531results about How to "Reduce the consumption of manpower and material resources" patented technology

The invention discloses a retinal vessel segmentation method based on combination of deep learning and a traditional method and relates to the fields of computer vision and mode recognition. According to the method, two grayscale images are both used as training samples of a network, corresponding data amplification, including elastic deformation, smooth filtering, etc., is done against the problem of less retinal image data, and wide applicability of the method is improved. According to the method, an FCN-HNED retinal vessel segmentation deep network is constructed, an autonomous learning process is realized to a great extent through the network, convolutional features of a whole image can be shared, feature redundancy can be reduced, the category of multiple pixels can be recovered from the abstract features, a CLAHE graph and a gauss matched filtering graph of the retinal vessel image are input into the network, an obtained vessel segmentation graph is subjected to weighted average, and therefore a better and more intact retinal vessel segmentation probability graph is obtained. Through the processing mode, the robustness and accuracy of vessel segmentation are improved to a great extent.

The invention relates to a method for building an intelligent substation relay protection cooperation simulation testing system. Based on a Windows multithreading operating system of a PC, aiming at related requirements for IEC61850 communication and digitization protection testing, and through reasonably allocating task priority and dispatching and communication among the tasks, a certain type IED function produced by a manufacturer can be realized on the PC through leading-in a CID (configured IED description) document representing external characteristics of different manufacturers, and the mutual coordination, interlocking and shutting relations among the IED provided by different manufacturers in process layers and spacer layers of intelligent substations can be on-line detected without needing a real IED device and under the premise that the main wiring manner of different substations is adopted, so that consumption of manual labor and material resources can be greatly reduced; and the existing IED does not stop operating when the intelligent substation is expanded and rebuilt or the IED is replaced, thereby avoiding careless mistake and error during the disassembly, transportation and reinstallation processes of the IED device.

The invention provides a method for bus origin-destination (OD) investigation by using mobile phone base station data and operating vehicle global position system (GPS) data, comprising the following steps: 1) collecting mobile phone positioning data and bus GPS data; 2) transferring the mobile phone positioning data into travel information of users; 3) extracting characteristic values from the travel information of the users; 4) analyzing the extracted characteristic values to obtain basic travel characteristics; 5) matching bus travel information with the bus GPS data to obtain bus travel characteristics; and 6) carrying out statistical process on the obtained travel characteristics, and then outputting a population travel characteristic report form. The method is based on the mobile phone positioning data and the bus GPS data and then is used for performing a series of processes on the mobile phone positioning data and the bus GPS data, thereby automatically obtaining a high-quality, high-fineness and large time-span population travel characteristic reform form from a great amount of data, intelligently acquiring the population travel characteristics, reducing manpower and material resource consumption and improving the accuracy and effectiveness of the investigation.

The invention provides a method for constructing an ontology base in mobile application, which comprises the following steps of: respectively carrying out matching on titles and introduction texts in mobile application in a database in a pre-generated concept tag set and a pre-generated attribute tag set and distributing weight values to matched concept tags and attribute tags; according to the concept tags of which the weight values are sorted from high to low, acquiring a concept tag path from a pre-generated concept tag tree; according to the concept tags in the concept tag path, inquiring an incidence relation of the pre-generated concept tags and the pre-generated attribute tags so as to obtain the attribute tags; and labeling the mobile application by utilizing the acquired concept tag path and the related attribute tags. The invention also provides a system for constructing the ontology base in mobile application. According to the technical scheme provided by the invention, the concept tags and the attribute tags can be automatically and efficiently labeled for the mobile application.

The embodiment of the invention discloses an image processing method and electronic equipment; the method comprises the following steps: converting an original pathology image into a result pathologyimage that satisfies target image parameters; taking an image area containing cells in the result pathology image as a target area; segmenting cells in the target area so as to obtain a segmentation result. The method can automatically detect and segment cells in the pathology image, thus reducing manpower and material consumption, preventing diagnosis errors caused by artificial participation, and improving the cell detection and segmentation precision.

The invention discloses a desert riparian forest spatial distribution obtaining method based on GIS buffer area analysis, wherein the method belongs to the field of drought area vegetation remote sensing technology. The method comprises the following steps of a first step, downloading a TM remote sensing image of a location with a drought area river, performing image preprocessing, remote sensing interpretation and NDVI calculation on the remote sensing image, and obtaining NDVI remote sensing data of the desert riparian forest; a second step, extracting a riverbank boundary vector line, and performing unified registering and correction on the remote sensing image in a GIS platform; a third step, generating a riverway peripheral multiple-buffer-area vector picture according to a research requirement; and a fourth step, overlapping the multiple-buffer-area vector picture and the NDVI remote sensing data of the desert riparian forest, extracting an NDVI mean value in each buffer area, using a vertical riverawy distance as an independent variable and using the NDVI mean value as a dependent variable, and performing desert riparian forest spatial distribution structure analysis by means of curve fitting. The desert riparian forest spatial distribution obtaining method supplies a beneficial reference for determining continuous gradient distribution of the desert riparian forest and the protecting range thereof.

The invention provides an autonomous dynamic sealing and gas extraction intelligent system for a coal mine, which is suitable for underground sealing and gas intelligent extraction in the coal mine. The autonomous dynamic sealing and gas extraction intelligent system comprises a gas reservoir connected with a gas extraction tube; the gas reservoir is connected with an automatic gas extraction pump for automatically adjusting the extraction negative pressure; the gas extraction tube positioned nearby a borehole is connected with an automatic gas concentration detector; five groups of polyurethane sealing bags are wound outside the gas extraction tube positioned in a coal bed; five groups of plugging cloth capable of being tightly fitted with a coal wall are wound outside the polyurethane sealing bags; a stocker is connected with an automatic feed pressure control pump through a feed pipe; the feed pipe positioned in the coil bed is colligated between the polyurethane sealing bags and the plugging cloth; data signals of the automatic gas concentration detector, the automatic gas extraction pump and the automatic feed pressure control pump are connected with a data line integrator through a data collection line; and the data line integrator is connected with an automatic monitoring controller through a data line. The autonomous dynamic sealing and gas extraction intelligent system has the advantages of simple structure, convenience in operation, convenience in intelligent control and better use effects.

The invention discloses a two-sided drilling combined machine tool and relates to the technical field of cold machining machine tools. The two-sided drilling combined machine tool comprises a control box, a main motor and a rack, wherein a conveying belt is arranged in the middle of the rack; the control box is arranged on one side of the feed side beside the rack; the main motor is connected with the conveying belt by a transmission mechanism; workbenches are arranged on the top of the rack; the workbenches are arranged at two sides of the conveying belt; bottom hole processing devices, orifice chamfering devices and tapping devices are symmetrically arranged at two sides of the conveying belt; the main motor, the bottom hole processing devices, the orifice chamfering devices and the tapping devices are connected with the control box; clamp bodies are arranged on the conveying belt at intervals; the clamp bodies are used for clamping to-be-processed box bodies; and two ends of the clamp bodies are matched with the workbenches at two sides by pin rollers. The main motor drives the conveying belt to drive the to-be-processed box bodies clamped on the clamp bodies to pass bottom hole processing work stations, orifice chamfering work stations and tapping work stations in sequence, so that drilling and tapping are finished, the labor and material consumption is reduced, and the processing efficiency is improved.

An embodiment of the invention discloses an electronic medical record filing management system and an electronic medical record filing management method. The electronic medical record filing management system comprises the components of a medical record generating server, an inspection report generating server and a medical case generating server, wherein the medical record generating server is used for receiving the electronic medical record of a target patient and transmitting the electronic medical record of the target patient to the medical case generating server. The medical case generating server is used for receiving the electronic medical record of the target patient, wherein the electronic medical record of the target patient is transmitted by the medical record generating server. The medical case generating server transmits a searching request which aims at the inspection report of the target patient to the inspection report generating server, and receives the inspection report which returns from the inspection report generating server. The medical case generating server generates the electronic medical case of the target patient. The inspection report generating server is used for transmitting the searched inspection report to the medical case generating server. The electronic medical record filing management system provided by the embodiment of the invention does not require manual acquisition for the medical record and the inspection report of the target patient by personnel in a medical case room, thereby effectively reducing manpower and physical resource consumption and improving medical case filing efficiency.

The invention discloses a method for designing a wireless power transmission device. The method comprises the following steps of: A, winding and installing a transmitting coil, a transmitting end amplifying coil, a receiving end amplifying coil and a receiving coil of the wireless power transmission device according to the design requirements and the given conditions; B, measuring electric parameters of the transmitting coil, the transmitting end amplifying coil, the receiving end amplifying coil and the receiving coil; C, establishing a multi-coil coupled wireless power transmission device system circuit model based on a mutual inductance model by using the actually measured electric parameters of the coils; D, setting an optimization object function and constraint conditions, and establishing a nonlinear programming model; E, solving a nonlinear programming problem to obtain a resonance compensation capacitance value; and F, configuring a capacitor according to the calculated resonance compensation capacitance value.

The invention discloses an intelligent garbage recovery system and a dustbin overflow processing method; the intelligent garbage recovery system comprises an intelligent dustbin, an intelligent garbage truck, a wechat mini app client end and a host computer monitoring center; the intelligent dustbin comprises a dustbin body, a dustbin controller, a garbage detector, a dustbin cover turning device,a dustbin positioning device and a dustbin communication device; the dustbin positioning device can position through GPS. The dustbin can detect garbage through an infrared paired transistor; when the garbage in the dustbin reaches certain height and blocks the infrared rays, a garbage overflow alarm signal can be triggered; compared with the prior art, the garbage quantity detection mode is higher in accuracy; the Zigbee network technology and the GPRS communication mode technology are combined, thus reducing the expensive cost of an existing intelligent dustbin employing the GPRS network communication.

The invention discloses a method for automatically extracting the tree height of a standing forest having high canopy density based on TLS and UAV. By utilization of UAV photographic measurement pointcloud data and ground precise point cloud data, the highest point and the lowest point of an individual tree are extracted; according to an individual tree positioning coordinate and automatic identification highest point information, the judged highest point and a positioning point are projected in a xoy plane; the identification accuracy is judged; and thus, a tree height value is rapidly extracted. The cost is reduced; the efficiency is increased; furthermore, on the premise that the tree height extraction precision is increased, partial manual survey is replaced; a lot of manpower and material resource consumption can be reduced; a test result shows that: the tree height extraction method provided by the invention has relatively high precision for tree height estimation of an artificial metasequoia forest; the tree height extraction value whole is closer to the actual measured value; and furthermore, the method in the invention also makes effective recommendations for forest resource assessment and business planning of small and medium-sized farms.

The embodiment of the invention provides a testing system and method. The testing system comprises an upper computer, an ADAS test rack and a tested controller. The upper computer is used for receiving test parameters input by input equipment, generating a control instruction according to the test parameters and sending the control instruction to the tested controller. The ADAS test rack is used for generating a controlled object simulating model, and a tested virtual vehicle is obtained through joint constructing of the controlled object simulating model and the tested controller. The testedcontroller is used for receiving the control instruction sent by the upper computer and controlling the virtual vehicle to complete virtual test aiming at an ADAS function system according to the control instruction. When the testing system and method are applied for testing, testing can be conducted through the mode of combination of the virtual vehicle, the virtual scene and the real controller,consumption of manpower and material resources is greatly lowered, and meanwhile, the influence on personal safety and the vehicle loss in the real vehicle testing process is avoided.

The invention discloses a method for extracting tree heights by the aid of unmanned aerial vehicles and ground-based laser radar combined with the same, and belongs to the technical field of forest resource dynamic monitoring. The method includes acquiring point cloud data of forest surface layers from two-dimensional images of the unmanned aerial vehicles; acquiring point cloud data of crown canopy lower layers by the aid of ground-base laser scanners; introducing real-time kinematic (RTK) data; registering the point cloud data of the forest surface layers and the point cloud data of the crown canopy lower layers to obtain metasequoia glyptostroboides tree height information in the same coordinate reference system. The method has the advantages that respective merits of the data from twodifferent sources can be complemented by one another, and accordingly the tree height acquisition precision can be improved under the condition of high crown density of tall arbors; manual ground survey can be replaced with the method to a certain extent, accordingly, the cost can be saved, and the efficiency can be improved.

The invention provides a membrane bioreactor device for retarding membrane pollution and a sewage treatment method. The membrane bioreactor device is characterized in that a three-phase separator is arranged in a membrane bioreactor, and a sewage treatment device with a membrane reaction zone at the upper part and a contact oxidation zone at the lower part is formed; sewage enters the contact oxidation zone from the bottom of the reactor and then enters the membrane reaction zone from a slit of the three-phase separator; under the combined action of the absorption of activated sludge and the interception of membranes, the treatment of the sewage is realized; with the adoption of a rotating membrane filtering component, the rotating shear force is increased to retard the membrane pollution, and meanwhile, the fact that all the membranes have uniform cleaning strength is guaranteed, and cleaning dead corners are reduced; the three-phase separator is connected with a gas guide tube, so that residual gas in the contact oxidation zone is guided into the membrane reaction zone at the upper part to be used as a gas washing source of a membrane component, therefore the energy consumption is reduced; online ultrasonic cleaning and chemical cleaning equipment is arranged to reduce the assembly and disassembly procedures in the membrane cleaning process. The sewage treatment device and method have the advantages of high treatment efficiency, small membrane pollution, stable effluent water quality and good convenience in operation and management.

The invention provides the technical field of cast-in-place concrete pavement. Templates and a foundation are fixed through ground nails, a construction concrete vibrating operation platform spans the templates of two sides of the construction concrete vibrating operation platform, manual material distribution and preliminary concrete vibrating leveling can be carried out by using the construction concrete vibrating operation platform when feeding of local pump trucks is not in place; on the basis of the cast-in-place concrete water collecting and plastering surface, surface galling treatment is carried out, and rolling and galling to concrete are conducted through a concrete pavement galling device; when template joints are treated and reinforcing mesh is manufactured and installed in concrete pavement expansion joints, reserved joint supports are installed at the joints, when the cast-in-place concrete pavement is finished, a certain strength is reached, limit support strips are removed first, then the reserved joint supports are pulled out of upwards, the reserved expansion joints are cleaning up, and after curing of the concrete pavement is finished, the concrete pavement is thoroughly cleaned up and filled with joint filling materials such as asphalt mortar; and cast-in-place concrete needs to be cured after completion, an automatic spraying film laminating machine and coiling block curing films are used for spraying water and covering the curing films on the cast-in-place concrete pavement.

The invention relates to a bus line station optimal arrangement method maximizing space-time reachability. The method comprises the following steps: determining an arrangement position and a direction of a single bus line, and obtaining a bus line arrangement line; acquiring passenger trip aggregation point data; acquiring city activity facility point data; acquiring walking network data along the bus line, and associating the walking network data with the bus line arrangement line, passenger trip aggregation points and city activity facility points; calculating total trip time from the trip aggregation points to the activity facility points; determining whether a sum of the total trip time and stay activity time is greater than total available time; constructing a bus line station optimal arrangement model; and obtaining a bus line station arrangement scheme maximizing the space-time reachability by use of a genetic algorithm. According to the invention, through introducing the space-time reachability as an object function, an optimal bus line station arrangement scheme is obtained, and the arrangement scheme satisfies the trip purpose demands of travelers and improves the service level of the bus line.

The invention provides a method for rapidly fixing a micro-quake sensor underground. The fixing method is characterized in that on the basis that an anchor rod (11) provided by the support way of an underground coal roadway driving working surface anchor rod (11) is taken as a carrier, the conventional buried type installation way is changed, and a sensor and the anchor rod (11) are fixedly connected integrally by rapidly fixing the micro-quake sensor device underground. The device comprises an outer cover and a connector, wherein the outer cover consists of a bottom plate (2), a cover body (3), an external sound wave insulating material (4) and closing holes (5), wherein the connector consists of a protruding shaft (7), a baffle plate (8) and a fixing bolt (9). By adopting the method, a series of problems of complex installation procedures, high time consumption, difficulty recovery and the like in the conventional micro-quake sensor installation way are solved. Rapid installation and detachment of the sensor are realized. Moreover, the cover body provided by the device can be used for fixing and protecting the sensor, and plays a role in insulating and eliminating noise.

The invention provides unmanned aerial vehicle battery replacing equipment. The unmanned aerial vehicle battery replacing equipment comprises a rack, a parking platform, a battery bin, a three-axis moving platform and a mechanical claw device. The parking platform, the battery bin and the three-axis moving platform are fixed to the rack, and the mechanical claw device is arranged on the three-axismoving platform. The three-axis moving platform drives the mechanical claw device to move to the battery bin and the parking platform, and the mechanical claw device takes out or places an unmanned aerial vehicle battery from the battery bin or the unmanned aerial vehicle. According to the unmanned aerial vehicle battery replacing equipment, the operation of replacing the battery of the unmannedaerial vehicle on the parking platform can be quickly carried out; intervention of professional operators is not needed, so that the use threshold of the unmanned aerial vehicle is reduced, the intelligent degree is improved, consumption of manpower and material resources is reduced, and the unmanned aerial vehicle is particularly suitable for some complex environments, and the working risk of theprofessional operators is reduced.

The invention discloses a tea green tedding machine, the structure of which is: a shaking machine driven by a power machine to shake up and down is arranged on the rack, the shaking output end of the shaking machine is fixed with a supporting plate, on which a screen unit is fixed through a plurality of springs, and a screen unit baffle is arranged around the screen unit. The shaking machine drives the supporting plate to bounce up and down and twitter the screen unit by the buffer of the spring, thus evenly dispersing the tea green all around, effectively replace manual operation, lowering the consumption of manpower and material resources and improving the working efficiency and the yield of tea green, with the tea green distributed evenly.

The invention discloses a target positioning method, and a server and a base station for target positioning, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: storing map data of a region and coordinate information of each base station on a map; determining a state index value of current communication between each base station and the positioning tag according to the data reported by each base station; judging whether the state index value of the current communication between each base station and the positioning tag meets a preset condition or not, and if so, calculating a first position coordinate of the target according to the coordinate information of each base station, the receiving time for receiving the coordinate point uploaded by the positioning tag and the sending time for uploading the coordinate point by the positioning tag; otherwise, calculating a second position coordinate of the target according to the coordinate information of each base station and the laser radar communication data generated by each base station. According to the method, the target can be accurately and quickly positioned with highprecision, the special requirement of the nursing home for positioning the old people is met, the deployment cost is reduced, and the manpower and material resource consumption is reduced.

The embodiment of the invention discloses a method, device and equipment for carrying out three-dimensional reconstruction on a two-dimensional image and a storage medium, and belongs to the technicalfield of image processing. The method comprises steps of obtaining a two-dimensional picture set; performing feature point extraction on a single picture in the two-dimensional picture set to obtaina feature point set; obtaining the size of the picture and the position information of the feature points in the feature point set in the corresponding picture; acquiring position information of the feature points in a world coordinate system based on an OpenCV camera calibration method; based on an LSD straight line detection method and the position information of the feature points in the worldcoordinate system, obtaining a horizontal line segment in the picture; constructing a three-dimensional grid chart corresponding to the picture based on a constraint Delaunay algorithm; and combiningthe three-dimensional grid diagrams constructed by the pictures in the two-dimensional picture set to obtain a three-dimensional surface model of the object, thereby completing three-dimensional reconstruction. According to the invention, three-dimensional simulation reconstruction can be carried out on the two-dimensional picture rapidly and accurately; and the manpower and material resource consumption during three-dimensional reconstruction can be reduced.

The invention provides a performance parameter testing system of an air conditioner and an air conditioning system. The performance parameter testing system is applied to a control system of the air conditioner, and comprises a detection mode setting module, a data transmission module, a parameter storage module and a working condition testing module; a detector only needs to do corresponding operation so that the detection mode setting module outputs a corresponding detection mode instruction; the working condition testing module can detect an optimal operation parameter matched with the detection mode instruction in a plurality of groups of pre-set optimal load operation parameters from the parameter storage module according to the detection mode instruction, and can control the air conditioner to operate according to the optimal operation parameter; the corresponding load operation parameters do not need to be changed for a plurality of times in a testing process, so that the working amount of detection can be reduced and the consumption of manpower and material resources is further reduced.

The invention discloses a video monitoring coverage rate calculation method and device, and a video monitoring layout method and system. A virtual three-dimensional model of a whole monitoring area is established through three-dimensional modeling; layout of virtual cameras is carried out in the three-dimensional model; a monitoring coverage area of each virtual camera, a monitoring coverage total area of all virtual cameras and a total area of the whole monitoring area are calculated accurately; and therefore, a video monitoring coverage rate of the whole monitoring area is calculated accurately. A virtual camera layout scheme can be adjusted according to the monitoring overage rate demand of a user. The layout of the virtual cameras in the whole monitoring area can be further optimized; and the video monitoring coverage rate of the whole monitoring area can be improved. Finally, the layout information of all virtual cameras can be output and is used for instructing layout construction of onsite real cameras. The layout accuracy of the onsite real cameras and the onsite construction efficiency can be improved.

The invention discloses a device and a method for controlling waste gas. The device comprises an absorption-liquid circulation groove, a cyclone absorption tower connected with the top of the absorption-liquid circulation groove through pipelines, as well as an adsorber of which one end is connected with the top of the cyclone absorption tower and the other end is connected with a liquid drainage port, wherein the cyclone absorption tower comprises a tower body, a gas-liquid-mixing cyclone blade group, a demisting cyclone blade group and a liquid inlet pipeline, and the upper and lower ends of the cyclone absorption tower are provided with a gas inlet pipeline and a gas outlet pipeline respectively. The method comprises the steps of blasting coating waste gas through a fan, allowing the coating waste gas to enter the cyclone absorption tower and the adsorber from an air inlet and treating the coating waste gas. The invention solves system failure caused when viscous components block equipment in the treatment of the coating waste gas containing the viscous components, reduces the time for shutdown maintenance caused by the equipment, as well as the consumption of manpower and material resources, and also solves the problem that the absorption method for controlling waste gas cannot reach standards. A technical system in the invention has high purification efficiency and can completely meet the requirements of national atmospheric pollutant emission standards. The system has the advantages of low resistance, low energy consumption, reliable operation and simple maintenance.

The invention discloses an AIS big data-based marine transportation statistical system and a statistical method thereof, and aims to form a specific basic database and a data analysis model through continuous data mining and experience accumulation on the basis of real-time and historical AIS data in combination with mining knowledge bases such as ship archives, port data and investigation and survey data under the assistance of online processing and finally automatically and regularly output statistical indexes such as ports, offshore channels and goods transportation volume, and dynamic information related to various commodities and ships, and support open type editing operation, visual interactive display and report export. According to the statistical system and the statistical method, an AIS big data platform oriented to sea transportation statistics is provided, a sea transportation statistics AIS big data mining analysis model is constructed, and a whole set of technical solutions of AIS data access, cleaning, storage management, mining analysis, index product generation and the like are formed; and a high-quality, timely and accurate marine transportation industry statistical index product can be provided for marine economic management.

The invention discloses automatic carton stacking equipment and a using method thereof. The automatic carton stacking equipment comprises a steering mechanical hand and an automatic glue spreading machine, and further comprises a material grabbing conveyor belt connected to the output end of the unloading conveyor belt; the automatic glue spreading machine is arranged at the upper side of an unloading conveyor belt; a joint of the material grabbing conveyor belt and the unloading conveyor belt is equipped with an unloading limiting mechanism capable of limiting cartons from moving; the output end of the material grabbing conveyor belt is equipped with a material grabbing limiting mechanism; the unloading limiting mechanism is in signal connection to the steering mechanical hand; and transmission speed of the material grabbing conveyor belt is higher than that of the unloading conveyor belt. According to the automatic carton stacking equipment disclosed by the invention, the unloading limiting mechanism and the material grabbing limiting mechanism are arranged, so that the steering mechanical hand can be automatically started after the cartons pass through the unloading limiting mechanism, and the steering mechanical hand can grab the cartons when the cartons stop at the material grabbing limiting mechanism, and therefore, the steering mechanical hand conveniently grabs the cartons one by one, working efficiency is improved, and a great deal of labor power is released.

The invention relates to the field of PCB coding, and provides a direct coding method for a PCB. The direct coding method comprises the following steps: directly coding the PCB by using a carbon dioxide laser, wherein the size of the focus light spot of the carbon dioxide laser is equal to or smaller than 0.14 mm; aiming at two-dimensional codes or one-dimensional codes in different sizes requested on different PCBs, coding is realized by controlling the power of the carbon dioxide laser and selecting different coding modes. The high-precision, high-speed and programmable carbon dioxide laser is adopted to directly code the PCB, aiming at two-dimensional codes or one-dimensional codes in different requested sizes, the coding depth can be controlled by controlling the power of the carbon dioxide laser, and appropriate coding modes are selected, so that the PCB is not damaged in the coding process, automation can be achieved in the production process, and the labor and the materials can be saved; laser coding is not affected by assembling steps or environment, can be directly acted on the PCB, and the process lasting property is good, so that the effect that the code lasts for the whole life of the PCB is achieved.

The invention discloses a bus shelter. The bus shelter comprises a bus shelter body and further comprises a solar energy system, a transmission system, a central control unit and a stop board device. The solar energy system is connected with the central control unit and the stop board device through the transmission system and is used for converting collected solar energy into electric energy, storing the electric energy and supplying power; the central control unit is connected with the stop board device through the transmission system and is used for controlling the operation of the stop board device; the stop board device comprises an electronic stop board, is controlled by the central control unit and is used for displaying information. According to the bus shelter, an intelligent bus shelter is achieved, wastes of paper public route stop boards can be effectively reduced, and a latest route map can be timely provided for passengers.

The invention discloses a cutting tool wear monitoring method based on a multiscale deep convolutional recurrent neural network. The method comprises the following steps of building an input matrix based on cutting tool data preprocessing data measured by a multipath sensor; building a multiscale convolutional neural network, obtaining multiscale characteristics, carrying out characteristic fusionon each branch of the multiscale convolutional neural network based on the output after pooling a maximum value, and finally obtaining the multiscale characteristics; building a deep cycle GRU network for extracting characteristics and expressions of different time scales, wherein the deep cycle GRU network comprises a first layer of GRU network and a second layer of GRU network, the unit numberof the second layer of GRU network is more than the unit number of the first layer of GRU network, and after the multiscale characteristics are processed through the deep cycle GRU network, the characteristics and the expressions of the different time scales are obtained; building a full connecting layer based on the characteristics, and mapping the characteristics to a sample marking space; and building a linear regression layer based on an output result of the full connecting layer, and obtaining a cutting tool wear capacity.