49 results about "Decision error" patented technology

The invention provides an active power distribution network prediction-scheduling integration method based on half-end-to-end, and the method comprises the steps: (1), obtaining photovoltaic output, a load power historical data set, a meteorological data set and power distribution network parameter information, and carrying out the initialization; (2) respectively establishing mathematical models of a prediction layer, a day-ahead scheduling layer and a decision evaluation layer, establishing a half-end-to-end model basic architecture based on the mathematical models, and performing photovoltaic output and load power prediction by the prediction layer; in the day-ahead scheduling layer, a day-ahead scheduling model is constructed according to resource elements contained in the active power distribution network; the decision evaluation layer calculates a day-ahead scheduling decision error and constructs a mixed loss function; (3) training a half-end-to-end model based on photovoltaic output, a load power historical data set, a meteorological data set and power distribution network parameter information to perform model parameter optimization; and (4) inputting day-ahead meteorological data to the half-end-to-end model obtained by training in the step (3), and obtaining an optimal day-ahead scheduling optimization strategy of the power distribution network.

The invention provides an autonomous operation obstacle avoidance method and system for a low-altitude aircraft, and the method is executed by the low-altitude aircraft, and comprises the following steps: S1, data acquisition: collecting data through a multi-source heterogeneous sensor group carried by the low-altitude aircraft, airspace control information, real-time meteorological data and collaborative sensing data of other aircrafts sent by the ground sensing base station are received through the air-ground communication interface; preprocessing the collected original data, wherein the preprocessing comprises data format standardization, abnormal value elimination and time synchronization; and S2, data fusion processing: carrying out credibility evaluation on the preprocessed multi-source heterogeneous sensing data and collaborative sensing data. According to the invention, through three-dimensional credibility evaluation and an air-ground data compensation mechanism, the perception precision is greatly optimized, the perception data efficiency is improved in complex environments such as low illumination, strong electromagnetic interference, rainstorm and the like, and obstacle avoidance decision errors caused by data distortion of a single sensor are avoided.

The invention discloses an intelligent decision-making method for a cerebral ischemia drug administration time window, and relates to the technical field of intelligent decision-making. The method comprises the following steps: S1, acquiring parameters, and setting a cerebral ischemia drug configuration scheme; s2, extracting a medicine characteristic parameter set and a medicine taking influence parameter set; s3, calculating a drug combination risk parameter set; s4, performing hierarchical classification processing on the drug combination risk parameter set, and performing drug correlation analysis; s5, performing weighted fusion on a correlation analysis result in combination with a drug influence attenuation rule, generating a drug administration time window evaluation parameter, and adding a label; and S6, according to the parameters, the labels and the configuration scheme, generating a cerebral ischemia drug administration time window intelligent decision scheme, and performing storage and backup. According to the method, by combining directional extraction of the drug characteristic parameter set and the drug taking influence parameter set with Pearson correlation algorithm screening, decision errors caused by data deviation are avoided.

The invention discloses an anti-unmanned ship unmanned aerial vehicle swarm dynamic clustering algorithm and a saturation attack path planning method, and belongs to the technical field of path planning. The invention discloses an anti-unmanned ship unmanned aerial vehicle swarm dynamic clustering algorithm and saturation attack path planning method. The method comprises the steps of constructing a multi-dimensional situation awareness index system; constructing a clustering decision function; and establishing a cluster structure dynamic adjustment mechanism, and carrying out collaborative scheduling optimization on the cluster structure. According to the invention, the problem of decision error caused by incapability of timely obtaining accurate information when communication is interrupted in the prior art is solved. According to the method, dynamic changes of the bee colony targets can be more flexibly coped with, it is ensured that each bee colony target is covered with the corresponding interception cluster, even if part of communication is interrupted, all clusters can still make decisions autonomously according to local information, certain interception capacity is maintained, basic interception tasks continue to be executed under the condition that communication is limited, and the communication efficiency is improved. It is ensured that interception preparation is completed before the bee colony reaches the defense target, and defense failure caused by response delay is effectively avoided.

The invention relates to the technical field of semiconductor radio frequency signal processing, and discloses a narrowband signal receiving system and method, and the system comprises a coarse frequency offset value capturing module, a carrier phase locking module, a digital domain carrier tracking module, a timing synchronization and multipath correction module, and a vector amplitude phase correction and equalization module. In the prior art, the technical problems of lock losing, judgment errors and high bit error rate caused by serious multipath interference and frequency offset drifting of narrow-band signals are difficult to solve in complex environments with multipath effect and high frequency offset, such as urban canyons, basements and warehouses. According to the invention, by introducing analog phase locking, digital fine tuning, dual-correlation symbol synchronization based on multi-path sensing and vector amplitude-phase combined compensation overall architecture with cooperation of analog and digital, the problems of synchronization failure and demodulation performance reduction caused by multi-path distortion in the prior art are avoided; and the sensitivity and the overall reliability of radio frequency signal receiving are remarkably improved.

The invention discloses a map construction method and system based on air-ground collaborative fusion air-ground perception, and belongs to the technical field of automatic driving and environment perception. In order to solve the problems that closed-loop feedback only stays at a data layer for correction, perception errors cannot be radically eliminated and system robustness is insufficient in existing air-ground collaborative map construction, perception differences, observation angles, speeds and other perception parameters are accurately bound to form parameterized difference data; the cloud data center unit performs periodic iterative optimization on the end-side semantic understanding model based on the data and issues update parameters to realize error source calibration; according to the method, bidirectional cross validation, unmanned aerial vehicle height adaptive adjustment and a double-weight layered grid fusion algorithm are fused, and the system adopts an end-cloud-end architecture and is matched with 5G + V2X dual-mode communication to guarantee air-ground end-cloud real-time interaction. According to the scheme, the map construction precision and the system robustness are effectively improved, the closed-loop feedback delay is low, the obstacle avoidance decision error rate is remarkably reduced, and the method is suitable for complex unstructured environments such as mine exploration and field rescue.

The invention provides a power system transient voltage control method and system. The method comprises the following steps: acquiring initial power system operation state parameters in real time and establishing a transient model; obtaining an initial transient voltage severity index based on the parameters and a preset initial voltage; constructing a physical information neural network based on the transient model and exporting a loss function of the physical information neural network; based on the parameters, a preset reward parameter and a noise network, obtaining an initial Rainbow agent, executing a removal action and calculating corresponding loss; and constructing a total loss function based on the total loss function and training to convergence by taking minimization as a target, and obtaining an intelligent agent to realize the control of the transient voltage of the power system. According to the method and the system for controlling the transient voltage of the electric power system, the electric power system can be rapidly controlled to recover stability, the situation that the transient voltage control decision is not accurate due to the fact that the action value is excessively estimated is avoided, and the situation that the instability degree of the electric power system is aggravated is further prevented.

The invention provides a deep learning DD channel estimation system and method combined with an adaptive CIR truncation mechanism, and the system comprises a pilot frequency estimation module which carries out the channel estimation according to a received pilot frequency sequence, and outputs a pilot frequency assisted channel estimation value; the deep learning prediction module is used for predicting the channel state of the next moment according to the historical channel estimation sequence; the data auxiliary channel estimation module is used for balancing and decoding the data symbols based on the channel state, and obtaining data auxiliary channel estimation after reconstruction; the self-adaptive CIR truncation module takes data-assisted channel estimation as input and outputs a channel estimation value after truncation; and the periodic pilot frequency correction module is used for triggering pilot frequency updating and correcting the pilot frequency assisted channel estimation value. According to the method, the influence of a data judgment error is actively considered, the tap weight is dynamically output by using the lightweight neural network, the historical sequence is intelligently cleaned and cut off, error propagation is effectively inhibited, and the stability and robustness of prediction are improved.

The invention discloses a substation intelligent maintenance aid decision-making method and system based on a digital scene, relates to the technical field of electric power operation and maintenance, adopts a cascade optimization algorithm to train a deep learning model to obtain an intelligent maintenance analysis model, effectively overcomes the defect that a traditional optimization method is easy to fall into local optimum, and improves the maintenance efficiency. The maintenance accuracy of an intelligent maintenance analysis model is improved, visual association is achieved by constructing a substation digital scene with interest points, operation and maintenance personnel do not need to interpret a complex data report or search equipment positions on a two-dimensional drawing any more, the fault positions can be determined more rapidly, and the maintenance efficiency is improved. And the risk of decision errors caused by unsmooth information transmission or experience dependence is obviously reduced.

The pulse width compression PPM modulation method based on superconducting nanowire single-photon detection belongs to the technical field of signal processing. In view of the problems that the prior art cannot reduce the communication capacity, increase the system overhead and solve the ranging accuracy when reducing the communication error rate caused by random jitter. The pulse width in the PPM symbol is compressed at the sending end, the time fluctuation range of the superconducting nanowire single-photon detector response pulse is reduced, and the ranging error caused by time fluctuation is reduced. The time range of the random appearance of photons is compressed, the crosstalk of the superconducting nanowire single-photon detector response pulse to the adjacent time slot is reduced, the symbol decision error probability is reduced, and the communication reliability is improved. The signal light power is limited in a smaller time range, the instantaneous light power in the pulse time period is improved, the light power utilization efficiency is improved at the same transmission power, and a longer transmission distance is achieved. The present application is suitable for the field of communication and is used for improving the transmission distance and the ranging accuracy.

The application discloses a virtual power plant resource decision optimization management method and system based on big data driving, and relates to the technical field of data management.The virtual power plant resource decision optimization management method and system based on big data driving comprises the following steps: collecting risk component data and operation performance data of a virtual power plant, and storing and constructing a virtual power plant management database after preprocessing; performing data quality risk analysis by evaluating communication continuity, equipment stability and meteorological disturbance, performing risk priority sequencing and data classification labeling according to the risk analysis result; fusing data quality, label influence and time persistence, measuring the adaptation degree between data and supply-demand prediction, and constructing a supply-demand prediction model; and measuring feedback optimization effect in view of prediction error, output deviation, constraint touch and data quality.The application solves the problems of inaccurate data cleaning and resource scheduling decision errors caused by the difficulty in defining the boundary of abnormal data in a virtual power plant.

The invention belongs to the technical field of intelligent driving, and particularly relates to a driving decision-making method under a blocked intersection, which comprises the following steps of: establishing a main vehicle dynamic visible range model through static geometrical information of a blocked object and a sensing range of a sensor, and solving hypothetical vehicle state information of each road at the intersection through the dynamic visible range model and a road structure. Environmental state input information is formed by detecting environmental vehicle state information and virtual vehicle state information, and the driving behavior of the host vehicle is determined on the basis of the environmental state input information. The virtual vehicle is generated based on the shielding object in the shielding state, and the driving strategy is formed based on the virtual vehicle, so that decision errors caused by the real environment information in the shielding state can be effectively avoided, the accident risk is effectively reduced, global consideration of the decision model on the uncertainty of the environment information and driving behavior robustness decision making are realized, and the driving experience is improved. And the traffic safety and efficiency of the intelligent automobile when the environmental information perception is insufficient are improved.

Shared information generation technique including key generation rate and soft-decision error correction in CV-QKD is disclosed. A receiver is configured to: set reference bit positions for basis reconciliation according to the reference bit positions with a transmitter, to generate sifted key quantization data; performs hard decision on a part of the sifted key quantization data to generate hard-decision data; perform bit position synchronization decision whether bit position synchronization is established; and in response to establishment of bit position synchronization, performs soft-decision error correction processing to generate shared information.

The application relates to the technical field of road marking, in particular to a road marking drawing method and system based on image recognition. The method comprises the following steps: acquiring a historical trajectory data set, a road design parameter set and an environment image set of a target road; analyzing the historical trajectory data set to determine a trajectory repetition degree; determining a geometric constraint condition according to the road design parameter set; determining a dangerous source distribution feature according to the environment image set; and determining a marking scheme according to the trajectory repetition degree, the geometric constraint condition and the dangerous source distribution feature. The method is helpful for improving the marking visible distance under extreme conditions, reducing out-of-control accidents caused by overspeed, reducing the contradiction between the danger source avoidance space and the road side, generating the marking scheme, avoiding that the compensation strength exceeds the physical limit of the lane, and reducing the decision error rate at the marking mutation.

The present application relates to the technical field of digital signal processing, and proposes a terahertz wireless transmission carrier phase recovery system and method based on tree structure Parzen estimation optimization, which comprises a blind phase estimation module, used for setting multiple test phases, calculating the decision error under each test phase, and obtaining the original phase estimation value of the current signal; a cyclic slip unwrapping module, used for selecting the continuous branch of the current original phase estimation value according to the phase estimation result of the previous moment, eliminating phase mutation, inhibiting cyclic slip, and completing phase compensation; and a parameter optimization module based on tree structure Parzen estimation, used for optimizing the test phase number and the sliding window length in the blind phase search according to the performance index after the carrier phase recovery, and obtaining the final carrier phase recovery parameter. The present application realizes low-complexity and strong-robustness carrier phase recovery, and significantly improves the stability of the terahertz wireless transmission system under strong phase noise.

The application discloses a compensation method for CDR channel asymmetry in a high-speed transmission system i and a decision error e i of a current received symbol, attempts to match a continuous received decision bit stream with a special bit sequence pattern to calculate inter-symbol interference ISI, and then uses the calculated inter-symbol interference ISI to compensate for the asymmetry of the channel The application provides a compensation method for CDR channel asymmetry in a high-speed transmission system, which is simple to implement, has a faster convergence speed and better performance.

This application provides a multi-agent collaborative decision-making system, method, electronic device, and medium. In this system, a multi-agent orchestration module decomposes tasks and assigns them to different agents. A credibility assessment module outputs a system credibility assessment value based on historical operational data. A dynamic confirmation gate module combines the current collaborative decision-making stage, the system credibility assessment value, and task risk assessment data, sending decision confirmation requests to the user only when necessary. A recording module filters and statistically analyzes the execution information of each decision session, generating decision indicator information. A stage switching module dynamically adjusts the collaborative decision-making stage accordingly, enabling human-machine collaboration permissions to adaptively upgrade and downgrade based on system performance. When the system is stable over a long period, it can automatically upgrade the stage and reduce manual intervention, continuously lowering the decision error rate. When frequent errors or constraint violations occur, it automatically downgrades and tightens the confirmation boundary, using manual supervision to correct deviations in a timely manner, thereby improving the overall accuracy of multi-agent collaborative decision-making.

The application belongs to the field of electronic technology and relates to a burst mode clock data recovery circuit and method of baud rate sampling structure. The clock data recovery circuit comprises a sampling comparator circuit, a polarity flip detection circuit, a Mueller-Muller phase detector, a phase control state machine and a phase interpolator circuit. The sampling comparator circuit samples an input signal and a threshold amplitude to obtain a decision data signal and samples the input signal and a reference amplitude to obtain a decision error signal. The polarity flip detection circuit receives the decision data signal and outputs a phase lock signal. The Mueller-Muller phase detector receives the decision data signal and the decision error signal and outputs a phase too early / too late signal. The phase control state machine receives the phase lock signal and the phase too early / too late signal, and outputs a phase control code to the phase interpolator circuit to adjust the phase of a sampling clock. The application reduces the clock data recovery from three times oversampling to baud rate sampling, thereby reducing the power consumption and area of the circuit.

This embodiment discloses an AIS-assisted method for identifying sidelobe echoes in marine radar. It utilizes AIS data to establish a pre-selected area, removes the main lobe, determines the sidelobe, and then selectively zeros and restores the main lobe to achieve accurate identification and effective suppression of sidelobe echoes. This method effectively identifies and eliminates interfering sidelobe echoes, ensuring that the true echo (main lobe) of the target ship is not mistakenly detected, thus preserving the core information of radar detection. After suppressing the sidelobes, the radar range-azimuth image becomes clearer, reducing interference from false targets. This helps the navigator more accurately assess the surrounding navigation situation, reducing the risk of navigational decision errors and improving the readability and safety of radar images. Furthermore, the introduction of AIS reported target data as a high-precision reference makes the locking of the main lobe echo more stable, avoiding potential biases that might arise from relying solely on the radar image's own features for clustering, thus providing technical support for suppressing or eliminating sidelobe echoes.

The invention relates to an object recognition method and device, electronic equipment and a storage medium. The method comprises the steps that a to-be-recognized driving scene graph is input into a preset object recognition model for multi-level feature extraction; inputting the first-level driving scene features into a first recognition prediction layer in a preset object recognition model for first category prediction processing to obtain a first prediction object category; inputting the second-level driving scene feature and the first prediction object category into a second identification prediction layer in a preset object identification model for second category prediction processing to obtain a second prediction object category; and inputting the third-level driving scene feature and the second prediction object category into a third identification prediction layer in a preset object identification model for third category prediction processing, thereby determining a target object category corresponding to the to-be-identified driving scene graph. According to the embodiment of the invention, similar object categories in the to-be-recognized driving scene graph can be effectively distinguished, the classification precision and reliability are improved, and automatic driving decision errors are reduced.

The invention provides an error priority processing method, a control device, a storage medium and a system, and belongs to the technical field of data processing. The method comprises the following steps: determining an application scene based on acquired running state data; based on the obtained related data of the error event and the determined application scene, error feature parameters are extracted; determining a dynamic weight coefficient for the application scene according to the application scene and the error feature parameter; and according to the dynamic weight coefficient and the error characteristic parameter, sorting the priorities of the error events, so as to process the error events according to the priority sorting. According to the invention, the dynamic weight coefficient can be dynamically adjusted for the application scene; different application scenes and equipment states can be adapted, and the priority of error events is dynamically decided; and the probability of system crash or key task interruption caused by priority misjudgment can be effectively reduced.

The application discloses a kind of radiation effect simulation test data credibility evaluation method, solve due to lack of quantitative data credibility evaluation method, user can only rely on experience to judge the credibility of data, strong subjectivity, lack of systematicness and standard, it can lead to technical problems of decision error;Combining fuzzy comprehensive evaluation method and analytic hierarchy process, the factors influencing the credibility of radiation effect simulation test data are combed from the side of data production process, a judgment matrix is established, some factors with unclear boundaries and not easy to quantify are quantified, and a comprehensive evaluation of the membership grade status of data credibility is carried out, solving the problem of quantitative evaluation of radiation effect simulation test data credibility.The method has strong self-adaptation capability, and the factor set, evaluation set, judgment matrix and membership matrix can be adjusted according to the understanding of data and its use, while the method proposes a constraint condition for the judgment matrix to ensure that the method can be used correctly.

The invention relates to the technical field of cost-benefit calculation, in particular to a molten iron cost and benefit measurement and calculation method for different furnace charge structures, which comprises the following steps: S1, furnace charge structure definition: determining at least two different furnace charge structures to be measured and calculated, each furnace charge structure comprising the type and proportion information of the corresponding furnace charge; s2, original data acquisition: acquiring furnace charge purchase cost, blast furnace energy consumption data, auxiliary material consumption data, molten iron yield data and production auxiliary data under each furnace charge structure as original input data; s3, cost and benefit calculation: on the basis of a preset molten iron cost calculation formula and a comprehensive benefit calculation formula, the verified original input data are substituted into the formula, and the molten iron unit cost of each furnace burden structure is calculated; and S4, optimal scheme screening: comparing calculation results of different furnace charge structures, and screening an adaptive blast furnace production process. The problems that in a traditional mode, furnace burden structure measurement depends on manual work, errors are prone to occurring, and decision errors are caused due to the fact that data are not verified are solved.

The invention discloses a multi-fidelity model construction method based on hyperplane correction, and belongs to the technical field of multi-fidelity agent models. According to the invention, the multi-fidelity model approximately replaces an expensive high-fidelity model. The core of the method is that a hyperplane correction mechanism is introduced to explicitly learn and correct a feature mapping relationship between models with different fidelity in an input space, so that the dependence on the number of high-fidelity samples is remarkably reduced, and meanwhile, the low-fidelity model and the high-fidelity model are accurately corrected; and finally, a multi-fidelity agent model with high prediction precision and strong generalization ability is constructed. In the face of new design points or working conditions with strong nonlinearity and multi-modal characteristics, the model constructed by the method shows better generalization performance and prediction robustness, and the risk of optimization decision errors caused by model mismatch is reduced; the method provides a visual quantitative basis for the main source of the difference between the high-fidelity model and the low-fidelity model, and has better interpretability.

This invention relates to the field of intelligent traffic control technology, and discloses a road network high-traffic emergency response system and method based on an artificial intelligence large-scale model. The system includes a data reliability fusion module, a traffic flow prediction module, a safe passage decision module, a cross-departmental collaborative scheduling module, and a passage decision optimization module. It performs spatiotemporal coupling analysis on pre-acquired traffic state matrix and road topology map data to obtain a congestion probability estimate, then performs passage decision analysis to obtain an initial traffic restriction plan. Combining emergency resource location data, it allocates permissions to multiple departments, generates multi-departmental collaborative instructions, and performs decision error analysis to obtain correction parameters. Based on the correction parameters, it generates an optimized traffic restriction plan. This invention can improve the efficiency of handling road congestion events.

The invention discloses a virtual power plant resource decision optimization management method and system based on big data driving, and relates to the technical field of data management. The virtual power plant resource decision optimization management method and system based on big data driving comprises the steps that risk component data and operation performance data of a virtual power plant are collected, preprocessed and stored to construct a virtual power plant management database; data quality risk analysis is carried out by evaluating communication continuity, equipment stability and meteorological disturbance, risk priority ranking is carried out according to a risk analysis result, and data classification labeling is carried out; fusing the data quality, the label influence and the time continuity, measuring the adaptation degree between the data and supply and demand prediction, and constructing a supply and demand prediction model; and aiming at the prediction error, the output deviation, the constraint touch and the data quality, the feedback optimization effect is measured. The problems of inaccurate data cleaning and resource scheduling decision errors caused by difficulty in defining the abnormal data boundary in the virtual power plant are solved.

The invention provides an LDPC-assisted non-orthogonal multiple access interference elimination method, receiving method, sending method and device, and relates to the technical field of transmission, and the interference elimination method comprises the steps: carrying out the continuous interference elimination of a non-orthogonal multiple access signal recovered from an optical signal, so as to obtain a large signal and a small signal, performing LDPC decoding on the large signal to obtain a decoded bit sequence; and reconstructing the large signal based on the decoding bit sequence to obtain a target large signal, and obtaining a target small signal based on the target large signal and the non-orthogonal multiple access signal. According to the invention, the noise generated by the judgment error of the large signal on the small signal can be effectively reduced in the non-orthogonal multiple access interference elimination process, the error rate of the small signal can be effectively reduced, the application performance of the small signal can be improved, and the power margin can be more reasonably utilized; and the reasonability of distributing the signals to the users can be improved to improve the user experience.

The invention discloses a scenic spot early warning prompt interaction method. The method comprises the steps of S1, collecting the highest altitude and the lowest altitude of a scenic spot and the average altitude of a downtown where the scenic spot is located; s2, whether the highest altitude or the lowest altitude of the scenic spot exceeds a preset altitude threshold value or not is judged, and if yes, high-reflection early warning is carried out. The invention further discloses a scenic spot early warning prompting system which comprises a data acquisition module, a calculation module, a judgment early warning module and a storage module. The highest altitude and the lowest altitude of a scenic spot and the average altitude of a downtown where the scenic spot is located are systematically collected, a temperature difference value is converted in combination with a clear air temperature vertical declining rate formula, meanwhile, a 3000-meter high reflection threshold value and a 5 DEG C temperature difference threshold value serve as judgment standards, originally scattered and fuzzy environment risk information is converted into an accurate and quantifiable early warning result, and the early warning effect is achieved. Decision errors caused by information interpretation deviation can be effectively reduced, and the information acquisition and travel planning cost is remarkably reduced.

The invention relates to the field of production, supply and marketing process management, is used for solving the problems of information lag, slow supply chain response and increased operation risk of an ERP data management system, and particularly relates to an ERP data matching management method and system based on a whole production, supply and marketing process. According to the method, a unified global data mapping and data real-time synchronization channel is constructed, bidirectional real-time data circulation among a producer, a supplier and a seller is realized, key data variation of any service node can be captured in real time, and the key data variation is converted into an associated event to be broadcasted to all related parties; the overall agility and resource utilization efficiency of the supply chain are improved, meanwhile, when real-time circulating events flow through key nodes, the events and a dynamic baseline are subjected to approval analysis and threshold comparison, data abnormity is accurately judged, directional early warning is triggered, noise data are effectively filtered, decision errors caused by spreading of error information in the chain are prevented, and the service life of the chain is prolonged. And risk management and control is improved from passive response to active prevention.