6results about How to "Improve guidance" patented technology

The application relates to a strip steel surface defect tracing method, system, device and medium. The method comprises the following steps: performing defect recognition on a strip steel surface defect image to obtain a defect type, a geometric feature vector and a texture feature vector, acquiring spatial coordinates and a timestamp corresponding to the image, and constructing a defect feature matrix; constructing a process knowledge graph based on production line equipment parameters, a theoretical speed curve, equipment topological relations, real-time working condition data and historical event records; performing candidate equipment positioning in the process knowledge graph by adopting a periodic matching strategy or a non-periodic matching strategy to generate a matching result set; acquiring an equipment health index from the process knowledge graph, calculating a final confidence and a comprehensive score based on matching parameters in the matching result set, and generating a tracing report. The method integrates multi-dimensional defect features and constructs a process knowledge graph, optimizes a defect and equipment matching strategy, and improves the accuracy and reliability of strip steel surface defect tracing.

This utility model relates to the field of blood specimen preservation technology, and in particular to a blood specimen preservation box, including a box body. The box body has multiple insertion holes evenly distributed on it for placing blood collection tubes. Each insertion hole is a conical hole, wider at the top and narrower at the bottom. A pair of sponge wheels are symmetrically arranged along the diameter of each insertion hole on its inner wall. This utility model's blood specimen preservation box features conical insertion holes, which retain the advantage of traditional larger insertion holes for easier insertion of blood collection tubes. During blood collection, medical personnel can easily align and insert the blood collection tube into the insertion hole. The larger opening at the top provides significant guidance, reducing the difficulty of insertion and improving blood collection efficiency. When inserting the blood collection tube, the sponge wheels rub against the outer wall of the tube, making insertion smoother. After insertion, the sponge wheels are in close contact with the outer wall of the blood collection tube, providing a clamping function and, together with the bottom of the conical hole, limiting the movement of the blood collection tube within the insertion hole.

This utility model provides a traction device, including: a frame, a traction seat, and a locking rod. The frame is movably arranged along a preset trajectory. The traction seat is installed on the top of the frame and is located on the side of the frame closer to the drying oven. The traction seat has an insertion slot that extends along the length of the frame. The insertion slot is for the insertion and engagement of traction fittings on the placement frame. The locking rod extends along the width of the frame and is movably inserted into the traction seat along the width of the frame. The side wall of the insertion end of the locking rod has a guide slope, and the locking rod has an initial state, a clearance state, and a locked state. When the traction seat is away from the placement frame, the insertion end of the locking rod is located in the insertion slot, and the locking rod is in the initial state. This traction device effectively solves the technical problem in the prior art where, after the profile has been dried, the operator needs to enter the high-temperature drying space to manually push out the placement frame.

The application discloses an industrial sensor data anomaly detection and repair method based on an attention mechanism, belongs to the technical field of industrial data processing, and carries out preprocessing on original data to obtain standardized data segments, a training set and a test set; end-to-end collaborative training is carried out on the training set to obtain a dynamic space-time attention detection model and a multi-scale self-attention repair model; the standardized data segments are input into the dynamic space-time attention detection model for anomaly detection to obtain abnormal related information; the standardized data segments and the abnormal related information are input into the multi-scale self-attention repair model for data repair to obtain repaired data; secondary verification and parameter fine-tuning operations are performed on the repaired data to obtain compliant repair data; and the POT algorithm is used to dynamically adjust an abnormality judgment threshold value, and normal industrial sensor data or compliant repair data is output. By using the above method, accurate detection and compliant repair of industrial sensor data anomalies are realized.

This invention provides a method for interpreting conventional well tests in complex reservoirs. The method includes considering permeability variations near the wellbore in a complex region, analyzing pressure recovery curves, calculating the flow coefficient based on shut-in time and bottom-hole pressure in each zone, analyzing the variation trend of reservoir properties around the well based on changes in the flow coefficient, calculating reservoir permeability at different time intervals, amplifying the time interval data to observe the relationship between reservoir properties and time intervals, and obtaining the wellbore reservoir coefficient based on the pressure recovery theory, considering the changes in bottom-hole pressure over time based on shut-in time and time. The method also calculates the pressure recovery rise value based on the wellbore reservoir coefficient and when the test data time intervals are the same. This invention is suitable for reservoirs with water injection, polymer injection, alternating gas and water injection, wellbore contamination, or improved permeability near the wellbore, and is also applicable to the interpretation of well test data from reservoirs with varying rock properties.

The application provides a method and device for identifying a fractured-vug reservoir type, a computer readable storage medium and an electronic device. The method comprises determining a lithology type of a reservoir in a study area and a reservoir type of the reservoir; analyzing reservoir porosity of the study area; obtaining conventional well logging curves of the study area, and determining sensitive well logging curves and sensitive well logging response characteristics that can be used to identify the reservoir type of the study area based on the conventional well logging curves; establishing identification criteria for different types of reservoirs based on the porosity of different types of reservoirs, the difference in the overlapping amplitude of the sensitive well logging curves and the values of the sensitive well logging response characteristics; and identifying and dividing the reservoir type of the study area by using the identification criteria for different types of reservoirs. The identification criteria for the reservoir type established by the application can accurately and intuitively identify different types of reservoirs, and can greatly improve the accuracy of well logging technology in identifying fractured-vug reservoirs, thereby guiding the exploration and development of oilfields.