123results about How to "Reduce manual inspection costs" patented technology

The invention relates to a high-precision deformation monitoring method of a wide-area electric iron tower based on a Beidou system. The high-precision deformation monitoring method comprises the following steps: judging whether real-time dynamic centimeter-grade monitoring requirements are met or not according to monitoring precision of a Beidou foundation CORS network; if so, obtaining iron tower monitoring data through a network RTK virtual reference station method; otherwise, obtaining the iron tower monitoring data through a double-monitoring-point base line attitude measurement method; processing and analyzing the monitoring data, and calculating an inclined angle and a sedimentation value of the iron tower; if the inclined angle and the sedimentation value of the iron tower exceed limit requirements of operating regulations of a power transmission line, determining a tower position coordinate and issuing a field inspection and maintenance instruction; if the inclined angle and the sedimentation value of the iron tower do not exceed the requirements of the operating regulations of the power transmission line, judging an inclining trend of the iron tower. The monitoring method provided by the invention can be used for carrying out all-weather, all-time and automatic monitoring on the wide-area electric iron tower; potential safety hazards are found and warned in time, and the manual inspection cost is effectively reduced.

The invention provides a cable insulation state online automatic monitoring and diagnosis system. A real-time data acquisition module acquires discharge data of a cable; a data automatic analysis and processing module processes and analyzes the data and calculates earth leakage capacitive reactance and impedance of the cable, expresses change of the cable insulation state through the change trend of earth leakage capacitive reactance and impedance, sets an early warning threshold with an average value obtained through long term of measurement and calculation acting as a reference value and compares a real-time measurement result with the reference value to obtain relative deviation which is compared with the early warning threshold; a change curve drawing module draws a real-time cable insulation change curve so as to obtain a cable insulation change trend curve and draw an impedance change curve; a cable insulation fault early warning module performs early warning; and a database module is used for storing the acquired data and the results of the aforementioned modules. Monitoring and fault diagnosis can be automatically performed so that the aspect of accuracy of cable insulation monitoring and fault line selection can be powerfully and reliably guaranteed.

The invention discloses an AOI character defect detection method based on industrial machine vision. The AOI character defect detection method comprises the steps that a to-be-detected image is acquired; the to-be-detected image is preprocessed to obtain a character-containing region-of-interest image of which the position is corrected; the region-of-interest image of the to-be-detected image is separated to obtain a character region image; template matching is carried out on the character region image of the to-be-detected image and a pre-created reference image template to obtain a templatematching result; whether the to-be-detected image has character defects or not is judged according to the template matching result; and a character defect judgment result is outputted. According to the method, the defects of the ROI can be detected under the condition of a low-pixel grey-scale map through template matching, the detection efficiency and the accuracy are improved, and the detectionlabor cost is reduced.

The invention provides an inferior-quality product detection and elimination system of a capsule filter rod forming machine and a use method thereof. The system comprises a detection device and an elimination device. The detection device comprises an image acquisition device arranged between a bar breaking device and a leading-in cutting device. The image acquisition device is right above a conveying device. The image acquisition device is connected with a controller and an image processor. The image processor is connected with the controller. The elimination device comprises a cigarette dividing wheel body. The circumferential direction of the cigarette dividing wheel body is uniformly provided with a plurality of separating bars used to connect with capsule filter rods. The cigarette dividing wheel body is also provided with an elimination electromagnetic valve connected with the controller. The elimination electromagnetic valve is connected with a blowing pipe. An air outlet end of the blowing pipe faces the outer part of the cigarette dividing wheel body. The system can detect positions of capsules in capsule filter rods in a production process of the capsule filter rods, to detect inferior-quality products and eliminate the inferior-quality products. The system solves problems of capsule missing and longitudinal bias over-standard.

The invention discloses an automatic inspection method based on simulated user behaviors. The automatic inspection method specifically comprises the following steps: analyzing the page information of a user system; automatically inspecting scripts by a programming system; generating an inspection client program package; starting a client program and posting back data on time; and automatically generating an inspection report. According to the automatic inspection method, the behavior of visiting the system in a browser by a user can be simulated, automatic visiting inspection can be performed on common functions of the system, meanwhile the screen a visited page is shot, and comprehensive analysis is carried out after the data is combined so as to form a daily inspection report and fault comprehensive analysis of the system, so that comprehensive monitoring for an operation system is further promoted, associated support is provided for system optimization, and the manual inspection cost is greatly reduced.

The invention relates to a retaining wall crack identification method based on a CNN and an SVM. An unmanned aerial vehicle equipped with a monocular camera is adopted to collect and establish a retaining wall crack identification database; image data preprocessing and data enhancement are carried out; a retaining wall crack recognition algorithm model is established based on the CNN and the SVM;the algorithm model is trained to obtain an optimal retaining wall crack recognition algorithm training model; the unmanned aerial vehicle collects retaining wall pictures in real time and uploads theretaining wall pictures to the upper computer through a cloud network; and the upper computer carries out preprocessing and carries out crack identification on the picture of the retaining wall by using a pre-trained model. Based on the images collected by the unmanned aerial vehicle, the cracks of the retaining wall can be accurately recognized through the intelligent algorithm, the retaining wall can be repaired easily, the manual inspection cost is reduced, and the efficiency is improved.

The invention relates to the technical field of manufacturing of air compressors, in particular to an air tightness detecting device of an air compressor crankcase. The device comprises a base, a water tank, a vertical lifter and a crankcase sealing component, wherein the water tank is put on the base; the vertical lifter is mounted on the water tank through a support frame, and comprises a lifting table, a vertical guide column and a lifting driver; the crankcase sealing component is mounted on the lifting table, and comprises a vertical end cover set relatively moving in the vertical direction and a horizontal end cover set relatively moving in the horizontal direction; and an air inlet hole and an air inlet pipe joint are arranged on the horizontal end cover set. The device satisfies the air tightness detection of crankcases with different specifications through the vertical end cover set and the horizontal end cover set, has the characteristics of simple operation and quick detecting speed, largely reduces the manual detecting cost, and solves the wrong detecting condition in manual detection.

The invention discloses a goods recall warning system based on electronic traceability data. An enterprise reports production, purchase and sales records, and an enterprise inventory record and a goods supply chain are formed. When the enterprise finds potential safety risks exist in a certain batch of goods, goods recall is initiated, the system can precisely display the sales and the inventory of the batch of goods in the supply chain, and a recall progress is controlled; when a consumer buys a goods, through traceability query, the system retrieves whether the goods is in a recall state, the consumer is warned that the goods is recalled, and cautious buying is warned; a circulation enterprise can receive a notice in real time, the recalled goods is locked, the sales and the inventory of the goods of the enterprise can be displayed through the system, and manual investigation cost is reduced; and as for a consumer who already buys the goods, if the buying is registered in the system, the system automatically sends a warning notice, and the consumer is reminded to return the goods. Accurate display of the storage condition and the sales condition of the enterprise in the supply chain is supported, the recall process is processed, and the recall process is controlled.

The invention discloses an intelligent lighting control system which comprises a central lighting master control terminal, and a steam engine room lamp control system, a stair lamp control system, a power distribution room lamp control system, a conference room lamp control system and a centralized control room lamp control system which are connected with the central lighting master control terminal. The central lighting master control terminal is connected with the steam engine room lamp control system, the stair lamp control system, the power distribution room lamp control system, the conference room lamp control system and the centralized control room lamp control system through communication equipment. Subsystem power-on and power-off control instructions are sent to the lamp systems through the radio communication system, and meanwhile the lamp systems return subsystem parameters to the central lighting master control terminal through the radio communication system; the intelligent lighting control system adopts an intelligent LED lamp control system, so that the manual inspection cost can be reduced, and the management quality and the working efficiency are improved; the service life of the lamp is prolonged and secondary investment cost is saved.

The invention discloses a portable device for detecting the depth of an engraved character. The device comprises a mechanical casing body, a clamping mechanism, rollers, a display screen and a laser triangulation optical path unit. The laser triangulation optical path unit includes a linear laser, a reflecting mirror, a lens and an image sensor; a filter piece is arranged between the image sensorand the lens; and a glass window is arranged at the bottom of the mechanical casing body. In addition, the invention also discloses a method for detecting depth of an engraved character. A trigger signal is generated; 3D contour data of a character surface are sampled and character characteristic data represented by a character scanning contour line are calculated; and then a character detection result is finally displayed. Therefore, non-contact comprehensive detection of the depth or height of the coded character, the size of the character, and the distance between adjacent characters can berealized; the manual detection cost during the process of motor vehicle manufacturing and annual inspection can be lowered; the detection accuracy and detection efficiency can be improved; and the technical problems existing in the industry can be solved.

The invention relates to an intelligent monitoring system for a wind power blade assembly mold. The intelligent monitoring system comprises a sensor, a signal acquisition and transmission system and acontrol system; the sensor comprise a plurality of vacuum degree sensors, a temperature sensor and a plurality of laser displacement sensors, and the laser displacement sensors are used for detectingthe width of a mold closing joint and the axial and chordwise dislocation degree of the mold closing joint; the multiple vacuum degree sensors are respectively installed on vacuumizing pipelines at the rear edge of an upper mold and the rear edge of a lower mold; the temperature sensor comprises a plurality of thermal resistors pre-buried in the surfaces of the upper mold and the lower mold, andthe thermal resistors are uniformly distributed on the whole surfaces of the upper mold and the lower mold; and the upper mold and the lower mold are divided into a plurality of areas, each area is provided with a data acquisition module, each data acquisition module is used for acquiring sensor data of the area nearby and sending the sensor data to an upper computer of the control system, and theupper computer monitors and displays the sensor data in real time. Parameters of the molds are fed back comprehensively, centrally and online, and the production efficiency and the product quality are improved.

The invention discloses a power distribution room equipment fault analysis and pre-judgment method and device based on edge computing, and the method comprises the steps: collecting the state quantitydata of a power distribution room sensing terminal, carrying out the normalization processing, and forming a sample data set; constructing a deep learning model based on a deep convolutional network,inputting the sample data set for identification training, and stopping training until an output identification result is consistent with a training sample label; performing fusion analysis on the state quantity by using the trained deep learning model; identifying and positioning abnormal sounds of multiple partial discharge sources and equipment for the plurality of sensing terminals in combination with a collaborative edge strategy; and judging the fault state of the power distribution room equipment based on the fusion analysis result and the identification positioning result. According to the invention, the manual inspection cost is effectively reduced, and information and data are acquired in real time; in addition, based on integrated judgment of a fusion analysis result and an identification positioning result, the accuracy of equipment fault judgment is improved.

The invention discloses an on-road berth shielding detection method and a device, and the method comprises the steps: determining whether the state of a to-be-detected berth is idle according to an image photographed by a camera installed in a road, of the to-be-detected berth; wherein the berth to be detected is located in the shooting range of the camera; if it is determined that the state of the to-be-detected berth is idle, performing key point detection on the to-be-detected berth according to a neural network; and determining whether the to-be-detected berth is shielded according to thedetected key points. According to the method, the key points are arranged on the berth, and whether the berth to be detected is shielded can be judged by detecting the key points, so that charging errors caused by shielding of the berth are avoided, and the manual troubleshooting cost of inspectors can be reduced.

The present invention discloses a method for inspection of a logistics transportation route optimization result. The method comprises four portions consisting of transportation event data collection,simulation of a transportation event, regulation of a transportation route and evaluation of an optimization result. The method for inspection of the logistics transportation route optimization resultcan rapidly simulate actual transportation events in batch to greatly reduce a manual inspection cost; the method can predetermine the transportation events in advance and can give a regulated distribution route and sequence to greatly improve an on-time rate in the actual distribution and save the transport capacity cost; and moreover, the method can calculate a transportation event probabilityaccording to the hundreds of thousands of true truck tracks to effectively avoid errors which are probably generated in manual collection and recode to allow the simulation events and the reality to be high in similarity and guarantee the accuracy of the implementing degree of the optimization result.

The invention discloses a monorail train contact and non-contact online detection steel beam, and relates to the technical field of train detection, the steel beam comprises a base and a steel beam body fixed above the base, a plurality of horizontal wheel abrasion detection devices, horizontal wheel pressure detection devices, collector shoe pressure detection devices, collector shoe abrasion detection devices and at least one walking wheel abrasion detection device facing the upper side are arranged in the steel beam body, wherein the horizontal wheel abrasion detection devices, the horizontal wheel pressure detection devices and the collector shoe pressure detection devices face the front side and the rear side respectively. The horizontal wheel pressure detection device and the collector shoe pressure detection device penetrate out of the side faces of the corresponding sides of the front side and the rear side of the steel beam body. Square holes matched with the corresponding horizontal wheel abrasion detection devices, the corresponding collector shoe abrasion detection devices and the corresponding walking wheel abrasion detection devices in position are formed in the frontside face, the rear side face and the upper side face of the steel beam body. According to the steel beam, online real-time detection is realized, networked, visual, cooperative and integrated management is realized, the manual detection cost and error are reduced, and the detection efficiency is improved.

The invention provides a detection method, system and device for detecting abnormal behaviors of a user and a storage medium, and the method comprises the steps: converting a user behavior log into adiscrete symbol sequence; abstracting the user behavior log into a user behavior sub-graph according to the symbol sequence; and performing sub-graph mining on the user behavior sub-graph to obtain anabnormal behavior coefficient, and judging whether the user behavior log is abnormal or not according to the abnormal behavior coefficient. According to the detection method provided by the invention, consistency description is carried out on a large number of heterogeneous user behavior logs existing in an enterprise, fusion of heterogeneous information is achieved, and then a graph mining algorithm is utilized to detect abnormal behaviors of internal users. The complementarity among the user behavior logs can be effectively found and utilized, so that the behavior of the user is reflected from different sides, and the anomaly detection and identification are more accurate and effective. Meanwhile, the automatic detection method reduces the manual detection cost, and greatly improves thedetection efficiency.

A goaf fireproof monitoring system based on infrared thermal imaging comprises an infrared thermal imaging acquisition system, a 5G transmission system, an image storage and processing system, a remote monitoring system and an alarm system, wherein the signal output end of the infrared thermal imaging acquisition system is connected with the signal input end of the image storage and processing system through the 5G transmission system; the signal output end of the image storage and processing system is connected with the signal input end of the remote monitoring system through a communication cable; the signal output end of the image storage and processing system is connected with the signal input end of the alarm system. According to the disclosed system, high-precision real-time omnibearing monitoring of all goaf areas can be realized, monitoring differences caused by different proficiency degrees of employees are effectively avoided, missing detection conditions are effectively avoided, along with increase of the number of the goaf areas, the system can greatly reduce the cost of manual detection, the workload of detection personnel is greatly reduced, the detection efficiency is improved, and unified management of the goaf is facilitated.

The invention relates to an automobile battery integrated connecting plate automatic detection device, and relates to the technical field of automatic detection equipment, the automobile battery integrated connecting plate automatic detection device comprises a base, the upper end of the base is provided with a transmission device, the right end of the transmission device is provided with a first driving wheel, and the outer surface of the first driving wheel is provided with a first conveyor belt; a first rotating shaft is fixedly connected to the lower end of the first driving wheel, a first driven wheel is fixedly connected to the lower end of the first rotating shaft, and a second conveying belt is arranged on the outer surface of the first rotating shaft. The base and the transmission device are arranged in a combined manner, so that an integrated board of a battery can be conveniently placed on the second conveying belt, the integrated board can be conveniently detected, the manual detection cost is reduced, and meanwhile, the situation that the detection efficiency is influenced by eye fatigue easily caused by long-time manual eye detection is avoided; and through the combined arrangement of the baffles and the buckles, the distance between the baffles can be adjusted conveniently through the connection of the through holes and the buckles.

The invention discloses a method and device for detecting a character size. The method comprises the steps: acquiring 3D contour data of the surface of an engraved code character; calculating data ofa geometric surface on which the character is located from the contour data; extracting point cloud data of an engraved character with depth or height information; extracting a single character and carrying out statistics of the geometric size of each character; and outputting a result. Besides, the device includes a 3D contour measuring unit, a guide rail, a rail fixing unit base, a motor, a motor driving unit, a displacement sensor and a processing unit. According to the invention, with full-automatic detection of the depth or height of the engraved character, the character size and adjacentcharacter spacing, the manual testing costs of the motor vehicle VIN code, engine number and the like in the motor vehicle manufacturing and inspection fields can be reduced; the detection accuracy and detection efficiency can be improved; and thus the method and device for detecting a character size have the great significance in promoting the inspection automation in the industry.

The invention provides an automatic network wiring evaluation method and system. The method comprise that a network wire is connected to a network wire detection interface; an I/O expansion module inan I/O expansion chips detects an RJ45 interface, an ON/OFF state and line condition of straight or intersected wires of network wiring connection; network wiring is carried out , a laser generator ina network wiring system carries out output, and light decay data of network wiring is collected; when the light decay data of network wiring reaches or exceeds a light decay data threshold, a fiber of network wiring is marked unqualified, and a fiber detection result is recorded, and uploaded to a displayer for display; and an image of an RJ45 terminal connected interface is shot, and compared with a preset RJ45 terminal connected interface and connected terminal wire end contour image, the color code wire sequence of the connected terminal wire ends is compared with the preset color code sequence, and a discriminating result is recorded, and uploaded to the displayer for display. Thus, network wiring can be evaluated automatically, accurately and efficiently.

The invention relates to the technical fields of agriculture , forestry , animal husbandry and fishery and specifically relates to a fish pond oxygen content automatic control system. The system comprises a power supply, a wire, a dissolved oxygen detector, a processor, a controller, an oxygen-increasing machine and a data wire. The dissolved oxygen detector, the processor and the controller are connected in parallel and then are connected with the power supply through a wire. The dissolved oxygen detector is connected with the controller through the wire. The dissolved oxygen detector, the processor and the controller area connected through the data wire. According to the invention, the dissolved oxygen detector is utilized to detect the oxygen content in a fish pond in real time, and detected signals are transmitted to the processor through the data wire; when the protector carries out comparison and obtains a result that the detected oxygen content is within the preset oxygen content range, the processor sends a power-on or power-off instruction to the controller, and the oxygen-increasing machine starts to work or stops working; in addition, the fish pond oxygen content automatic control system is high in intelligent degree, the oxygen content in the fish pond is automatically controlled, the manual detection cost is lowered, manual detection is prevented from being not timely, and fishes are prevented from dying due to low fish pond oxygen content.