37results about How to "Avoid manual misjudgment" patented technology

The invention discloses a fault diagnosis method for a distribution network in a power distribution system, comprising the steps of: constructing a communication network with each distribution network management device in the distribution network as a node, and the distribution network management devices in the communication network can share each distribution network management The monitoring data collected by the equipment; the monitoring data includes the identification of the corresponding distribution network management equipment; the upstream and downstream relationship of each distribution network management equipment in the distribution network is determined according to the characteristics of the current; according to the changes in the monitoring data of each distribution network management equipment Characteristics, as well as the upstream and downstream positional relationship of each distribution network management device in the distribution network, generate a fault report; the fault report includes one of fault location, fault range and fault type and any combination thereof. Since the embodiment of the present invention can automatically determine the fault location and fault type of the distribution network, it can effectively avoid manual misjudgment, thereby improving the accuracy of fault judgment.

The invention discloses a method for regulating and controlling the welding quality of an ERW pipe. The corresponding range of the aspect ratio I of external burr within the application range of a metal streamline angle is obtained through simulation; the corresponding range is verified through experiments; then the corresponding range is used as a criterion factor for judging the quality; and thequality of the actual ERW pipe is judged on line according to the criterion. Compared with the existing simulation technology, the relationship between the external burr aspect ratio I and the ERW pipe quality is obtained according to the aspect ratio I = H / W of the external burr at a weld joint; the criterion factor for judging the ERW quality through the external burr aspect ratio I is established, so that the appearance of the external burr is conveniently quantified, online judgment and regulation is realized, the production efficiency of the ERW pipe is improved, and the labor cost is reduced; and the relationship between the metal streamline angle theta and the external burr aspect ratio I is obtained through simulation and experiment verification, so that the online quality controlprocess of the ERW pipe is guided, the directionality of the control process is determined, the efficiency and the accuracy rate of quality control of the ERW pipe are improved, and the quality of the ERW pipe is further improved.

The invention provides a pathological slice detection method and device, computer equipment and storage media, which belong to the technical field of medical devices, including obtaining image encoding of pathological slices; calling a preset pulse neural network model and a preset residual neural network model and GoogLeNet The model analyzes and marks the image code; reconstructs and displays the marked image corresponding to the final diagnosis result, and makes a diagnosis report. Technical effect: Using the preset pulse neural network model and the preset residual neural network model can analyze and diagnose the acquired pathological slice image coding, and accurately and quickly mark the lesion area. When the diagnostic results of the two are inconsistent, use the preset GoogLeNet The model makes the final diagnosis result and marks the lesion area more accurately. Compared with manual operation, it greatly shortens the detection and diagnosis time and reduces the labor intensity of doctors. At the same time, it also avoids manual misjudgment and improves the quality of diagnosis and the accuracy of diagnosis results. sex.

A system and method for judging in place of motor assembly based on a smart camera relate to the field of automobile instrument assembly. The present invention is to solve the problem that the existing motor for judging whether the motor controlling the swing of the pointer in the automobile instrument is in place is identified by manual naked eyes, and it is difficult to ensure the accuracy. The invention uses a smart camera to collect the actual picture of the assembly board, and then judges the parameters of the motor positioning column and the pin in the picture according to the picture, so as to judge whether the assembly is qualified or not. Negligence due to fatigue. It effectively improves the assembly accuracy and provides a basis for later product traceability.

The invention relates to a semi-supervised EEG signal sleep staging method under multi-domain characteristics, belonging to the field of brain-computer interface. In this method, the original EEG signal is processed by combining the ant colony algorithm and the semi-supervised Bayesian classification method to obtain the original feature set under multi-domain features, which is optimized by the ant colony algorithm and an optimal Feature subsets, and use the improved semi-supervised Bayesian classification method, using the optimal feature subset as the classification feature, combined with active learning strategies to classify it in stages. This method can not only effectively realize sleep staging, avoid the waste of computing resources caused by low-efficiency feature attributes and blind search process, but also reduce the number of labeled samples. By comparing with various sleep staging methods proposed in recent years, the results It shows that this method can not only achieve the staging accuracy effect of the mainstream algorithm, but also greatly reduce the demand for labeled samples and avoid the occurrence of manual misjudgment.

The invention provides a water area entanglement removing device and method. The device comprises a high pressure pump, a controller and nozzles. The controller is used for sending a water pressure regulating signal to the high pressure pump according to the types of water area entanglements; and the high pressure pump is used for regulating the water pressure according to the water pressure regulating signal so that the nozzles can cut and remove the water area entanglements on the basis of the high pressure water cutting principle according to the regulated water pressure. According to the types of the water area entanglements, the high pressure pump is controlled to regulate the water pressure of the cut water area entanglements, the cutting efficiency for the water area entanglements can be improved, and energy waste caused by cutting is lowered.

The invention discloses a semi-automatic assembling tool for an automobile inward-opening wrench. The semi-automatic assembling tool comprises a workbench surface and a frame. The workbench surface is provided with a positioning part, a detecting part and a progressive type driving part. The detecting part is provided with knurl detecting sensors, a shaft pin length detecting sensor, a buffer gasket detecting sensor and a buffer ring detecting sensor. Collected electric current signals are output to a PLC through the knurl detecting sensors, the shaft pin length detecting sensor, the buffer gasket detecting sensor and the buffer ring detecting sensor to be processed. An air cylinder fixing bracket is further arranged on the workbench surface, provided with a pressing mechanism and connected with a bottom plate. The frame is arranged on the lower portion of the workbench surface. An electrical plate is arranged in the frame. According to the semi-automatic assembling tool for the automobile inward-opening wrench, the operation intensity of employees is relieved, and the assembling efficiency is greatly improved; artificial misjudgment is avoided through detection conducted by the knurl detecting sensors, the buffer gasket detecting sensor and the buffer ring detecting sensor, so that the good product rate is greatly increased.

The invention discloses a system and method for automatically detecting the user mode of a small home electric current line, including a user mode test station, which is connected to the small home electric line through a double-speed link, and the user mode test station includes an internal wired or wireless device. The connected six-axis robot, CCD camera assembly, power tester, PLC control system, and operation display screen, the entire system is connected to the Internet through an external network connection device. It is possible to automatically detect the user mode of the small household current pipeline. Including standby power, filter life, display screen and other tests, the production efficiency is high, the labor cost is low, and manual misjudgment is eliminated.

The invention relates to a debugging method of a railway signal maintenance system. The method includes: using the debugging recorded data of a single monitoring station as the basis, obtaining the debugging content of the station according to the standard debugging rules, debugging the data in real time, recording the debugging information, providing the debugging results for confirming, checking the debugging results, analyzing the leftover problems and finally generating a debugging recording table and a leftover problem recording table in accordance with code requirements of the standard debugging rules. Compared with the prior art, the debugging method has the advantages of providing graphic interfaces, being capable of automatically generating the debugging recording information and the leftover problems, being capable of generating the final debugging recording table and the leftover problem recording table according to the debugging recording information after engineering debugging is finished, greatly improving the field debugging efficiency, and bringing large convenience for the debugging and debugging tracking of the railway signal maintenance system.