35results about How to "Avoid misleading" patented technology

The invention provides a geoscience specimen digital acquisition and management system, and relates to the technical field of geoscience specimen acquisition, and the system comprises a data acquisition module which collects specimen attribute fields, specimen photos and process metadata; the data quality evaluation module is used for performing bidirectional modulation on the basic weight based on the dependency relationship set of the fields to obtain an effective weight, and calculating an integrity score based on the effective weight; calculating an accuracy score, a specification degree score and a timeliness degree score; calculating to obtain a comprehensive quality score; the data optimization suggestion module is used for generating an optimization suggestion according to the score of each dimension and the score of the comprehensive quality; and the data storage management module is used for storing specimen attribute fields, specimen photos, process metadata, quality evaluation results and optimization suggestions. According to the method, the quality problem can be recognized in time, targeted optimization suggestions can be automatically generated, and intelligent priority recommendation is provided for field acquisition based on historical quality statistical data, so that the quality and efficiency of geoscience specimen data acquisition are improved.

The invention belongs to the technical field of power equipment state monitoring, and discloses a transformer discharge detection method and system with an anti-interference function, and the method comprises the steps: obtaining a multi-mode discharge original signal of a transformer, carrying out the synchronization of a coefficient through a channel, anchoring a synchronous interference signal, extracting initial multi-dimensional features, and carrying out the detection of the multi-mode discharge original signal. Performing weighted average fusion on the initial multi-dimensional features according to a channel synchronization coefficient to obtain an anti-interference feature vector; constructing a feature screening-interference immune lightweight neural network model, inputting anti-interference features, taking a channel synchronization coefficient as an interference immune factor, and outputting a discharge type identification result; and obtaining an evaluation index by combining the peak amplitude of the multi-mode discharge original signal of the transformer after the de-noising preprocessing, and obtaining a discharge risk level based on the evaluation index. According to the invention, accurate identification and risk grade evaluation of transformer discharge are realized, and the problems of poor anti-interference performance and the like are solved.

The invention discloses a multi-modal tampering information detection and positioning method based on mitigation of modal misleading. The method comprises the steps of S1, image tampering region identification, S2, non-tampering region and text interactive learning, S3, LLM knowledge supplementation, and S4, tampering identification and positioning. After a tampered area and a non-tampered area of an image are recognized, an LLM generates explanation of text modal background knowledge, and the consistency of the text modal and the background knowledge and the consistency of the image modal and the background knowledge are compared to serve as the basis of multi-modal tampering information detection and positioning, so that the modal misleading of multi-modal tampering information detection and positioning is relieved.

The application belongs to the technical field of mechanical fault diagnosis, and discloses a rolling bearing small sample fault diagnosis method and system based on an online soft label Gaussian prototype network. The method collects bearing vibration signals under different working conditions to construct a data set, divides the data set into a meta-training set and a meta-testing set, and splits the data set into a support set and a query set; a Gaussian prototype network model containing embedding, prototype calculation and classification modules is constructed; in the meta-training stage, soft labels are dynamically generated by using an online soft label strategy, hard label loss is combined to carry out multi-task training to obtain optimal parameters; in the meta-testing stage, Gaussian prototypes are constructed based on the support set, classification is realized by calculating the Euclidean distance between samples and prototypes, and when the feature distribution drifts, the prototype parameters are fine-tuned to adapt to cross-condition diagnosis. The method effectively alleviates label noise interference, can still guarantee diagnosis accuracy under a small number of labeled samples, and significantly improves the model generalization ability and diagnosis stability.

The invention discloses a silicon controlled rectifier forward and reverse bidirectional switching solid-state module, and aims to solve the problems that an existing silicon controlled rectifier switching scheme is high in short circuit risk, high in cost and complexity and difficult to maintain, and a simple relay replacement scheme is short in service life. According to the technical scheme, the device comprises a hardware circuit structure and a single-chip microcomputer control logic part, the hardware circuit structure comprises a main loop silicon controlled rectifier unit, a relay switching unit, a single-chip microcomputer control unit, a signal acquisition unit and a power supply unit, and a mixed topological structure of three main loop silicon controlled rectifiers and a common double-pole double-throw relay is adopted. And in cooperation with closed-loop control logic of load state judgment, silicon controlled rectifier turn-off, relay switching and silicon controlled rectifier conduction, current forward and reverse safe switching is realized. Two silicon controlled rectifiers for switching are omitted, so that the risk of short circuit is thoroughly avoided; the relay is switched only when the silicon controlled rectifier has no output, so that the service life is prolonged; the circuit structure is simplified, the hardware and maintenance cost is reduced, and the anti-interference capability is remarkably improved.

This application discloses a GIS high-voltage switch housing with a safety protection structure for use in the field of high-voltage switches. This switch housing, through the inclusion of a sealing protection mechanism, allows the mechanism to monitor the sealing performance of the main housing. If a problem occurs in the sealing performance of the main housing, leading to SF6 failure... 6 When a gas leak occurs, the trigger board will activate the leak detection switch, causing the alert control module to activate the alarm and alert the staff. This allows staff to detect the gas leak in a timely manner and prompts them to conduct appropriate inspections and maintenance. This provides a protective effect, reducing the impact of problems with the casing's sealing. Furthermore, through the installation of gas sensors and gas analysis modules, when the leak detection switch is triggered, the sealing protection mechanism will also perform a self-check on its internal sealing to prevent false alarms. This avoids misleading staff and greatly improves practicality.

The utility model provides an anti-counterfeiting packaging film which comprises an AL film, an OPP film, a VC film, a false anti-counterfeiting mark, a covering anti-counterfeiting piece and an anti-counterfeiting two-dimensional code, the AL film, the OPP film and the VC film are compounded together, and the false anti-counterfeiting mark is printed on the OPP film; an anti-counterfeiting two-dimensional code is arranged on the AL film, and the AL film is compounded with the covering anti-counterfeiting sheet; according to the utility model, the AL film, the OPP film and the VC film are compounded, so that the composite film has protection and mechanical properties; the anti-counterfeiting mark and the anti-counterfeiting two-dimensional code are arranged in a staggered manner, and dynamic anti-counterfeiting of the thermosensitive covering anti-counterfeiting piece is matched, so that the anti-counterfeiting reliability and concealment are improved, and the anti-counterfeiting device is not easy to counterfeit.

The application discloses a power distribution box remote inspection management method and system based on an Internet of Things, and relates to the technical field of power distribution equipment operation and maintenance management. In view of the problem that remote inspection defaults to adopt sensing data, and after sensing link failure, back transmission of smooth false data forms virtual inspection, the method carries verification incentive configuration in the inspection instruction, executes switching of incentive objects selected from existing controllable loads in the power distribution box by the intelligent gateway, and synchronously collects the output of each sensor in the verification observation window; item-by-item comparison is performed according to three types of expected response modes of change, slow change and invariance of the incentive response verification table, link credibility and link abnormality are distinguished; only when verification is passed, the inspection data is adopted, an inspection work order is dispatched for an abnormal channel, and previous data is marked for rechecking according to a tracing period, and if the abnormality exceeds an upper limit, manual inspection is performed, remote alarm is temporarily stopped, and the inspection interval is adaptively adjusted according to the verification passing condition. The application can verify the authenticity of the sensing link without adding hardware, and is suitable for remote inspection of the power distribution box.

This disclosure proposes a method for synthesizing multimodal data for decision-making attribution explanation in the mining industry, comprising the following steps: First, extracting causal logic from industry texts to construct a structured rule base; second, collecting on-site multimodal data and filtering out data pairs strongly correlated with rules through scenario-based weight modeling and cross-modal association mechanisms; third, using a multimodal generative adversarial network with rule constraint mechanisms and combined with rule mutation technology to synthesize multimodal data with complete logical chains and covering various complex working conditions; finally, ensuring data quality and achieving self-evolution of the knowledge base through a three-level verification and rule feedback mechanism, and storing qualified data in a hybrid storage database. This invention solves the problems of complex causal relationships and scarce high-quality training samples in the mining field, and can automatically and in batches generate logically rigorous and scenario-diverse multimodal data, improving the training efficiency and generalization ability of attribution decision models.

A kind of high reliability anti-reverse connection circuit suitable for redundant dual controller, increase high side MOS gate auxiliary circuit and sensor low side MOS control circuit.When power is connected, auxiliary circuit does not work;When power is reversed, triode T1, T2 is turned on, and then the gate voltage of MOS Q1, Q2 is pulled to the GND of reverse connection, so that the gate-source voltage of Q1, Q2 is lower than threshold value, to ensure the reliable and stable turn-off of MOS on power bus, at the same time, the gate voltage of MOS Q3, Q4 is also pulled to the GND of reverse connection, so that the gate-source voltage of Q3, Q4 is lower than threshold value, to ensure the reliable and stable turn-off of MOS on sensor ground wire.Diode D1 and D2 realize that this part of circuit does not conduct when power is connected, and only works when power is reversed, resistance RH and RL provide base bias voltage of triode and play the role of current limiting.This application realizes the high reliability anti-reverse protection of redundant dual controller system and external common ground sensor through the distributed configuration of high and low side MOS on the input end of automobile main load power supply and the backflow end of sensor ground wire and the design of targeted auxiliary circuit, and the anti-reverse circuit design scheme suitable for redundant dual controller can effectively realize the high reliability anti-reverse protection.

The application discloses a terminal crimping die tracking information management method for automobile wire harness, relates to the technical field of information processing, and comprises the following steps: acquiring crimping records generated in a continuous operation state and corresponding time position marks, performing trajectory sketching on sequence changes of the crimping records in a writing process, performing expansion processing on the crimping records according to a time advancing relationship, and forming basic record data. The application realizes identification and positioning of repeated writing and covering behavior by sketching sequence changes of crimping record writing and extracting periodic characteristics, restores a real advancing relationship of records, guarantees accuracy of a corresponding relationship of data, controls subsequent writing rhythm at the same time, makes record distribution tend to be balanced, suppresses a covering trend, maintains continuity of a record trajectory, and improves data stability and quality traceability reliability.

The utility model provides an IGBT driving circuit based on a push-pull structure, and relates to the technical field of power electronic device driving, and the IGBT driving circuit comprises an optocoupler isolation module which is used for receiving a control signal and providing electrical isolation output; the push-pull driving module comprises an NPN type triode Q1 and a PNP type triode Q2 which are complementary and symmetrical; the push-pull driving module is configured as follows: when the optocoupler is conducted, Q1 is saturated and conducted, Q2 is cut off, and a driving current charges an IGBT grid electrode through R2; when the optocoupler is turned off, the Q2 is saturated and turned on, the Q1 is turned off, and the driving current flows through the R3 to discharge the grid electrode of the IGBT. Bidirectional driving current is provided through a push-pull structure, the charge charging and discharging speed of the IGBT grid electrode is increased, the switching loss is reduced, bidirectional driving current is provided through a switch-on resistor R2 and a switch-off resistor R3, the resistance value of the switch-on resistor R2 is selected to be small, the purpose of reducing switch-on loss Eon is achieved, the resistance value of the switch-off resistor R3 is selected to be large, and the purpose of reducing switch-off Vce is achieved.

This invention relates to the field of natural language processing, specifically to a method and system for evaluating and selecting training value of corpus for incremental pre-training. The method involves: acquiring the forward inference results of a base model on a general corpus; segmenting the acquired candidate incremental corpus into text segments; performing forward inference on each text segment using the base model to obtain a first predicted probability distribution; performing forward inference on the lightly augmented text segments using the base model to obtain at least one second predicted probability distribution; calculating four evaluation signals for each text segment based on the first and second predicted probability distributions; weighting and fusing the four evaluation signals to obtain a comprehensive training value score for each text segment; and selecting the target corpus from the candidate incremental corpus based on the comprehensive training value scores of all text segments. This invention solves the problem of a single dimension in corpus value evaluation, effectively controls noisy samples, and significantly improves the resource utilization efficiency of incremental pre-training.

The application discloses a kind of anti-degradation multi-sensor fusion SLAM method and system, belong to robot synchronous positioning and mapping technical field.The method includes obtaining original data from camera, laser radar, inertial measurement unit and global navigation satellite system, based on VIG tight coupling optimization unit, original data is preprocessed and initial estimate in front end, obtain global pose, based on LIG tight coupling optimization unit, motion distortion correction and feature extraction processing are carried out by original data and global pose, based on two-stage factor graph optimizer, laser feature and GNSS observation information are fused in two stages, global optimization is executed, and high-precision, globally consistent pose and map are output.The application overcomes the limitation of single sensor, suppresses cumulative error, realizes high-precision, high robustness and global consistency positioning and mapping in large-scale complex scene outdoors.

This invention relates to a method for real-time online detection of wastewater indicators. Before detection, a low-concentration water body is injected into the detection chamber to perform micro-dose detection. By observing whether there is a nonlinear shift in the initial response behavior, it is determined whether there is residual response on the inner wall of the detection chamber. If so, a local delayed detection and pre-rinsing operation is performed to suppress interference responses caused by the chemical memory of the detection chamber. After completing the pre-response suppression, a slow-varying physical stimulus process is applied to the wastewater to be tested, stimulating the release of masked pollutants in the wastewater. The pollutant response signals are continuously tracked, and fluctuating behavior is identified. Based on the changing trend of the response curve, a stable response interval is identified as the sampling point for final detection. For cases with superimposed responses from multiple pollutants, the rise rate, fall rate, and tailing characteristics of the response profiles of each indicator are analyzed to identify the physical differences of multiple response signals and perform physical-level decoupling, improving the accuracy of identifying multiple pollutants.

The application discloses a switch cabinet intelligent protection measurement and control method and system based on a double-CPU architecture, and relates to the technical field of measurement and control methods. The method based on the double-CPU architecture comprises the following steps: step S1, a protection CPU collects on-off state data; a measurement and control CPU monitors audio starting conditions; step S2, the measurement and control CPU continuously monitors human body proximity detection data; step S3, a formal broadcast sequence is a formal audio prompt tone for prompting the on-off state data; step S4, after the formal broadcast sequence of the cabinet is completely finished, the adjacent cabinet body re-executes step S1; and step S5, the measurement and control CPU continuously monitors the on-off state data forwarded by the protection CPU. Through the mechanism of step S1, the system can complete detection and confirmation of the presence of an operator before formal broadcasting, thereby reducing invalid voice output in a no-one scene, reducing noise interference and system resource occupation.

This application relates to the field of slope monitoring technology and discloses a calibration method and apparatus for highway slope monitoring signals based on deformation characteristics. The method includes: collecting raw monitoring data through a network of monitoring sensors installed on the surface of the highway slope; cleaning the raw monitoring data to remove outliers and noise interference, obtaining a standardized deformation data sequence; extracting deformation features based on the standardized deformation data sequence using a deformation trend recognition algorithm to generate a deformation feature set; converting the dimensions of multiple deformation features in the deformation feature set into calibration signal control dimensions; wherein the calibration signal control dimensions include control amplitude dimension, control frequency dimension, and control phase dimension, and each dimension of the deformation feature is converted into a corresponding calibration signal control dimension; generating a calibration monitoring signal based on the multiple dimensions of the calibration signal control dimensions and outputting it. This achieves effective calibration of slope deformation monitoring signals, providing reliable support for slope stability monitoring.

The invention provides an aluminum wire forming control system, method and device based on load feedback, and relates to the technical field of material processing industry control. Comprising a load acquisition and historical window construction module, a load window segmentation identification module, a load memory feature extraction module, a load memory feature vector construction module, a load decoupling and equivalent load generation module, a control parameter inversion calculation module and a load memory state updating module. According to the method, a load historical window is taken as a core, continuous acquisition and segmented identification are carried out on a formed load, a load hysteresis characteristic and a historical residual effect are introduced, and the problem that traditional control only depends on an instantaneous load and is difficult to reflect historical influence is solved. A real-time load is split into an instant response component and a historical residual component, and historical residual influence is dynamically reduced, so that excessive compensation and control oscillation caused by load memory are avoided. By constructing a load intelligent control system, collaborative optimization of load sensing and control in the aluminum wire forming process is achieved.

This application relates to the field of semiconductor technology. Embodiments of this application provide a surge negative charge driving circuit and a switching power converter for suppressing crosstalk, comprising: a driving module and a surge negative charge module; a first terminal of the driving module receives an input signal, and a second terminal of the driving module is connected to the gate node of a silicon carbide MOSFET, used to control the turn-on and turn-off of the silicon carbide MOSFET according to the input signal; a first terminal of the surge negative charge module receives the input signal, a second terminal of the surge negative charge module is connected to a power supply terminal, a third terminal of the surge negative charge module is connected to a ground terminal, and a fourth terminal of the surge negative charge module is connected to the gate node of the silicon carbide MOSFET, used to release negative charge to the gate node during the turn-off process of the silicon carbide MOSFET when the drain voltage of the silicon carbide MOSFET rises, causing Miller current to flow back to the gate node, in order to neutralize the Miller current. Highly efficient crosstalk suppression is achieved through the physical method of charge neutralization, without relying on a continuous negative voltage power supply, simplifying the system architecture and reducing costs.

The invention provides a water surface floating object classified cleaning robot for a water storage reservoir of a hydropower station and a working subarea setting method. The robot comprises a large garbage collector, a small garbage collector and a movable connecting structure, a water pump is arranged in the large garbage collector to provide suction force, and both the large garbage collector and the small garbage collector are provided with filter screens. After the robot enters water, openings of the large collector and the small collector are located under the water surface, water and garbage enter the corresponding collectors respectively under the suction action of the water pump, the garbage is intercepted through the filter screens, and the water is discharged. The small garbage collector is provided with a garbage recognition camera, and a driving propeller is arranged on the outer side of the large garbage collector. Large and small garbage can be collected in a classified mode, the collecting angle is adjusted through the multiple sleeves, and the feeding effect is improved; on the basis of grid discrete calculation, a weighted Voronoi distribution mechanism is adopted, a plurality of optimal working sub-areas are generated, and multi-robot efficient operation is achieved.

This application relates to a circuit breaker, electronic equipment, and a method for driving the circuit breaker. The driving circuit includes a first suppression circuit and a second suppression circuit; the first suppression circuit is connected to the control electrode of a first switching transistor and a controller external to the circuit breaker, respectively; the second suppression circuit is connected to the control electrode of the second switching transistor and the controller, respectively; the first suppression circuit is used to transmit the control signal from the controller to the second switching transistor and suppress the crosstalk current generated during the turn-on and turn-off of the second switching transistor; the second suppression circuit is used to transmit the control signal from the controller to the first switching transistor and suppress the crosstalk current generated during the turn-on and turn-off of the first switching transistor. Using this application, bidirectional suppression of both positive and negative crosstalk can be achieved, enhancing the reliability of the circuit.

The application discloses a crosstalk suppression circuit and an electric device, the crosstalk suppression circuit comprises at least two MOS transistors connected in series to form a half-bridge circuit, and a driving circuit for driving the MOS transistors to work, and the crosstalk suppression circuit at least comprises a clamping circuit connected between the gate and the source of the MOS transistors, and a driving monitoring unit connected to the output end of the driving circuit; the clamping circuit is configured to clamp the gate-source voltage of the MOS transistors to 0V when in the on state; the driving monitoring unit is configured to provide a control level capable of turning on the clamping circuit when monitoring that the driving circuit provides a driving voltage capable of turning on the MOS transistors. Compared with the prior art, the application realizes active clamping control of the gate-source voltage of the MOS transistors, can prevent the MOS transistors from being mis-conducted or broken down due to crosstalk, and improves the stability and reliability of the system.

The application discloses a dairy product pre-packaged food automatic detection system and relates to the technical field of dairy product packaging detection.The system comprises a water storage tank containing water and further comprises a vertical plate fixed to the top of one side of the water storage tank, a fixed shaft is fixed to the outer wall of the vertical plate, and a rotatable rotating plate is installed on the fixed shaft; a clamping assembly is installed on the rotating plate and used for clamping and fixing the packaging product; a first sleeve is fixed to the outer wall of the rotating plate and is sleeved on the fixed shaft; a second sleeve is slidingly installed on the outer wall of the fixed shaft through a flat key, a second spring is connected between the second sleeve and the vertical plate, and the opposite surfaces of the first sleeve and the second sleeve are both provided with spiral inclined surfaces. Through cooperation between structures, the vibration force generated by impact can shake off the bubbles attached to the clamping assembly and the surface of the packaging product, so that the bubbles cannot mislead the sealing property detection of the packaging product, and the accuracy of the sealing property detection is improved.

The application relates to a robot reinforcement learning control method, system, device and storage medium. The method comprises the following steps: obtaining real interaction data of a robot control task, constructing an environment dynamics model based on a probability neural network set by using the real interaction data, and capturing the uncertainty of a real environment and generating virtual data by using the environment dynamics model; combining the virtual data with the real interaction data to generate mixed training samples, training a parameterized policy network and a value network by using the mixed training samples; performing model-based reinforcement learning on the policy network and the value network, introducing a dynamic relative entropy regularization mechanism in the policy optimization process of the reinforcement learning, and generating an optimal policy of the robot control task. By introducing the dynamic relative entropy regularization constraint mechanism in the model-based policy optimization framework, the cumulative influence of the environment model prediction error is inhibited, and the training instability problem caused by the model bias is effectively alleviated.

This invention provides a retrieval enhancement generation method and system based on adaptive information bottleneck. The system includes a multi-strategy retrieval module, a joint embedding encoding module, a compressed-sensory reordering module, an adaptive information bottleneck compression module, and a large language model generation module. The method includes the following sub-steps: S1: Obtain candidate text blocks; S2: Perform compressed-sensory reordering on the initial candidate text blocks to filter highly relevant text blocks; S3: Perform vector encoding on the context text and query statement q; S4: Perform adaptive information bottleneck compression; S5: Generate the question-and-answer result for query statement q. This method dynamically compresses the retrieval results through adaptive information bottleneck, reducing the context occupation of the large language model, lowering inference costs, shortening response latency, and improving system operating efficiency; it filters highly relevant text blocks through compressed-sensory reordering, filtering irrelevant information, avoiding noisy content from misleading the model, and improving the accuracy of the answer.

The application discloses a method and device for intelligently identifying the calculability of a power supply area file verification driver and a storage medium, and relates to the technical field of power supply area data processing. The method performs multi-dimensional file element verification on a power supply area file and constructs a power supply area metering topology structure; performs file anomaly identification according to the structure validity and file completeness, marks the structure as uncalculable and prevents it from entering the operation data quality evaluation when there is a file anomaly; performs secondary determination on the data completeness rate, line loss rate rationality, light and heavy load state and power balance deviation of the structure calculable power supply area, takes the structure validity as the calculability criterion, and completes the access control before the operation data calculation, so as to avoid the pollution of the non-physical operation data of the invalid power supply area structure to the statistical sample pool and realize the accurate identification of the calculability of the power supply area.

This application discloses a digital management method and system for hospital nursing quality indicators, relating to the field of medical and nursing quality information technology. The method includes the following steps: setting assessment rules for evaluating nursing process quality indicators; acquiring patient nursing records and constructing a patient-centered event time series; based on the assessment rules, filtering nursing events related to the corresponding nursing process from the event time series; dynamically adjusting the strictness of the assessment rules based on the identity information of nursing staff and the clinical status information of patients; verifying the event time series according to the adjusted assessment rules and obtaining verification results; determining the compliance of the nursing process based on the verification results, and generating a compliance conclusion and audit report for the nursing process. This application can intelligently distinguish between genuine nursing quality defects and discrepancies in record appearances caused by differences in personnel and context, solving the problems of fragmented processes, isolated data, and delayed assessment in traditional nursing quality management.

The invention relates to the technical field of atomization equipment, and discloses a power-on prompting method of atomization equipment, the atomization equipment and a readable storage medium, and the power-on prompting method comprises the steps: obtaining reset source information and identification data of a preset storage area after power-on; determining a reset type according to the reset source information and the identification data; and displaying power-on prompt information according to the reset type. According to the technical scheme, the situation that short-circuit reset is misjudged to be normal power-on in the prior art is effectively avoided, so that it is ensured that the system can output a correct protection prompt under the abnormal condition, and misleading caused by mistakenly displaying starting-up information is avoided.

The application discloses a multi-modal residual value evaluation method and system for mobile terminal pre-set-off, and belongs to the field of electric digital processing, comprising the following steps: migratable feature acquisition, migratable feature reliability evaluation, residual value evaluation result verification and mobile terminal pre-set-off. The application analyzes migratable features by inputting static data into a migration learning model, synchronously evaluates the reliability of the migratable features, determines whether to take reliability adjustment measures based on the evaluation results, then performs residual value evaluation to output residual value analysis results for credibility verification, pre-sets off the mobile terminal to be evaluated based on the residual value analysis results after credibility verification, and determines whether to end the lease period based on the reservation mechanism triggered by the mobile terminal to be evaluated after the preset lease period, thereby improving the accuracy of pre-set-off data and solving the problem of reduced accuracy of pre-set-off results due to reduced reliability of residual value evaluation results in the prior art.

The application belongs to the technical field of navigation and positioning, and specifically discloses a method and system for cooperative positioning of unmanned aerial vehicles (UAVs) in a satellite denial environment. The application uses the relative distance information between cluster UAVs to design a cluster UAV cooperative positioning system architecture based on relative information assistance. Through the architecture, the communication between the inertial navigation system and the UAV cluster can provide more reliable positioning services, and the selective correction adaptive particle filtering algorithm is combined to optimize the positioning accuracy. The method of the application uses the inertial navigation system to obtain the self-position of each auxiliary UAV, uses the exogenous relative distance sensor to measure the relative distance with respect to the UAV to be assisted, and then obtains the observation position of the UAV to be assisted. The result is brought into the improved particle filter for filtering to correct the drift error of the inertial navigation system, thereby improving the positioning accuracy of cooperative positioning in the denial environment.