27results about How to "Accuracy" patented technology

The invention discloses a two-stage space-time diagram network and multi-source information fusion time sequence probability prediction method and device, and relates to the technical field of artificial intelligence and big data analysis. The method comprises the following steps: acquiring historical wind speed sequence data and corresponding target variable sequence data; preprocessing the data, and constructing a training sample according to a preset time sliding window; constructing a time sequence probability prediction framework of the two-stage space-time diagram network and multi-source information fusion; based on the fluctuation correlation of the historical sequence data, constructing an adjacent matrix between nodes; inputting the training sample and the adjacent matrix between the nodes into a wind speed prediction model, training the model through a designed threshold perception loss function of a wind speed-power nonlinear relationship, and outputting a multi-node wind speed prediction probability of a first stage; and inputting the multi-node wind speed prediction probability and the multi-source environmental factor data into the gradient boosting tree model for second-stage prediction, and outputting a multi-node wind power prediction result. According to the invention, prediction errors can be reduced.

The application discloses a wind turbine load rapid evaluation method for wind farm collaborative regulation, and relates to the technical field of wind turbine safety regulation. The specific implementation scheme is as follows: standard pulse instructions are applied to the wind turbine to extract vibration characteristic parameters and load oscillation initial amplitude; based on the rate of the candidate regulation instruction and the environmental wind speed, a transient excitation intensity function is set and effective excitation equivalent is calculated; according to the ratio of the effective excitation equivalent and the reference excitation equivalent, the relative impact intensity and the load oscillation amplitude are determined; the envelope function is constructed by combining the vibration characteristic parameters of the wind turbine, and the earliest safety execution time required for attenuation to the safety threshold is solved; the executability of the regulation instruction is determined by comparing with the maximum waiting time set by the rated blade bending moment load, and the load evaluation is completed; the collaborative controller can dynamically and accurately arrange the instruction sequence, and the overall safety of the wind turbine is improved.

The invention provides an F-P spectral imaging system and method, and belongs to the technical field of spectral component measurement, and the system comprises a front lens which is used for collecting light energy and converting the light energy into emergent light meeting the limitation of the clear aperture of an F-P interferometer; the annular band optical filter comprises a central area and a plurality of concentric annular areas surrounding the central area, the bandwidth of each area is the same as the free spectral range of the F-P interferometer, and the annular band optical filter is used for eliminating level aliasing in emergent light of the front lens; the F-P interferometer is used for carrying out wavelength selection on emergent light of the annular band optical filter and outputting an interference field; the imaging mirror is used for projecting the interference field to the detector; and the detector is used for converting the projected optical signal into a digital electric signal. The F-P spectral imaging system which can maintain high spectral resolution and also can realize wide spectrum coverage is constructed by introducing the annular band optical filter which is accurately matched with the FSR of the F-P interferometer.

This invention provides a method and apparatus for vehicle-mounted audio zone noise reduction, relating to the field of vehicle control technology. The method includes: when any target occupant among multiple occupants in a vehicle is in a call state, determining the target seat area where the target occupant is located from multiple seat areas in the vehicle; determining an acoustic control area based on the target seat area; when there is playback content in the acoustic control area, reducing the playback volume of the playback device in the acoustic control area; and when it is detected that the target occupant's call has ended, restoring the playback volume of the playback device in the acoustic control area to its original volume.

The application provides a heat supply regulation and control method and device of a heat exchange unit, electronic equipment and a storage medium. The method comprises the following steps: acquiring a current heat load value and a heat supply regulation and control parameter of the heat exchange unit in real time according to a preset regulation and control period; determining a first target heat load value of the heat exchange unit based on the heat supply regulation and control parameter; correcting the first target heat load value to obtain a second target heat load value; and regulating and controlling the heat supply of the heat exchange unit based on the second target heat load value and the current heat load value. The technical problem that the heat supply demand of each heat exchange unit cannot be accurately measured in the prior art is solved, and the purpose of flexible heat supply regulation and control is achieved.

The present application relates to the technical field of mine production, and specifically discloses a mine water geological parameter monitor, which comprises a mine water geological parameter module, a water quality state analysis module, a mine safety analysis module, a water disaster risk assessment module, a monitoring and early warning terminal and a database. By installing appropriate sensors on the mine water geological corresponding monitoring points and making them in communication connection with the mine water geological parameter monitor, real-time monitoring and acquisition of the water quality, gas and hydrological parameters of each monitoring point in each monitoring period can be realized. The mine water geological parameter monitor can monitor the temperature, pH value, conductivity, dissolved oxygen content and suspended solids content of the mine water in real time, as well as the methane concentration, carbon dioxide concentration, oxygen concentration and gas release rate. In addition, the mine water geological parameter monitor can also monitor the water inflow, water level value, water storage volume and drainage flow, thereby providing accurate and reliable data support for mine water management.

This invention relates to the fields of computer vision and civil engineering monitoring technology. It discloses a machine vision-based method for detecting concrete defects in high-speed railway bridge piers, comprising: calculating a global threshold and a local threshold based on a second image; weighting the global and local thresholds to obtain a mixed threshold; and segmenting the second image according to the mixed threshold to obtain a defect image. This invention, through binarization preprocessing of the image and combined with the Faster R-CNN algorithm, can accurately extract concrete defect features of high-speed railway bridge piers, significantly reducing computational resource consumption. Simultaneously, a weighted risk scoring method is designed to effectively assess the degree of concrete defects, ensuring high-precision assessment results. Furthermore, this invention innovatively designs an early warning system that can issue timely warnings when the detected defect degree reaches a certain threshold, avoiding potential safety risks.

The invention provides a NaCl solution viscosity detection device and method based on an asymmetric electrode QCM (Quartz Crystal Module) sensor, a round concave area is constructed on a base, a silica gel ring is arranged at the bottom of the round concave area, and the asymmetric electrode QCM sensor is arranged on the silica gel ring. The base, the hollow cylinder and the cover are combined to form a flow cell, and a circular through hole in the cover is used for enabling a NaCl solution to flow into an M-type electrode of the asymmetric electrode QCM sensor. The weakening effect of the M-type electrode on the fringe field effect and the reduction effect of the M-type electrode on the electrical property interference of the liquid are utilized to realize the high-precision measurement of the viscosity of the solution. When the viscosity of the solution is detected, firstly, the NaCl solution with the corresponding concentration is prepared according to requirements, then the peristaltic pump, the sensor wafer, the upper computer and other instruments are connected to form the detection device, and the viscosity value of the NaCl solution is calculated according to the resonant frequency variation of the QCM sensor. According to the device and the method, the viscosity of the NaCl solution can be accurately measured at low cost.

The utility model discloses a novel ton bag, which comprises a bag body for containing materials, a hoisting fixing structure sewn on the outside of the bag body for hoisting and fixing the bag body, a top connecting component installed on the top of the bag body, and a bottom connecting component installed on the bottom of the bag body for connecting the inside and outside of the bag body.

The application provides a kind of fast recovery diode operating reliability test method and system, it is related to circuit test technical field, the method comprises: fast recovery diode is set on experiment table, setting test environment parameter, and setting the frequency data of test power supply;Further setting test power supply, and the test voltage data of test resistance both ends is acquired, further determines reliability variation index, and determines reliability test result according to the reliability variation index of multiple test periods.According to the application, the test authenticity and accuracy can be improved by simulating complex working conditions through periodically changing test environment parameters, and the reference value of test results can be improved.Based on the dynamic adjustment of test environment, the workload of fast recovery diode is improved, and the test accuracy is improved.The reliability variation index of each test period can also be calculated to accurately know the performance change and reliability decline range of fast recovery diode, which provides an important basis for determining the reliability of fast recovery diode.

The application provides a shortest path determination method, device, equipment and medium. The method comprises the following steps: generating a public key and a corresponding private key, and sending the public key to a cluster node; obtaining encrypted address information sent by the cluster node, and decrypting the encrypted address information according to the private key to obtain address information of the cluster node; determining address information of a user node, and determining an address information tree according to the address information of the user node and the cluster node, wherein a root node of the address information tree is the user node, and child nodes of the address information tree comprise byte information corresponding to the cluster node; determining user distance information between the user node and the cluster node according to the address information tree, and determining target cluster distance information sent by the cluster node, wherein the target cluster distance information is cluster distance information between the cluster node and a blockchain node; and determining target shortest distance information of the user node and the blockchain node according to the user distance information and the target cluster distance information. The information communication efficiency and resources are improved.

The invention discloses a flow batch collaborative data governance method. The method comprises the following steps: judging whether to acquire upstream data or not according to current task information; if the upstream data is acquired, judging whether to switch to a batch processing mode or not according to the upstream data; if the mode is switched to the batch processing mode, the upstream data is subjected to batch cleaning processing successfully according to the current task information and then stored in a database, and then the mode is switched to the stream processing mode; if the batch processing mode is not switched, switching to a stream processing mode; when the mode is switched to the stream processing mode, upstream data are monitored, and when the upstream data are updated, the updated upstream data are subjected to stream cleaning processing according to the current task information and then stored in a database. According to the method, the upstream data is cooperatively processed through flow batch, the timeliness and integrity of data management are effectively improved, judgment of the upstream data is introduced before a batch processing mode, it is further ensured that data processing of each batch processing has integrity, accuracy and high efficiency, and redundancy of flow processing can be reduced.

The invention belongs to the field of artificial intelligence operation and maintenance, and discloses an electric power information system fault early warning and explaining method and system based on an RAG framework, and the method comprises the steps: obtaining historical log data with fault tags, coding the historical log data into feature vectors, constructing a vector knowledge base with the fault tags, and carrying out the fault early warning and explaining of the fault tags; therefore, the fault retrieval process can be compared based on the historical real fault features, and the retrieval result has a direct corresponding relation with the actual fault scene, so that the reliability of fault symptom judgment is improved. According to the method, the electric power information system logs are obtained in real time and converted into the feature vectors, retrieval is carried out through the vector knowledge base, similarity judgment is directly carried out on historical fault features when the logs are generated, and potential fault symptoms are rapidly recognized. Through the vector knowledge base with the fault labels, real-time feature vector retrieval and explanation generation based on the enhanced context, the fault early warning process has accuracy, interpretability and engineering practicability at the same time.

This invention relates to the field of electrolytic oxidation technology, and in particular to an online monitoring system for electrolytic coloring. It includes: a power calculation module, a power supply module, an electrolytic cell, a stirrer, a heat exchanger, and a cooling device. The power calculation module is connected to the power supply module, the power supply module is connected to the electrolytic cell, the electrolytic cell is connected to the heat exchanger, and the heat exchanger is connected to the cooling device. An electrolyte is provided inside the electrolytic cell, and the stirrer is located inside the electrolytic cell. A monitoring unit is used to detect the surface area of ​​the workpiece being processed and the parameters of the electrolyte in real time. A control unit is used to control the output current of the power supply module based on the surface area of ​​the workpiece. This invention, through dynamic real-time monitoring of the metal electrolytic coloring process, fully ensures the production quality of the electrolyte and the workpiece. Furthermore, by monitoring relevant parameters during the production process and automatically adjusting them, it prevents local defects in the finished workpiece and improves the processing quality.

The utility model discloses a support assembly for a temperature resistance test of an automobile central control screen mounting bracket, which relates to the technical field of high temperature resistance tests of automobile interior trim parts and comprises a base frame arranged below a heating assembly in a test box, a cover plate is arranged on the inner side of the base frame, and a plurality of turnover frames are rotatably arranged in the cover plate. According to the utility model, the plurality of overturning frames and the adjustable storage seat are rotatably arranged in the cover plate, the limiting part is used for clamping and positioning the automobile central control screen mounting bracket body on the storage seat, and the driving part is matched to drive the plurality of overturning frames to rotate, so that the automobile central control screen mounting bracket body reaches a suspended state; a high-temperature heat source acts on a hidden part on the automobile central control screen mounting bracket body through the heat penetrating gaps in the storage seats and also acts on the other side of the automobile central control screen mounting bracket body through the gap between the two storage seats, so that the automobile central control screen mounting bracket body is comprehensively heated; and the obtained test data has certain accuracy.

The embodiment of the application discloses a system aging state detection method, device, equipment and readable storage medium, the method comprises: obtaining at least one running state of the system to be detected and at least one state transition model corresponding to the running state; obtain the target parameter corresponding to the state transition model, and obtain the first weight of the target parameter by hierarchical analysis; determine the anti-decay index corresponding to each running state based on the target parameter and the first weight corresponding to the target parameter, and determine the aging state information of the system to be detected according to the anti-decay index. By analyzing the target parameter to determine the weight corresponding to the target parameter, the association between the target parameter and the system aging state is strengthened, so that the anti-decay index determined by the target parameter and the weight corresponding to the target parameter is more objective and accurate, thereby improving the effectiveness and accuracy of the aging state detection of the system to be detected when determining the aging state information of the system to be detected based on the anti-decay index.

The application discloses a power system load curve clustering analysis method, determines the target and requirement of power system load curve clustering analysis, carries out data preprocessing, uses a self-organizing feature mapping neural network to construct a feature extraction model, uses an MAML algorithm to carry out multi-task learning, carries out rapid adjustment through meta learning, applies a Gaussian mixture model to cluster the extracted features, uses indexes to evaluate the clustering effect, carries out clustering result analysis, determines whether the predetermined performance standard is met, and further carries out iterative optimization, so that the self-organizing feature mapping neural network, meta learning and the Gaussian mixture model are combined, and greater value is brought to power system operation and energy management.

The application discloses a millimeter wave radar point cloud and visual image fusion method, which comprises the following steps: acquiring a camera image, a plurality of 4D millimeter wave radar point clouds and SNR information corresponding to each 4D millimeter wave radar point cloud; performing Gaussian diffusion on the 4D millimeter wave radar point cloud based on the SNR information to obtain a diffused radar bird's eye view (BEV) feature; obtaining a visual sparse feature based on a sampling point of the camera image generated based on a point cloud heat map; fusing the diffused radar BEV feature and the visual sparse feature based on a deformable cross-attention mechanism to obtain a sampling point sparse feature; and performing cross-attention fusion on the sampling point sparse feature and a query vector of a target object to obtain a fusion feature of the camera image and the plurality of 4D millimeter wave radar point clouds, thereby improving the accuracy and reliability of environment road condition perception.

The application discloses a kind of calculation methods of X-ray intensity distribution in power cable, first using multi-frequency X-ray machine to five kinds of power cable materials of copper, aluminum, XLPE, silicone rubber and semiconductive layer, record initial X-ray dose rate and dose rate after penetration;Second, the transmittance of different materials through different thickness, average attenuation coefficient and each section average attenuation coefficient are calculated by X-ray attenuation formula, and the fitting formula is obtained;By comparing the results of traditional method with the results of the application calculation method, it can be found that when using traditional attenuation coefficient calculation, due to lack of measurement of X-ray attenuation coefficient of multi-frequency X-ray source transmission material and consideration of multiple hardening phenomenon occurred when cable material is irradiated by X-ray, larger error can be caused.It can be confirmed that the calculation method of this experiment is more accurate than traditional method.

This invention relates to the field of rolling mill technology, specifically to a rapid adjustment device for the parallelism of rolling mill rolls. The device includes a base plate, a vertical plate, and a main drive mechanism. The output end of the main drive mechanism is meshed with upper and lower distributed work rolls and support rolls. The support rolls penetrate the vertical plate and extend to both sides of the vertical plate. Bearings are fitted onto the work rolls and support rolls at positions corresponding to the vertical plate. The width of the bearing cross-section is greater than the thickness of the vertical plate. Guide grooves are formed on the vertical plate, and a hydraulic mechanism is fixedly installed at the upper end of the guide grooves. This invention allows for easy insertion of the acute-angled tip of a trapezoidal feeler gauge into the narrow gap between two cylindrical bearings, enabling precise positioning and stable support of the support rolls. Combined with a finely adjustable hydraulic lifting mechanism for the work rolls, it achieves standardized and quantitative measurement and comparison of the gap between the two ends of the rolls without relying on the operator's feel, thus providing a direct and reliable basis for rapid and precise adjustment of parallelism.

The application belongs to the technical field of satellite signal processing, and provides a satellite-borne GNSS multipath modeling method, device, equipment and storage medium. The method comprises: establishing a satellite three-dimensional model and a signal source model in the same coordinate system to simulate the incidence process of the signal; when the signal ray emitted by the signal source model has an intersection with the satellite three-dimensional model, it is considered that there may be a reflected signal; the possible reflected signal is verified according to the intensity ratio of the signal ray before and after passing through the reflection surface of the satellite three-dimensional model; if the intensity ratio is within a set range, it is confirmed that the reflected signal exists; in the case that the reflected signal exists, the reflection point and the reflection path are calculated; the code pseudorange delay, the carrier phase delay and the Doppler delay are calculated to obtain a multipath error model. The method can calculate the multipath error of a satellite-borne receiver, and realize the suppression of the multipath effect at a low cost.

The utility model discloses a measuring device for an aircraft pedal stroke limit actuator cylinder, which belongs to the technical field of aviation detection and comprises a vertical plate, a long cross rod, a meter clamp, a threaded rod and a separation blade. The threaded rod is in threaded fit with an inner hole of the hydraulic lock, the blocking piece serves as a measuring upper end face, the upper end of the vertical plate is welded to the long transverse rod to form a right-angle structure, the lower end of the vertical plate is fixed to the bottom end of the hydraulic lock, and the bottom end of the hydraulic lock serves as an installation reference. The upper end of the gauge stand sleeves the long cross bar, and the lower end clamps the dial gauge to measure the moving distance of the separation blade. According to the utility model, the probing thread and the hydraulic lock form a whole, the measurement mode is simple and efficient, the measurement method is accurate and practical, a pure mechanical structure is adopted, and no safety problem is involved.

This invention relates to a health monitoring device and method for weld seams in metal structures of metallurgical cranes, belonging to the field of metallurgical crane operation and maintenance technology. It includes a detection upper cover, a detection interlocking plate, and a detection lower cover. Detection components are provided on the top surface of the upper cover and the bottom surface of the lower cover. Each detection component includes a probe sleeve and a probe upper cover fixedly mounted on the inner wall of the probe sleeve by bolts. An electromagnetic ultrasonic monitoring probe is fixedly installed on the inner wall of the probe upper cover. A telescopic groove is formed on the side of the probe sleeve near the detection interlocking plate, and a connecting ring cylinder is slidably installed on the inner wall of the telescopic groove. This invention addresses the shortcomings of existing technologies in the health monitoring of weld seam areas in metal structures of metallurgical cranes by combining an electromagnetic ultrasonic probe with a simulated sample that simulates the damage state of the weld seam area being monitored. The simulated sample has the same temperature and stress state as the weld seam being monitored, increasing the detection accuracy of the device.

The application relates to the technical field of nuclear power plant operation, in particular to a nuclear power plant operation technical specification determination method and device, equipment and a storage medium. The method comprises the following steps: obtaining limit condition corresponding to each operation system in each operation mode in a nuclear power plant from a database; obtaining operation parameters of each operation system in a current operation mode in the nuclear power plant; if the operation parameters of any operation system do not meet the limit condition corresponding to the current operation mode, determining a risk index of the nuclear power plant when the operation parameters of the operation system do not meet the corresponding limit condition according to the operation state of the nuclear power plant; determining a safety configuration time and a safety configuration operation according to the risk index; and determining a conventional operation specification of the nuclear power plant according to the safety configuration time and the safety configuration operation. The application can optimize the accuracy of the design of each nuclear power plant operation technical specification.

The spherical tank sealed sampler provided by this invention includes: a spherical tank, a sampler, a nitrogen pipeline, and a float assembly. A sampling port is provided at the bottom of the spherical tank. The sampler is connected to the sampling port via the sampling pipeline, and the nitrogen pipeline is connected to the sampling pipeline. The float assembly includes: a guide tube, the lower end of which is fixed to the spherical tank, and a liquid inlet at the upper end of which; and a sealing float, which is buoyantly disposed within the guide tube. It can extract oil from the spherical tank through the guide tube, and the extracted samples are more accurate and representative than those obtained using existing processes.

This invention discloses a fault diagnosis system for rotating equipment based on a large language model, aiming to improve the accuracy and efficiency of fault diagnosis for industrial rotating equipment. The system consists of six parts: data collection, data preprocessing, a neural network model, a time-series label knowledge base, a large language model, and a user unit. The system can not only detect faults in real time but also enable interaction through the user unit, allowing for analysis and prediction of the rotating equipment's operating status based on user needs. The system optimizes input through data preprocessing techniques and enhances the large language model using a time-series label knowledge base. Based on this, and combining equipment operating data, historical records, and neural network diagnostic results, the large language model can accurately identify potential faults and generate actionable maintenance suggestions, thereby significantly improving equipment reliability and the safety of industrial production.

This invention provides a method and system for predicting the efficiency of biochemical treatment based on the dynamic evolution of water quality fingerprints. The method includes: collecting spectral data at the inlet of a wastewater treatment system and extracting water quality fingerprint feature vectors to construct a time-series dataset reflecting dynamic changes in water quality; simultaneously collecting effluent efficiency index data and establishing a time correspondence between the data and the water quality fingerprints to form structured training data; using deep learning models such as LSTM or Transformer to learn from the training data, constructing a mapping relationship from water quality fingerprints to future efficiency indicators, and achieving accurate prediction of biochemical treatment efficiency; generating early warning information based on the prediction results and dynamically adjusted graded early warning thresholds, and formulating optimized process control schemes by combining an expert knowledge base and an experience-based learning model. This invention breaks through the traditional passive management model that relies on delayed monitoring, achieving early warning and proactive prevention of potential risks in wastewater treatment systems, effectively improving treatment efficiency and reducing energy consumption and operating costs.