164results about How to "Meeting Industrial Needs" patented technology

The invention discloses a cloth defect detection method based on machine learning. The method particularly comprises the following steps of image segmentation, image enhancement, image denoising, sub image feature extraction, defect point area segmentation, offline cloth learning, online cloth detection, and cloth defect point classification. In the offline cloth learning stage, a BP neural network is used to train standard image characteristic parameters, and a standard value is obtained. In the online cloth detection stage, the BP neural network is used to detect the feature parameters of the sub image. In the cloth defect point classification stage, a depth learning algorithm based on a convolutional neural network is used to classify cloth defects. The cloth defect detection method based on machine learning has a self-learning function and can meet the continuously-developing industry needs. The invention also provides a cloth defect detection device based on machine learning, which comprises an image acquisition unit, an image processing unit, a data communication unit and an action execution unit. The detection device can realize high-efficiency and accurate detection, and workers can be freed from heavy and tasteless physical labor.

The invention relates to an oil layer three-section block removing technology with excellent block removing effect. A block removing agent will be injected at three sections; then, clear water will be injected after the reaction of 4 to 24 hours at each section; the quantity of clear water will be 1 to 2 times of the sum between the volume of an oil pipe and the volume of the circular space from the bottom of the oil pipe to the top of a perforation interval. Because the composition and function of the block removing agents different from each other, the invention can be applied in a broad scope to adopt to the needs in various stratum, realize excellent block removing effect with the removing rate of over 75 percent, thus satisfying the industrial needs.

The invention provides a polarization-maintaining flat optical fiber coupling ball microscale sensor based on polarization state detection and belongs to the technology of manufacturing and measurement of precise instruments. The polarization-maintaining flat optical fiber coupling ball microscale sensor comprises a laser, a semi-transparent semi-reflective prism, a quarter lambda wave plate, a probe, a polarization state detection device A, a polarization state detection device B and a computer, wherein the probe is composed of a flat package layer polarization-maintaining optical fiber and a coupling ball, and the laser, the semi-transparent semi-reflective prism, the quarter lambda wave plate and the probe are arranged in sequence. Emergent light of the laser is reflected and transmitted by the semi-transparent semi-reflective prism, and reflected light enters the polarization state detection device A; transmission light enters the probe, reverse transmission of a transmission light beam is achieved after the transmission light beam passes through the coupling ball, the transmission light exits from the probe, and emergent light passes through the quarter lambda wave plate, is reflected by the semi-transparent semi-reflective prism again and then enters the polarization state detection device B. When the difference value between the polarization state detected by the polarization state detection device B and the polarization state detected by the polarization state detection device A is changed, it can be determined that the probe is in contact with a detected hole. The polarization-maintaining flat optical fiber coupling ball microscale sensor is high in precision and high in speed.

The invention relates to a 3D (three-dimensional) imaging device and an imaging method based on laser scanning. The imaging device and the imaging method solve the problems of low detection efficiency and low accuracy rate in the prior art. The imaging device comprises a laser device (1), a camera (2), an auxiliary laser device (3), a stepping motor (4), a motor controller (5), a connecting rod (6) and a scanning object (7). The imaging method comprises the steps of 1, calibrating the camera (2) to obtain an internal parameter of the calibrated camera (2), 2, calibrating the 3D imaging device based on the laser scanning according to the internal parameter of the calibrated camera (2) obtained in Step 1 to obtain a pose of the camera during data acquisition each time, and 3, calculating scanned point cloud data according to calibrated data and the pose of the camera during the data acquisition each time in Step 1 and Step 2 to obtain a scanning model. The imaging device and the imaging method are used in the field of 3D scanning.

The invention discloses automatic equipment for coating the surfaces of iron rings by glue. The automatic equipment comprises a rack, a feeding module, a coating module, a discharging module, a platform movement module and a controller, wherein the rack is used as a support base; the feeding module is used for conveying a plurality of workpieces at the same time; the coating module is used for coating glue, the discharging module is used for unloading the workpieces; the platform movement module is used for overturning and carrying the workpieces at each station; the feeding module, the coating module and the discharging module are arranged on the rack in sequence along the length direction of the rack; the platform movement module is fixed at two sides of the rack in a stretching manner; the movable part of the platform movement module is capable of overturning and clamping the workpieces to sequentially convey the workpieces from the feeding module to the coating module and the discharging module along the length direction of the rack; the controller is in circuit connection with the feeding module, the coating module, the discharging module and the platform movement module. The automatic equipment for coating surfaces of iron rings by glue has the advantages of saving the human cost, being high in efficiency, high in accuracy, stable in quality and high in automation degree, greatly improving the production efficiency and satisfying the demand of industrial production.

The invention provides a calibration technology for a vision sub-pixel of an embedded type machine with optical path adjustment, which is a calibration technology of an adjustable optical path with on-line vision measurement. Main technologies including an optical path adjusting technology, a sub-pixel angular point extraction technology and a sub-pixel vision calibration technology are adopted in a calibration process, wherein the optical path adjusting technology comprises an optical intensity saturation prevention technology and an objective surface parallel-adjustment technology; the sub-pixel angular point extraction technology utilizes a spatial moment; and the sub-pixel vision calibration technology is based on an ideal grid. The invention overcomes the defects of the traditional measurement technology, carries out high-precision and high-stability calibration on a camera on a production line and can automatically carry out the vision measurement by using the calibration technology on the production line and finally detect the quality qualification of products; in addition, by adopting a design algorithm based on engineering idea, the invention has the advantages of high precision and speed, low requirements for production environment quality and high instantaneity, can well meet the requirements of industrial production, and has important significance on the vision measurement of the products in actual industrial production.

The invention provides a grabbing method for industrial stacked parts, terminal equipment and a readable storage medium. The method comprises the steps that a series of grabbing poses of the industrial parts placed under a standard pose in a stacking scene are generated, and a pose estimation result is obtained; the pose estimation result is evaluated by adopting a grabbing property evaluation function, wherein an expression of the grabbing property evaluation function is as follows: f1 is an evaluation value of grabbing position accessibility, f2 is an evaluation value of the relative heightof one industrial part to be grabbed, f3 is an evaluation value of the stability of the industrial part to be grabbed, f4 is an evaluation value of the grabbing angle of an end effector, and alpha i is a weight parameter corresponding to the evaluation values; and the grabbing sequence and the grabbing pose corresponding to each industrial part are determined. The grabbing stability and efficiencyare improved, and the industrial requirement is met.

The invention discloses Grabcut-based sandstone particle improved segmentation algorithm research, and provides a sandstone particle size segmentation algorithm based on an image. Firstly, a method for adaptively and automatically generating a target candidate box is provided, a foreground and background mixed model can be quickly segmented from a background image, the time for manually drawing the box is greatly shortened, and the requirement for real-time performance in an engineering field is met; secondly, the mass center of the super-pixel image of the SLIC is clustered by adopting a K-Means clustering method based on the SLIC, so that the number of samples participating in clustering can be greatly reduced; the Gibbs energy function can determine the weights of the two segmented edges; in order to reduce the number of iterations of foreground and background segmentation of an unknown label of Grabcut in a candidate box, an information entropy function with a certain weight is added to an energy function of Gibbs, segmentation information of a segmented image is supervised, and the real-time performance of the system is further optimized. The invention can be applied to real-time on-line analysis of the grain size of the sandstone in a factory.

The invention discloses a preparation method of a high temperature resistant forsterite type refractory material. The method comprises the following steps: using nickel-iron slag as raw materials and magnesia powder as additives, wherein the ratio of [w (MgO) + w (FeO)] to [w (Al2O3)+w (Cr2O3)] is 10.50 to 13.57, the ratio of w (MgO) to w (Cr2O3) is 34.90 to 48.12 and the ratio of w (MgO) to w (SiO2) is 1.19 to 1.61, adding binding agents and controlling calcination temperature to be 1360 DEG C to 1450 DEG C, inducing mineral phase reconstruction of the nickel-iron slag, optimizing transformation process of refractory crystal form (Mg2SiO4, MgO.Fe2O3, MgO.Al2O3, MgO.Cr2O3) to increase refractoriness of the refractory material. The refractoriness of the obtained refractory material is 1700 to 1800 DEG C, and the refractory material also has the advantages of high compressive strength, large bulk density, low apparent porosity, and can fully meet the industrial need of the refractory material. The preparation method of the high temperature resistant forsterite type refractory material has the advantages of high utilization rate of resources, high production efficiency, high added value, environment friendliness, easiness in process control, low production cost and the like.

The invention relates to a fixing device of a leading-out cable of a pressure sensor, and aims to solve the problems that the existing pressure sensor is damaged or measure failure is caused due to the fact that the leading-out cable is not fixed. A fastening spring screw is arranged between an outer cover of the pressure sensor and a leading-out terminal of the leading-out cable and is near to the leading-out cable after passing through the outer cover of the pressure sensor, a cable-protecting spring and a pouring sealant. Furthermore, a fastening spring screw pouring sealant ring groove is formed in the inner wall of a part in which the pouring sealant is filled, of the outer cover of the pressure sensor. Based on the arrangement of the fastening spring screw and the fastening spring screw pouring sealant ring groove, the outer cover, the cable-protecting spring and the pouring sealant of the pressure sensor and the leading-out cable are fixed into a whole after the pouring sealant is solidified, so that the leading-out cable can be firmly connected with a transmitting circuit board always no matter the pressure sensor is used under a severe environment or a vibration environment. Thus, the normal use of the pressure sensor is ensured.

The invention discloses an ultrashort pulse laser induced plasma assisted electric spark compound processing device and an ultrashort pulse laser induced plasma assisted electric spark compound processing method under action of a magnetic field and belongs to the field of laser processing and electric spark compound processing of special processing. The device compounds a laser induced plasma processing unit, an electric spark processing unit and a compound magnetic field unit together organically. The laser induced plasma processing unit comprises an ultrashort pulse laser, a laser power supply, a water cooler and a light path conversion assembly. The compound magnetic field comprises a direct current excitation power supply and an annular electromagnet. The electric spark processing unitcomprises a five-degree-of-freedom precision platform for controlling a workpiece to move expectedly. The device and the method provided by the invention sole the problem that it is hard to process alow conductivity material and achieve cross-dimension processing and the processed surface is not enough high in quality in the electric spark processing technology, and have a very wide applicationprospect.

The invention relates to a mullite corundum carbide silica brick for a joint part of a transitional zone and a firing zone of a cement kiln. The mullite corundum carbide silica brick comprises the following raw materials by weight percent: 20-0% of 5-2mm sintered mullite, 30-10% of 2-1mm sintered mullite, 20-10% of 1-0.088mm sintered mullite, 15-10% of silicon carbide less than 0.088mm, 20-10% oftabular corundum less than 0.088mm, 5-0% of 20-15mum silica powder and additionally added binding agent, wherein the mass of binding agent is 3.5-1.5% of total mass of all the raw materials; the binding agent is selected from one or two of magnesium lignosulfonate and magnesium chloride solution; proportion of the binding agent is 1.05-1.25. The mullite corundum carbide silica brick provided by the invention has excellent high temperature resistance and chemical corrosion resistance and is suitable for the joint part of the transitional zone and the firing zone of the cement kiln. Compared with 6-month service life of the ordinary mullite silicon brick, the service life of the product provided by the invention is more than 12 months.

The invention relates to the field of organic synthesis and in particular relates to a continuous production method and device of 4-chlorophenylhydrazine hydrochloride. A continuous production mannercombining tubular reaction and kettle type reaction is adopted; diazotization reaction is carried out in a tubular reactor and raw materials are uniformly mixed; the reaction is stably carried out, the safety of the reaction is improved, side reaction is reduced and the purity and the yield of a final product are improved; reduction reaction and acidification reaction are carried out in a reduction reaction kettle so that the production continuity is improved, the total reaction time is reduced, the production efficiency is improved, the energy consumption is saved and the production cost is reduced; the yield of the prepared 4-chlorophenylhydrazine hydrochloride is greater than 90 percent and the purity is greater than 96 percent; the continuous production method and device meet industrial requirements and are suitable for industrial continuous production.

The invention discloses an image-based gravel particle size detection and analysis system, which comprises a rack, discharging equipment, image acquisition equipment, light supplementing equipment, image processing equipment, a display, a sliding block and a recovery box, segmenting the sandstone image by the image processing equipment comprises the following sub-steps: firstly, taking ResNet based on a feature pyramid network (FPN) as a feature extraction network, secondly, proposing a self-adaptive ROIAlign module, mapping each suggestion box output by the RPN to all feature levels of the FPN. A multi-scale feature is adopted to obtain a maximum value through a parameter layer for fusion, finally, an IoU prediction branch is added to improve the positioning performance of a network, moreaccurate segmentation is achieved, an NMS algorithm based on positioning confidence is provided to preferentially reserve a detection frame with high positioning precision to be provided for a targetdetection branch and a mask branch. Segmentation precision is further improved. The method can be applied to real-time on-line analysis of the grain size of the sandstone in a factory.

The invention provides a temperature self-compensation double-optical-fiber coupling ball microscale sensor based on polarization state detection and belongs to the technology of the technology of manufacturing and measurement of precise instruments. The temperature self-compensation double-optical-fiber coupling ball microscale sensor comprises a polarized light generating device, a semi-transparent semi-reflective prism, a quarter lambda wave plate, a measuring probe, polarization state detection devices, a temperature compensation device and a computer, wherein the polarized light generating device, the semi-transparent semi-reflective prism, the quarter lambda wave plate and the measuring probe are arranged in sequence. The optical axis of the emergent light of the polarized light generating device and the optical axis of the incident light of the measuring probe coincide. The polarization state detection device A is located on the optical axis A of the path of reflected light formed after the emergent light of the measuring probe passes through the semi-transparent semi-reflective prism. The polarization state detection device B is located on the optical axis B of the path of reflected light formed after emergent light of a reference probe is reflected by a reflecting mirror B. When the difference value between the polarization state, detected by the polarization state detection device A, of a light beam and the polarization state, detected by the polarization state detection device B, of the light beam is changed, the measuring probe is in contact with a detected hole. The temperature self-compensation double-optical-fiber coupling ball microscale sensor has the temperature compensation function and is high in precision and high in speed.

The ultrasonic-assisted glass heat-bending device based a millimeter-wave heat source and a control method. The ultrasonic-assisted glass heat-bending device comprises a machine frame; a feeding area and a discharging area are respectively arranged on two sides of the machine frame; a furnace cavity is formed on the machine frame; a control box is arranged at one side of the machine frame; a graphite mould and a variable-frequency millimeter-wave heat source connected with the control box are arranged in the furnace cavity, wherein the frequency of the variable-frequency millimeter-wave heat source ranges from 2.5 GHz to 20 GHz, and the power is of kilowatt magnitude; a cavity is formed in the graphite mould; a preheating area, a hot bending pressurizing area, a pressure maintaining area and a cooling area are arranged on the furnace chamber; a shifting fork executing mechanism used for shifting the graphite mold is arranged on the machine frame; and the preheating area, the hot bending pressurization area, the pressure maintaining area, the cooling area and the shifting fork execution mechanism are separately connected with the control box. According to the invention, the mold is heated more uniformly, the molding rate and material surface quality are remarkably improved by assistance of ultrasonic vibration, and parameters such as temperatures, pressure and the like are controlled cooperatively in different areas, so that requirements for manufacturing 3D ultra-thin glass with high surface quality are met.

The invention discloses a special-shaped sandwich fiber product sandwich guiding pultrusion device. The device comprises a pultrusion die and a preforming module. The pultrusion die comprises a forming die cavity and a die core. The forming die cavity comprises a feed end and a discharge end. The die core penetrates through the whole forming die cavity. The preforming module comprises a preforming male die, a preforming ring, a preforming die cavity, a supporting and guiding module and a connecting and positioning module, wherein the die core extends to the outer portion of the feed end to form the preforming male die; the preforming ring is mounted on the preforming male die and can move on the preforming male die in the feeding direction; the preforming die cavity is formed by a gap between the inner side of the preforming ring and the preforming male die; the supporting and guiding module guides an upper fiber layer, an sandwich and a lower fiber layer into the preforming die cavity; the connecting and positioning module connects the supporting and guiding module with the preforming module and positions the supporting and guiding module and the preforming module. By adopting the device, the surface smoothness of fiber products can be improved, and the interlaminar shear strength and surface toughness are enhanced. The special-shaped sandwich fiber product sandwich guiding pultrusion device is suitable for automatic and continuous production of structure-complicated special-shaped fiber products.

A lithium ion battery module for an electric forklift truck, and a power supply box, which belong to the technical field of lithium ion batteries. The battery module comprises a housing and a batterypack in the housing; the battery pack comprises cells (11), an inter-cell heat insulation sheet (12), and a bottom surface insulating plate (13), a side surface insulating plate (15) and an end surface insulating plate (14) which are at the periphery of the cells (11), and a bus bar support (7) at the top; the cells (11) are square lithium iron phosphate batteries, and are grouped in a mode with each parallel branch having eight cells which are connected in series, a protruding spacer (18) is provided on the surface of the side surface insulating plate (15) and the surface of the bottom surface insulating plate (13), and the bus bar support (7) is provided with an inter-cell (11) connection bar (4) and an end connection bar (6). The power supply box comprises a box body (34), the box body(34) is internally provided with a high-voltage box (35), a BMS and the described lithium ion battery module for an electric forklift truck, a box cover (39) is provided on the box body (34), and an exhaust valve (50) is provided on the box cover (39). The lithium ion battery module and the power supply box both have high reliability in terms of structure and thermal performance.

The invention provides a double-optical-fiber coupling ball microscale sensor based on polarization state detection and belongs to the technology of manufacturing and measurement of precise instruments. The double-optical-fiber coupling ball microscale sensor comprises a laser, a polarizer, a semi-transparent semi-reflective prism, a quarter lambda wave plate, a probe, polarization state detection devices and a computer, wherein the probe is composed of an incidence optical fiber, an emergent optical fiber and a coupling ball, the laser, the polarizer, the semi-transparent semi-reflective prism, the quarter lambda wave plate and the probe are arranged in sequence. The optical axis of emergent light of the laser and the optical axis of incident light of the incident optical fiber coincide. The polarization state detection device A is located on the optical axis of the path of reflected light formed after the emergent light of the emergent optical fiber is reflected by the semi-transparent semi-reflective prism. The polarization state detection device B is located on the optical axis of the path of reflected light formed after an emergent light beam of the laser passes through the polarizer and then is reflected by the semi-transparent semi-reflective prism for the first time. When the difference value between the polarization state, detected by the polarization state detection device A, of a light beam and the polarization state, detected by the polarization state detection device B, of the light beam is changed, the probe is in contact with a detected hole for detection. The double-optical-fiber coupling ball microscale sensor is high precision and high in speed and has the three-dimensional measurement capacity.

The invention discloses a preparation method of amorphous iron-nickel phosphonate with an efficient photocatalysis oxygen production property. The preparation method comprises the following steps: (1)respectively dissolving nickel nitrate and 2-carboxyethyl phosphonic acid by using N,N-dimethyl formamide so as to obtain a solution A and a solution B; and (2) enabling the solution A and the solution B to react under a heating condition, so as to obtain the amorphous iron-nickel phosphonate with the efficient photocatalysis oxygen production property. The invention further discloses the amorphous iron-nickel phosphonate prepared by using the method, and application of the amorphous iron-nickel phosphonate as a photocatalyst. By adopting the preparation method, an amorphous iron-nickel phosphonate catalyst can be prepared by changing reaction conditions, the process operation is simple, the repeatability is high, and laboratory and industrial requirements can be met. The amorphous iron-nickel phosphonate catalyst prepared by using the method has the efficient photocatalysis oxygen production property.