherein: the conductive part includes two substrates disposed opposite to each other and a spiral structure disposed between the two substrates. Both the two substrates and the spiral structure are made of conductive metal materials. The magnetic part has a flexible porous structure and is arranged between the two substrates to generate a magnetic field. When the substrate is subjected to external pressure, the spiral structure and the magnetic part are compressed simultaneously, the magnetic flux passing through the spiral structure changes, and the voltage of the two substrates changes, by measuring the voltage change of the two substrates to reflect the change of external pressure, the pressure measuring process is achieved.

Abstract: The invention belongs to the field of filament additive manufacturing, and discloses a polymer multi-material high-flexibility laser additive manufacturing system and a method thereof. The system comprises a first robot arm, a second robot arm, a positioner, a rotational extrusion nozzle in which a plurality of extrusion modules are disposed and a laser, each extrusion module is used for extruding one kind of filament, and the rotational extrusion nozzle is connected with the first robot which drives the rotational extrusion nozzle to move according to a preset trajectory; the laser is connected with the second robot, and is used for emitting a laser to fuse the filament extruded from the rotational extrusion nozzle, and through the cooperative motion of the first robot and the second robot, the extrusion and fusion of the filament are performed synchronously; the positioner serves as a forming mesa, and the rotation of the positioner cooperates with the motions of the two robots.

Abstract: A method for obtaining a normal vector, a geometry and a material of a three-dimensional object based on a neural network is provided. The present disclosure provides, based on an idea of “actively irradiating an object with a number of specific patterns, capturing photos at the same time, and obtaining a normal vector of an object by calculating the obtained photos”, an acquisition method combined with a neural network. Further, the method uses the obtained normal vector to optimize a model of the object. This method can also obtain material feature information while obtaining the normal vector. Finally, a high-quality geometric result and a high-quality material acquisition result are obtained jointly. The number of illumination patterns obtained by using this method is small, and the normal vector obtained by the method has high accuracy and the method is not limited to a specific acquisition device.

Abstract: The present disclosure belongs to the technical field of advanced manufacturing auxiliary equipment, and discloses an independently temperature-controlled high-temperature selective laser sintering frame structure, comprising a galvanometric laser scanning system, a powder feeding chamber, a forming chamber and a heat-insulating composite plate, and targeted optimization design is performed on the respective functional components.

Abstract: The present disclosure belongs to the technical field of advanced manufacturing auxiliary equipment, and discloses an independently temperature-controlled high-temperature selective laser sintering frame structure, comprising a galvanometric laser scanning system, a powder feeding chamber, a forming chamber and a heat-insulating composite plate, and targeted optimization design is performed on the respective functional components.

Abstract: The invention belongs to the field of filament additive manufacturing, and discloses a polymer multi-material high-flexibility laser additive manufacturing system and a method thereof. The system comprises a first robot arm, a second robot arm, a positioner, a rotational extrusion nozzle in which a plurality of extrusion modules are disposed and a laser, each extrusion module is used for extruding one kind of filament, and the rotational extrusion nozzle is connected with the first robot which drives the rotational extrusion nozzle to move according to a preset trajectory; the laser is connected with the second robot, and is used for emitting a laser to fuse the filament extruded from the rotational extrusion nozzle, and through the cooperative motion of the first robot and the second robot, the extrusion and fusion of the filament are performed synchronously; the positioner serves as a forming mesa, and the rotation of the positioner cooperates with the motions of the two robots.