277 results about "Decision threshold" patented technology

The invention discloses a self-adaptive low-delay motion scene live broadcast method and system, and particularly relates to the technical field of scene live broadcast. Through unified mapping and exception suppression of multi-source time sequence data, a multi-scale sliding window predictor and a short-time autoregression and long-time trend sensing algorithm are combined; a more accurate bandwidth prediction result with interval confidence description is generated, characteristics such as offset cumulant, fluctuation intensity and error residence time are extracted by using a residual trajectory, threshold crossing frequency, switching amplitude, direction alternation rate and critical zone residence duration are analyzed synchronously with a parameter switching log, critical oscillation characteristics are formed, and the bandwidth prediction accuracy is improved. The risk identification is more accurate, the high-frequency oscillation risk score of the system is calculated through a normalization and time sequence risk identifier, the risk assessment result is mapped into an executable stable intervention strategy, the system state observation sequence after adjustment execution is subjected to short-time assessment, and a feedback packet is formed to write back a closed loop. And online optimization of the weight, the decision threshold and the cooling time of the bandwidth predictor is realized.

The invention belongs to the technical field of radar signal processing, and discloses a sea surface small target detection method based on optimized characteristic mode decomposition, which comprises the following steps: S1, acquiring to-be-detected signal data; s2, decomposing an original signal into a plurality of modal components by using FMD, and selecting an envelope spectrum entropy as a fitness function; s3, performing global optimization on the fitness function in the FMD by using an SOS algorithm; s4, introducing a PSO algorithm to carry out local optimization on key parameters of the FMD; s5, components with low envelope spectrum entropy values and correlation coefficients larger than a threshold value are reserved; s6, extracting an envelope spectrum entropy and frequency band energy ratio feature from the screened modal components, introducing a Gini coefficient as a weighting factor, and constructing a GSEBE joint feature; and S7, inputting the entropy value of the envelope spectrum into a DELM classifier with a controllable false alarm, and realizing target detection based on comparison between a predicted value and a judgment threshold. According to the invention, the capability of distinguishing sea clutters and target echoes is enhanced, and more accurate classification detection is realized.

The invention relates to a double-arm intelligent collaborative tea picking method and device based on multi-strategy dynamic scheduling, and belongs to the field of robot automation. The method comprises the following steps: obtaining three-dimensional coordinate information of a target picking point; identifying and positioning potential branch and leaf shields, and generating space data of the shields; the method comprises the following steps: simultaneously projecting a shielding object and a clamping jaw geometric contour under an expected grabbing pose on a plane where a target picking point is located, analyzing the overlapping amount, the proximity and / or the density of the projections of the shielding object and the clamping jaw geometric contour, and generating a standardized shielding evaluation index; comparing the shielding evaluation index with a preset decision threshold, and if the shielding evaluation index is greater than the preset decision threshold, executing a master-slave collaborative picking method based on multi-stage positioning; otherwise, executing the parallel picking method based on dynamic collision-free region division. The problems that a traditional single-arm tea picking robot is low in operation efficiency, high in collision risk and insufficient in intelligent degree in a dense and unstructured tea tree environment are solved.

The invention discloses an electric energy meter detection assembly line fault diagnosis and prediction method based on multi-modal time sequence analysis. The method comprises the steps of collecting multi-modal data including electric energy meter visual data, time sequence sensor data and text log data in real time; performing cross-modal fusion of time sequence alignment on the multi-modal data to generate joint feature representation; performing joint optimization of fault diagnosis and prediction; performing fault diagnosis based on the joint feature representation, and outputting a current fault type and probability; predicting a future fault probability based on the equipment state continuous evolution model; in response to batch conduction characteristics which are output by the prediction model and reach a preset abnormal value, triggering recalculation of the associated modal data; correcting an initial condition of the equipment state continuous evolution model according to the fault type obtained through re-calculation; and dynamically adjusting a diagnosis decision threshold according to the prediction confidence output by the corrected equipment state continuous evolution model.

The invention relates to the field of building construction safety, in particular to a risk prediction method and system for building construction. Aiming at the defects of multi-source data isolated analysis, dynamic risk response lagging, insufficient prediction precision and the like in the prior art, a unified analysis base is formed by constructing a space-time fusion data space and integrating multi-dimensional dynamic data such as structure micro-deformation monitoring, environmental parameters, three-dimensional live-action scanning, personnel positioning, a building information model and the like; based on a deep neural network architecture, designing a multi-modal feature extraction mechanism to quantify the coupling risk, and generating a partition risk probability distribution diagram; and in combination with a construction stage characteristic matching security policy library, implementing a three-level early warning mechanism and an automatic avoidance instruction. A closed-loop optimization mechanism is introduced, model parameters and decision threshold values are dynamically adjusted through actual accident feedback, and continuous evolution of a prediction system is achieved. According to the method, the active prevention and control capacity of compound accidents such as collapse and high-altitude falling is remarkably improved, and a self-adaptive intelligent protection system is constructed for a construction site.

The invention discloses a bearing defect intelligent detection method and system based on deep learning, and relates to the field of bearing defect detection. Multi-modal data such as bearing vibration, acoustics, thermal imaging and the like are acquired by using various sensors, and a four-dimensional feature tensor is constructed through preprocessing such as noise reduction and feature extraction; features are fused through a reconfigurable multi-branch convolutional neural network, and defects are identified and a development trend is predicted in combination with a meta-learning twin network; a decision threshold is optimized by adopting a quantum heuristic algorithm, and multi-level early warning is realized; and continuous evolution of the model is completed through edge-cloud collaboration and federated learning, the functions of data calibration compensation, model dynamic optimization and the like are achieved, and efficient and accurate detection of bearing defects is achieved. The detection time is remarkably shortened, and the positioning precision is high; the novel defect response speed is high, and faults can be predicted in advance; system energy consumption is reduced, model updating is improved, stable operation of equipment is effectively guaranteed, and cost reduction and efficiency improvement of industrial intelligent operation and maintenance are facilitated.

The invention discloses a method and system for detecting a well wall in real time, electronic equipment and a storage medium. The method and system are used for judging well drilling abnormity by analyzing the shape of rock debris. The method for detecting the well wall in real time comprises the steps that multi-mode underground real-time data are obtained; inputting the multi-modal underground real-time data into a pre-established anomaly recognition model, performing streaming reasoning, and outputting a recognition result; performing time sequence integration and trend analysis according to the identification result to obtain an analysis result; generating real-time alarm information according to a preset decision threshold rule and the analysis result; the anomaly recognition model is obtained through the following training method: acquiring multi-modal underground historical data; performing time synchronization processing and space positioning processing on the multi-mode underground historical data to obtain processing data; performing exception annotation on the processed data according to expert knowledge, and constructing an annotated data set; and training the multi-modal fusion anomaly recognition model according to the labeled data set to obtain an anomaly recognition model.

The invention relates to the technical field of power distribution fault positioning, in particular to a power distribution single-phase earth fault positioning method and device based on multi-source information fusion. The device comprises a data acquisition module, a fault line selection module, a grading emergency module, a fault positioning module and a parameter optimization module. According to the method, the zero-sequence current is monitored in real time, the dynamic change curve is generated, the fault line is accurately identified in combination with amplitude and phase characteristics, electrical parameters, environmental factors and load importance are fused to carry out comprehensive risk assessment and start a hierarchical response mechanism, and the fault point of the fault line is accurately positioned by adopting a voltage drop method. And the monitoring frequency and the decision threshold value are adaptively adjusted according to the fault characteristics and historical data, so that response lag and insufficient precision of a traditional fault positioning method are avoided, full-flow intelligent management from fault detection, accurate positioning to parameter self-optimization is realized, the accuracy and efficiency of fault processing are improved, and safe and stable operation of a power grid is ensured.

The invention relates to the technical field of magnetic detection, in particular to a target positioning method based on geomagnetic anomaly and an axis frequency magnetic field. Comprising the following steps: S1, preparing before entering water; s2, approaching a target; s3, target detection: when no target appears, an observation signal is composed of an environment magnetic field, and the energy value of the part is very small; once the target appears, the energy of the observation signal can be continuously and obviously increased, when the energy value is greater than a preset judgment threshold, the target point is judged as a suspected target point, and if the suspected point is continuously detected for a specified time, the existence of the target is confirmed; s4, combined positioning: under a Kalman filtering framework, enabling the target to be equivalent to a magnetic dipole and an electric dipole, and correcting a position predicted by a target state equation by combining measurement equations of the two models, thereby realizing combined positioning of the target and obtaining more accurate target position information; and S5, verifying and outputting a positioning result. The method has the advantages of improving the positioning precision, enhancing the anti-interference capability and the like.

The embodiment of the invention provides a CSI (Channel State Information) performance monitoring report triggering method based on an AI / ML (Artificial Intelligence / Markup Language) model and a related device, and provides a channel environment adaptive cumulative sum CUSUM algorithm, the algorithm configures different CUSUM parameter sets for different states of UE (User Equipment) respectively, each CUSUM parameter set comprises a relaxation factor k and a decision threshold h, and the relaxation factor k and the decision threshold h correspond to each other. The values of k and h in different parameter sets are different; the UE can select the most matched CUSUM parameter according to the current state (or scene), so that a performance monitoring mechanism of the UE can intelligently balance the detection sensitivity and robustness. Moreover, according to the scheme, performance differences are accumulated through a CUSUM algorithm and then compared with a decision threshold value to judge whether a performance degradation report is triggered or not, instantaneous jitter of a channel is effectively filtered through accumulation of the performance differences, and it is ensured that the report is triggered only when the performance of the AI / ML model continuously declines. Therefore, the uplink signaling overhead caused by mistaken touch and the resource waste caused by subsequent network response (such as mode switching) are reduced.

The invention provides an intelligent grading compressor control method and system based on load self-adaption, and belongs to the technical field of compressor control. The method comprises the steps that multi-dimensional data of a compressor unit is obtained through a distributed sensor network; carrying out preprocessing and feature extraction on the multi-dimensional data to obtain a feature vector; inputting the feature vector into a load prediction model to obtain a predicted load state; adjusting a decision threshold value of the grading decision tree based on the predicted load state to obtain a target grading decision tree; inputting the feature vector into a target grading decision tree to generate an execution scheme; obtaining energy efficiency feedback data for executing the execution scheme, inputting the predicted load state and the energy efficiency feedback data into the reinforcement learning model, and obtaining a control strategy by taking Pareto optimization as a target; and adjusting the control action of the compressor unit based on the control strategy. The operation energy efficiency of the compressor system is improved, and equipment mechanical loss and energy consumption are reduced.

The invention relates to the technical field of market trend prediction, and discloses a market trend prediction system driven by macroeconomic indicators. An index acquisition module of the system dynamically acquires core economic indexes such as GDP growth rate, CPI, PMI and currency supply; the data preprocessing module is used for carrying out layered noise reduction processing on the multi-source heterogeneous data; the feature engineering module constructs a market sensitive feature set through spatio-temporal feature fusion; the prediction model building module is used for building a multi-layer nonlinear prediction model based on a deep belief network; the dynamic adjustment module adopts reinforcement learning to optimize a decision threshold value and combines a Markov chain to carry out state transition planning; and the feedback iteration module analyzes and predicts deviation through Bayesian filtering and realizes strategy updating. According to the method, deep learning and reinforcement learning technologies are creatively fused, the prediction precision is remarkably improved through a dynamic calibration mechanism, and the method can be widely applied to the macroeconomic analysis fields of financial investment, industrial planning and the like.

The invention provides a micro-grid main grid cooperative switching intelligent regulation and control method and system, and relates to the technical field of power grid regulation and control. According to the method, the historical operation data of the micro-grid and the main grid are collected in real time, and the future operation state parameter set is generated, so that the operation states of the micro-grid and the main grid are accurately predicted. The dynamic stability index of the micro-grid and the power grid health index of the main grid are calculated, the two indexes serve as input, a switching decision management model is applied to generate a switching tendency score, and the switching tendency score is compared with a dynamic decision threshold value in real time to judge whether switching conditions are met or not. According to the method, the collaborative switching control instruction is automatically generated according to the correlation index and the switching mode rule, and the micro-grid is finely pre-adjusted in advance, so that smooth seamless switching between the micro-grid and the main grid is realized when the physical switching action is executed, and the safety, the reliability and the stability of the switching operation between the micro-grid and the main grid are improved.

The invention relates to the technical field of automatic driving, and discloses an automatic driving lane changing decision-making method based on risk assessment. The method comprises the steps of fusing multi-dimensional features according to real-time data of a vehicle surrounding environment, generating spatial-temporal feature representation containing position, speed and environment information, and realizing comprehensive perception of a complex traffic environment. And inputting the spatial-temporal feature representation into a risk assessment model, carrying out probabilistic modeling on an abnormal risk in a lane changing process, outputting a risk feature vector with confidence, and providing a refined risk reference for decision making. And then constructing a risk distribution field based on the risk feature vector, predicting a propagation path of the risk distribution field through a sequence prediction model, and prospectively perceiving the dynamic change of the risk. And finally, aiming at a prediction result, constructing a self-adaptive decision threshold generation model, and according to a comparison result of a real-time risk feature vector and a multi-level decision threshold, realizing an accurate and flexible automatic driving lane changing decision, and improving the safety and adaptability of a lane changing process.

The invention relates to the technical field of power system signal measurement, in particular to a mutual inductor digital sampling method and system. The method comprises the following steps: acquiring a signal output by a secondary side of a mutual inductor for a power system in real time; determining the load fluctuation degree at the current moment; determining a dynamic sensitivity coefficient at the current moment; obtaining a dynamic reference mean value, a dynamic relaxation parameter and a dynamic decision threshold value used in the CUSUM algorithm at the current moment; determining the cumulative sum between the signal and the dynamic reference value in the CUSUM algorithm at the current moment; and determining the sampling frequency of the mutual inductor according to the cumulative sum between the signal and the dynamic reference value in the CUSUM algorithm at the current moment and the size of the dynamic decision threshold so as to realize digital sampling of the mutual inductor. According to the invention, through adaptive adjustment of the reference mean value, the relaxation parameter and the decision threshold value, the rate of missing report and false report is reduced, and the identification capability of initial faults such as mutual inductor turn-to-turn short circuit and the like is improved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a data processing and decision-making method, device, equipment and medium, and the method comprises the steps: obtaining multi-dimensional source data, carrying out the standardization processing, screening the standardization data based on a decision-making scene, and obtaining a core index set, the method comprises the following steps: establishing and optimizing indexes, mining association characteristics among the indexes, constructing and optimizing a dynamic statistical model, carrying out standardization processing on newly added multi-dimensional source data, obtaining a key decision index value by utilizing the dynamic statistical model, and carrying out comparison judgment on the key decision index value and a preset decision threshold value, and generating a decision scheme by combining the comparison judgment result with a preset scheme generation mechanism. According to the method, multi-scene adaptive support and real-time decision optimization are realized through unified multi-dimensional data standardization, dynamic scene-driven core index screening and association characteristic mining, real-time model updating and closed-loop decision scheme generation.

The invention belongs to the field of power equipment state monitoring, and relates to a generator partial discharge on-line monitoring method, system, equipment and medium, and the method comprises the following steps: obtaining four types of original signals of a generator; extracting a partial discharge feature significant signal layer from the original signal by using an adaptive hierarchical denoising algorithm; constructing a feature quantity library based on the partial discharge feature significant signal layer, and extracting the frequency spectrum gravity center and wavelet energy entropy of each type of original signals; performing fuzzy logic weighting on the frequency spectrum gravity center and the wavelet energy entropy of each type of original signals to obtain a primary fusion result of each type of original signals; performing deep fusion on the primary fusion result of each type of original signals by adopting an LSTM neural network to obtain a partial discharge primary judgment result; and obtaining the score of the partial discharge preliminary judgment result based on the abnormal degree score of the mahalanobis distance, and if the score is greater than a decision threshold, determining that partial discharge occurs. The partial discharge of the generator can be quickly and effectively judged, and field operation and maintenance personnel can respond to the partial discharge conveniently.

The invention discloses a data processing system for territorial space planning based on big data, and relates to the technical field of big data processing, and the system comprises a data dynamic feature quantification module which is used for monitoring a data updating event in real time and quantizing generated features; the influence propagation analysis module is used for calculating an influence propagation coefficient; the dynamic processing range defining module is used for comparing the influence propagation coefficient with an adjustable decision threshold value and outputting a corresponding processing range; the data fusion processing module is used for executing data consistency verification and updating, and measuring generation accuracy, time and calculation consumption; and the strategy optimization and learning module is used for calculating a return value and reversely adjusting the adjustable decision threshold in response to the return value. According to the method, the contradiction between the efficiency and the accuracy of massive dynamic data processing is solved by intelligently evaluating the data updating influence, dynamically scheduling the processing resources and continuously performing self-optimization by applying reinforcement learning, and the response speed, the resource utilization rate and the self-adaptive capability of the system are improved.

The invention discloses a remote sensing image land use overrun identification method and system based on deep learning, and the method comprises the steps: obtaining a land use remote sensing image, and carrying out the preprocessing of the land use remote sensing image, so as to obtain a to-be-identified image pair; performing feature extraction and matching on a picture pair needing to be recognized by using a pre-trained Siamese-Resnet50 model and a gray-level co-occurrence matrix so as to obtain depth similarity and texture similarity; based on the depth similarity and the texture similarity of the picture pair, performing dynamic weight feature fusion calculation to obtain comprehensive similarity; and comparing the comprehensive similarity with a set judgment threshold, judging whether the land use range of the remote sensing image exceeds the limit or not, and outputting a result. According to the method, the depth similarity, the gray level co-occurrence matrix (GLCM) texture features and the dynamic weight adjustment strategy are combined, high-precision detection and anomaly recognition of the land use range are achieved, the problem that ultralimit recognition is difficult is solved, and the recognition efficiency is improved.

The invention discloses an intelligent operation and maintenance management system and method based on digital twinning, and relates to the technical field of intelligent operation and maintenance management. The system comprises a parameter acquisition and anomaly identification module, a digital twin mirror image module, a fault trajectory generation module, a non-dominant fault positioning module and a closed loop verification module. The parameter acquisition and anomaly recognition module acquires data and recognizes anomaly based on a composite judgment threshold value; the fault trajectory generation module drives digital twin mirror image backtracking to generate fault time sequence trajectory data; the non-dominant fault positioning module constructs a reference scene and compares, analyzes and identifies non-dominant associated fault points; and the closed-loop verification module generates a verification instruction, and the verification instruction is verified by the physical device and then fed back to the digital twin mirror image to complete closed loop and confirm the fault root cause. According to the method, fault full-time-sequence tracing and hidden fault accurate identification are realized, and the operation and maintenance reliability and accuracy are improved.

The invention provides a simulation clearing factor traceability method and device for a regional electric power spot market. The method comprises the following steps: obtaining a simulation clearing result for the regional electric power spot market; if the simulation clearing result does not meet the preset constraint condition, triggering a clearing factor traceability process; the clearing factor traceability process comprises the following steps: acquiring original input data of a simulation model oriented to a regional electric power spot market; calculating a sensitivity index of each factor to the simulation clearing result according to the original input data and the simulation clearing result; taking the factors of which the sensitivity indexes of the factors to the clearing results are greater than a third threshold value as key factors after screening; inputting the screened key factors into a traceability model to obtain the contribution degree of each key factor to the simulation clearing result deviation; and if the contribution degree of the key factor to the simulation clearing result deviation is greater than a decision threshold, the factor is the main cause of the simulation clearing result deviation.

The invention relates to the technical field of image recognition, in particular to an abnormal security scene monitoring method and system for infrared thermal imaging, and the method comprises the steps: collecting a picture of a monitoring region through an infrared thermal imager, building a video frame sequence, and constructing a Gaussian mixture model for each pixel point; performing spatial analysis on the video frame sequence, establishing a foreground patch, and determining artificial environment spatial interference of each pixel point in the current frame through the foreground patch; performing time analysis on the video frame sequence in combination with the artificial environment space-time interference to obtain the artificial environment space-time interference of each pixel point in the current frame; evaluating space-time interference of an artificial environment by using a Gaussian mixture model, and judging and marking whether each pixel point in the current frame is in a candidate state or not; and presetting a decision threshold, counting the number of continuous frames with candidate state marks, comparing the number of continuous frames with the decision threshold, and distinguishing normal and abnormal environmental changes. Benign environment changes and real threats are effectively distinguished, and a large number of invalid alarms are prevented from being generated.

The invention relates to the technical field of fire-fighting fire super-early-stage false alarm solution scheme design, in particular to a fire-fighting fire super-early-stage false alarm solution method and system based on multi-modal fusion. The method comprises the following steps: synchronously acquiring multi-dimensional data such as a temperature field, a smoke spectrum, gas type and concentration, environment sound waves and the like through a multi-mode sensor array; after features are extracted, the features are input into a false alarm solution discrimination model obtained through adversarial training normal form learning to be analyzed; the model can deeply identify the essential difference between the fire and the high-simulation interference signal; and finally, according to the confidence output by the model, generating an early warning signal in combination with a dynamically adjusted decision threshold. The system correspondingly comprises a sensing module, a processing module, a judging module and a decision-making module. According to the invention, through confrontation training and multi-mode deep fusion, the problem of false alarm is fundamentally solved, super-early, high-reliability and self-adaptive intelligent fire early warning is realized, and the guarantee capability of fire safety is significantly improved.

The invention relates to the technical field of information security, in particular to an AI video detection method based on multi-feature branch fusion, and the method comprises the following steps: extracting a frame extraction color image from a video, and obtaining a standardized frame sequence after preprocessing; calculating an inter-frame differential volume; obtaining a time sequence spectrum volume according to the standardized frame sequence; performing bilateral filtering decomposition on the standardized frame sequence to obtain an illumination consistency volume; respectively inputting the three types of volume features into a deep convolutional neural network, and after feature extraction and fusion, outputting an AI forgery probability through a classifier; and comparing the AI forgery probability with a decision threshold to generate a video category label, and calculating an index. According to the method, the multi-dimensional features of the time-space domain, the frequency domain and the physical illumination domain are fused, the potential traces of the deeply-forged video are effectively captured, the stable detection performance is kept under various video quality conditions, the accuracy is improved, and reliable technical guarantee is provided for media information security.

The invention relates to a medical equipment fault prediction method and system based on multi-index fusion, and relates to the technical field of medical equipment fault prediction, and the method comprises the steps: collecting and associating multi-source heterogeneous operation data of target medical equipment; reversely analyzing and labeling event influence intervals in the time sequence dynamic monitoring data, and constructing a labeled time sequence data set of equipment state evolution; constructing a multi-task fusion prediction model; acquiring latest time sequence dynamic monitoring data in real time, inputting the latest time sequence dynamic monitoring data into the multi-task fusion prediction model, and synchronously acquiring an output future equipment comprehensive state index attenuation gradient prediction value and a discrete event occurrence probability prediction value; a fusion prediction score is calculated and a preventive maintenance alert is generated when a dynamically adjusted decision threshold is exceeded. The problems of high false alarm rate and insufficient early warning accuracy caused by the fact that traditional medical equipment fault early warning adopts a single judgment basis and related multi-class data are not integrated are solved.

Method and system for processing encrypted data comprising evaluating a client's encrypted data vector by at least one decision tree provided by a server. This method comprises, for evaluating a client's encrypted data vector by at least one decision tree (22) provided by a server (6), in a comparison phase: by a first execution environment, implementing a homomorphic encryption scheme, calculation (52, 54) of an evaluation vector, comprising encrypted components representing a difference between a component of the encrypted data vector and a decision threshold value associated with a corresponding node of said at least one decision tree, and providing the evaluation vector to a second execution environment which is a secure execution environment, executed by said server but controlled by said client.and by the second secure execution environment: - decryption (56) of said evaluation vector by applying a private key of said client, determination (58) of the sign of each component of the decrypted evaluation vector and provision of an encrypted sign vector to the first execution environment. Figure for the abstract: Figure 4,

The invention belongs to the technical field of resource scheduling, and discloses a dynamically constrained multi-resource scheduling method and system based on a decision threshold, and the method comprises the steps: obtaining a real-time resource state and a current environment constraint state, and calculating a value function under the current resource state and the current environment constraint state; constructing a multi-source dynamic resource coupling system model, establishing a cross-state optimization equation set based on the model and the value function, and solving the cross-state optimization equation set to obtain a decision threshold; constructing a two-state environment constraint indicator, judging an executable state of an environment constraint state based on the indicator, calculating a resource proportion according to a real-time resource state, and obtaining a relative state index; and based on the decision threshold and the executable state, constructing a resource scheduling dynamic decision engine, and performing real-time decision on multi-resource scheduling. According to the method, the dynamic decision engine is constructed to process the resource state and the constraint state in real time, a scientific threshold type decision signal is output, and the decision efficiency of resource scheduling with constraints is remarkably improved.

The application relates to the technical field of electric digital data processing, in particular to a collection method based on a dynamic threshold value, equipment and a medium. The method comprises the following steps: obtaining a set of experimental crawler programs whose crawling results on a target data source are successful, which are included in an experimental collection group; obtaining a crawling success rate of each program in the set on a candidate data source in a candidate data source set; determining a crawling characteristic judgment index of the target data source according to the crawling success rate; if the index is greater than or equal to a preset judgment index threshold value, determining a collection power of the target data source according to a comparison result of a collection power index of the target data source and a preset collection power index threshold value, and collecting the target data source based on the collection power; otherwise, determining the collection power of the target data source according to a comparison result of the collection power index of the target data source and an updated collection power index threshold value. The application can dynamically adjust a decision threshold value, and balance resource efficiency and a collection success rate.

The invention belongs to the technical field of semiconductor packaging, and provides an online monitoring method and system for thermal cycle failure of TSV copper salient points, and the method comprises the steps: synchronously collecting resistance data and acoustic emission signals of a test structure containing the TSV copper salient points, and writing the resistance data and acoustic emission signals into a data cache region; calculating a resistance change rate relative to an initial value based on the resistance data in the data cache region, and generating a primary trigger event when the resistance change rate exceeds a real-time judgment threshold value; in response to the primary trigger event, estimating physical coordinates of the abnormal activity; scanning the region of interest taking the physical coordinates as the center to obtain local deformation data, and fusing the physical coordinates, the local deformation data and the resistance change rate to generate a failure diagnosis conclusion; and based on the failure diagnosis conclusion, carrying out backtracking analysis on historical data before the primary trigger event occurs in the data cache region, and adaptively adjusting a real-time judgment threshold, so that real-time monitoring and intelligent diagnosis of the TSV copper bump thermal cycle failure are realized.

The present application belongs to the field of state monitoring of the production and processing process of mechanical equipment, and particularly relates to a health monitoring method and system for a machine tool electric spindle for time-varying working conditions. The Weibull distribution is used to fit the probability distribution of the mean feature associated with the health state output by the discriminator model D. Then, based on the optimal distribution parameter, the critical value for distinguishing normal and abnormal data in the Weibull distribution is determined, and the critical value is used as the decision threshold when the discriminator model D evaluates the output data. The trained feature extractor model CVAE is obtained to realize online monitoring of the processing state. Taking into full consideration the complex working conditions faced by the processing of complex structural parts, the proposed conditional variational encoder can adapt to data changes under different working conditions, and improve the accuracy and robustness of health monitoring through feature decoupling and generative adversarial learning. The discriminator model D trained by alternating cycles of the generator and the discriminator can autonomously determine the health state of the equipment.