346 results about "Fingerprint database" patented technology

The invention particularly relates to a water pollution intelligent traceability system based on a three-dimensional fluorescence spectrum, which relates to the technical field of environmental monitoring, and comprises a water sample collection and three-dimensional fluorescence data acquisition module, a data preprocessing and PARAFAC component decomposition module, a multi-source pollution characteristic fingerprint database module and an intelligent comparison and pollution source analysis module. According to the method, standard acquisition and preprocessing are adopted, and the original data quality is ensured by means of scattering rejection, instrument correction and the like; pure fluorescence components are decomposed through a PARAFAC algorithm, and feature extraction reliability is guaranteed through triple verification. In the comparison link, spectrum similarity, concentration proportion difference and space-time hydrological constraint multi-round screening are adopted, and irrelevant pollution sources are removed; and then the contribution proportion is quantified, and Monte Carlo simulation, water quality and specific pollutant cross validation are carried out, so that the crossing from suspected tracing to quantitative responsibility investigation is realized.

The invention relates to the technical field of power plant data processing, in particular to a virtual power plant integrated management system, which comprises a data acquisition module for acquiring voltage fluctuation characteristics and power climbing rate parameters of energy equipment in real time; the equipment fingerprint database construction module generates an equipment fingerprint code comprising a dynamic response time-lag coefficient and an adjustment margin quantized value; the dynamic clustering module is used for dividing simulation sub-models of regional topology constraints based on the geographic position of the equipment and a power regulation threshold value; the multi-time scale prediction module is used for generating source load prediction data by fusing meteorological parameters through a space-time diagram convolutional network; the digital twin simulation module outputs an energy storage charging and discharging threshold value and a demand response priority strategy; and the cross-domain collaboration module adopts a double-chain block chain architecture to realize security verification and data integrity binding of federated learning feature parameters. According to the invention, through equipment characteristic digital modeling, regional co-simulation and multi-energy flow coupling regulation and control, the resource aggregation precision and response real-time performance in a new energy strong fluctuation scene are improved.

The invention discloses an environment-adaptive transformer oil sample Raman spectrum detection method and related equipment, and relates to the field of optical sensing systems. The method comprises the following steps: collecting oil sample Raman spectrums and environmental parameters in multiple operation scenes, and constructing a multi-scene spectrum characteristic model and a standard fingerprint database; pre-processing and denoising parameters are adaptively set based on the environmental perception vector, and baseline correction and joint denoising are carried out on the original spectrum; scene discrimination is carried out by fusing the characteristics of peak position, peak height, peak width, integral area and the like, a scene-related component standard spectrum dictionary is generated, and the concentration and confidence of each target component are obtained by adopting constrained spectral line unmixing and quantitative calibration; and driving the fingerprint database and the model to update in combination with quality control indexes such as spectral shape relevancy and residual errors and a drift detection result. The system is composed of a Raman spectrum acquisition module, an environment monitoring module and a data processing module, and can improve the robustness and quantitative precision of Raman detection of transformer oil in a complex environment.

The invention belongs to the technical field of fault early warning, and discloses a heater fault early warning method and system based on current analysis. Comprising the steps that transient current signals of all heating wire loops in the copper bush heater are collected in real time, harmonic characteristic parameters are extracted, and a dynamic current fingerprint database and a multi-dimensional harmonic characteristic spectrum are generated respectively; dynamically calculating the contact impedance between each heating wire and the copper sleeve groove according to the dynamic current fingerprint database and the multi-dimensional harmonic characteristic spectrum; the current distribution path of each heating wire in the copper sleeve groove is restored in real time, the abnormal contact form of each heating wire is identified, the falling risk probability and falling risk strength of each heating wire are dynamically predicted by fusing the falling precursor signals of each heating wire detected in real time, and a grading early warning strategy report is generated in real time; according to the invention, fault early warning can be converted into preventive maintenance from post-maintenance, the intelligent level of operation and maintenance of the heater is improved, and the continuity and safety of production are guaranteed.

The invention discloses a data security monitoring and early warning method based on the Internet of Things, and the method comprises the steps: obtaining the real-time operation characteristics of target Internet of Things equipment, and constructing an equipment behavior fingerprint database based on the real-time operation characteristics; constructing a quintuple ontology model based on the equipment behavior fingerprint database, mapping the general tactical framework to an Internet of Things equipment operation scene according to the quintuple ontology model, and generating a cross-domain tactical association rule database; analyzing the multi-source interaction data according to the cross-domain tactical association rule base, and constructing an attack path atlas according to the obtained multi-source interaction features; inputting the attack path atlas into a pre-constructed graph neural network model to obtain a multi-stage attack chain, identifying a persistent threat attack chain in the multi-stage attack chain, and calculating a confidence score of the persistent threat attack chain; and performing anomaly detection on the original network traffic data based on the confidence score, and generating an anonymized early warning analysis report. According to the method provided by the invention, the anomaly detection accuracy of the Internet of Things data is improved.

The invention provides a chemical ship cabin intelligent coating leakage positioning and early warning control method and system, and relates to the technical field of intelligent monitoring, and the method comprises the steps: collecting data through a multi-class sensor array, constructing a parameter distribution map, extracting features through a convolutional neural network, carrying out the time sequence analysis through a long and short term memory network, and carrying out the early warning. The variational auto-encoder constructs a leakage feature fingerprint database, collects data in real time, then carries out feature extraction and fusion processing, matches the data with the fingerprint database, determines a leakage position and a leakage rate, divides a monitoring area, and executes prevention and control. The leakage monitoring precision and the response speed can be improved, and the chemical accident risk is reduced.

The invention discloses a solid waste-based zinc chloride preparation process control method and system, and relates to the technical field of zinc chloride preparation, and the method comprises the following steps: obtaining a unified time base line, establishing a bubble phase reference field, collecting a sound-induced echo sequence, a micro-pressure waveform sequence and a light scattering sequence of a reaction liquid under the bubble phase reference field, and calculating the solid waste-based zinc chloride preparation process. Fusing to generate a bubble density space-time matrix; and performing reversible time-frequency rearrangement based on the bubble density space-time matrix, decomposing to obtain different frequency band distributions, extracting a narrow-band resident bubble group, calculating critical volume distribution and collapse precursor indexes, and constructing a dynamic risk fingerprint database. According to the method, a unified time base line and a bubble phase reference field are constructed, the bubble state is perceived in real time, collapse forebodes are recognized, a dynamic risk fingerprint database is established, directional intervention and reverse energy channel collapse nucleus extinguishing are achieved in combination with an energy aggregation node, finally closed-loop regulation is constructed through calibration write-back, the safety and stability of zinc chloride preparation are improved, and the method is suitable for large-scale popularization and application. And efficient utilization and clean production of solid waste are promoted.

The invention relates to an open source component multi-modal dependency risk tracing method and device, and the method comprises the steps: employing a mode of combining static analysis and dynamic analysis to analyze a component dependency relationship of software, and combining AST analysis and construction script analysis; function-level features are extracted, a binary fingerprint database is constructed, the similarity between different versions is analyzed through LSH, behavior patterns in binary codes are analyzed, and hidden dependencies or malicious code injection is detected; the version updating history of the dependent component is analyzed and monitored by using a time sequence, and the vulnerability security of the component is evaluated in combination with attack graph analysis; high-risk components on the path are calculated, potential supply chain attack points are identified, and risk points are subjected to cross validation; a time sequence diagram database is used for recording the component dependency relationship, and time backtracking query is supported. According to the method, a multi-mode dependency analysis method is adopted, potential dependency risks are rapidly identified, and potential supply chain attack risks are timely warned.

The invention relates to the technical field of distribution network unmanned aerial vehicle autonomous tour-inspection navigation, in particular to a distribution network unmanned aerial vehicle tour-inspection autonomous navigation method based on GPS information and visual information, which comprises the following steps: acquiring a GPS and smoothing projection coordinates, constructing a Thiessen region random index, optimizing a route and acquiring a flight image, evaluating a risk and adjusting exposure parameters, and generating a light environment value. According to the method, an environment model is constructed by fusing GPS information, Gaussian projection is adopted to eliminate earth curvature errors, moving average filtering is adopted to suppress signal noise, Thiessen polygon is utilized to quantify routing inspection point and obstacle distribution, a tornado optimization algorithm is combined to generate an optimal route, the shortest path without repetition and obstacle avoidance are realized, and obstacles are identified based on a YOLOv12 model. A risk avoiding strategy is made according to the risk value, a route is dynamically optimized, a light environment fingerprint database is constructed, illumination change is predicted in combination with LSTM, aperture shutter sensitivity and white balance are adjusted in a self-adaptive mode, image brightness and definition are optimized, and inspection efficiency and data reliability are improved.

The invention relates to the technical field of wireless positioning, and provides a high-speed rail user positioning method and system based on trajectory compensation, and the method comprises the steps: recognizing high-speed rail users, carrying out the data preprocessing, constructing high-speed rail grids, and generating a signal fingerprint database; preliminarily screening out a plurality of candidate grids according to RSRP and TA signal features reported by high-speed rail users in real time; based on the service cell switching sequence, a hidden Markov model or particle filtering is adopted for motion trail modeling, and the advancing direction and speed of a train are recognized; introducing a multi-source information fusion and grid compensation strategy; and selecting a final positioning result from the candidate grids in a weighted voting mode, and outputting grid IDs and latitude and longitude coordinates. Through multi-source data fusion, track compensation and intelligent decision making, the positioning precision and reliability of the high-speed rail user in a complex mobile environment are remarkably improved, and the method has important technical popularization value.

The invention relates to the technical field of data processing, and discloses an advertisement putting state real-time monitoring method and system. The method comprises the following steps: collecting an advertisement putting event stream, and extracting an instantaneous index and a fluctuation rate; counting historical abnormal conduction time delay and intensity, and constructing a conduction matrix; when single-point abnormity is detected, downstream abnormity is predicted according to the conduction matrix, the deviation degree is calculated, and an abnormal conduction chain is searched; conducting chain features are extracted to form abnormal fingerprints, fingerprint database similarity is matched, high similarity is directly confirmed, and low similarity is injected into probe flow verification. By constructing the real-time monitoring method based on the abnormal conduction matrix, the problems that in the prior art, the conduction relation between indexes cannot be quantified, the downstream abnormal moment cannot be predicted, the false report and missing report rate is high, and the abnormal confirmation response is slow are solved, and the accuracy, the real-time performance and the intelligent level of advertisement putting abnormal detection are improved.

The invention provides an antibacterial ceramic glaze sintering process optimization and intelligent temperature control method and system. According to the method, the molecular vibration characteristics of the antibacterial agent at different temperatures are dynamically obtained, and a thermal decomposition dynamic fingerprint database is constructed according to the attenuation law of the molecular vibration characteristics; meanwhile, a three-dimensional temperature field of the glaze layer is reconstructed based on a coupling relation between sound wave propagation parameters and glaze thermal expansion. And carrying out transfer learning on the fingerprint database and historical process data, predicting a glaze thermal stability attenuation parameter, and calculating a temperature gradient and molecular chain fracture compensation coefficient. And fusing the temperature field and the attenuation parameter, and dynamically regulating and controlling the sintering temperature curve and preserving heat by combining the compensation coefficient. The adjusted parameters generate closed-loop feedback by verifying the matching degree of the glaze microstructure and the antibacterial indexes, the compensation coefficient is corrected, and it is ensured that the antibacterial performance of the glaze is stabilized within the process allowance. The temperature control precision and the antibacterial performance stability of antibacterial ceramic glaze sintering are improved.

The invention relates to a circuit board defect identification method and system based on multi-dimensional image data, and belongs to the technical field of data identification processing, and the method comprises the following steps: obtaining synchronous image data of a circuit board to be detected in a plurality of imaging modes; performing space-spectrum joint registration on each modal image to generate a multi-dimensional image cube with a unified coordinate system and pixel alignment; inputting the multi-dimensional image cube into a pre-trained multi-branch heterogeneous fusion neural network; generating a pixel-level defect probability graph by utilizing a defect sensing context decoder, and performing geometric constraint optimization on the probability graph by combining prior information of a circuit board design layout; outputting defect types, positions and confidence coefficients, and establishing an interpretable defect fingerprint database according to the multi-dimensional response characteristics of the defects; the method has the beneficial effects that false defect signals generated by image noise and circuit board surface texture interference can be effectively inhibited, the omission ratio and the false detection ratio are greatly reduced, and pixel-level accurate defect positioning is realized.

The invention discloses a mobile phone lease risk intelligent early warning system based on multi-source data fusion, and relates to the technical field of mobile phone lease. Comprising a data acquisition module, an equipment fingerprint database module, a user credit assessment module, an equipment state monitoring module, a market environment analysis module, a cross-modal association analysis module, a three-dimensional risk assessment module, an early warning decision center and a dynamic confrontation training module. According to the mobile phone lease risk intelligent early warning system based on multi-source data fusion, omnibearing information including the user dimension, the equipment dimension and the market dimension is collected from multi-source data, a three-dimensional evaluation system of user credit, the equipment state and the market environment is established, and especially for the user dimension data, the risk of mobile phone lease is evaluated. According to the method, static data such as historical credit investigation and consumption records are collected, unstructured data such as real-time behavior tracks, social relations and APP use habits of users are also collected, risk factors of multiple dimensions are comprehensively considered, and a comprehensive and accurate risk assessment result is provided.

The invention discloses a similar weather retrieval method based on physical alignment fingerprints, and the method comprises the steps: obtaining a constructed fingerprint database and the time-space sequence data of a target meteorological field corresponding to the to-be-queried weather, and enabling the fingerprint database to be constructed through fingerprints generated by the time-space sequence data of the meteorological field corresponding to a plurality of historical weathers; performing physical consistent double-view contrast learning on the time-space sequence data of the target meteorological field to generate a first physical enhancement double-view result corresponding to a scalar field and / or a second physical enhancement double-view result corresponding to a vector field; inputting the first physical enhancement double-view result and / or the second physical enhancement double-view result into a trained fingerprint generation model to obtain a query fingerprint; retrieving a plurality of fingerprints similar to the query fingerprint in a fingerprint database to obtain a fingerprint retrieval result; and finding out a plurality of corresponding target historical weathers according to the fingerprint retrieval result, and taking the plurality of target historical weathers as similar weather retrieval results. The accuracy of similar weather retrieval can be improved.

The invention belongs to the technical field of marine environment monitoring and protection, and discloses an unmanned aerial vehicle multi-mode marine environment real-time monitoring system based on deep learning, and the system comprises the steps: extracting an instantaneous velocity vector based on an ocean current trajectory; a sea surface flow velocity field is generated, a calibration pile fingerprint database is constructed, and three-dimensional grid parameters are set; secondly, correcting the thickness of a vertical layer of the three-dimensional grid, constructing a tide compensation floating coordinate system, and generating a multi-modal sensor collaborative acquisition instruction set; secondly, performing hard synchronization on multi-modal data, generating a fusion data cube, predicting pollutant concentration increase through LSTM (Long Short Term Memory), and generating a high-risk area list; thirdly, obtaining the battery health state of the unmanned aerial vehicle, limiting the flight attitude, generating an optimized path, and predicting a residual endurance curve; and finally, dynamically allocating unmanned aerial vehicle-subarea mapping through an auction algorithm, verifying bidding by using a block chain, and finely adjusting LSTM parameters through an energy consumption data reverse calibration model and anomaly detection to form closed-loop optimization.

The invention discloses an intelligent diagnosis method for analyzing line hidden dangers based on dynamic electrical fingerprint characteristics, and belongs to the technical field of power line state monitoring and fault prediction. According to the method, a dynamic electrical fingerprint is constructed through high-frequency acquisition of line voltage and current instantaneous value signals and extraction of multi-dimensional features such as a time domain, a frequency domain and a time-frequency domain; establishing an electrical fingerprint database and a health model of different load working conditions in a line health state; during on-line monitoring, through three-level analysis of deviation comparison, state classification and trend prediction, graded early warning of line hidden dangers is realized, and abnormal feature items are output for auxiliary diagnosis. According to the invention, subtle changes of electrical parameters can be captured, the problems of low sensitivity, weak anti-interference capability and incapability of early warning in the prior art are solved, early recognition and advanced prediction of latent hidden dangers are realized, and the safety and reliability of a power system are significantly improved.

The invention discloses an electric power protection measurement and control terminal information security protection method, system and device and a medium, and the method comprises the steps: building an environment fingerprint database through collecting the physical quantity of a power grid, carrying out the threat level evaluation, and adjusting a security strategy; based on the environment fingerprint database and the threat level evaluation result, classifying the transmission data, deploying quantum key distribution nodes in the transformer substation, and providing differentiated secure transmission for different types of transmission data; and in combination with the environment fingerprint database and the differentiated secure transmission data, executing cognitive security analysis, establishing an anomaly detection model, and obtaining threat traceability visual positioning. According to the method, the dynamic environment fingerprint database is constructed by collecting multi-dimensional physical quantities and is bound with the digital certificate to form a dual authentication mechanism, so that the defect that a traditional scheme depends on static cryptography is overcome, real-time perception and adaptive response to a complex and changeable electromagnetic environment are realized, and the security of the system is improved. And the environmental adaptability and the safety protection capability of the system are obviously improved.

The invention provides an indoor fingerprint positioning method based on area fitting, which relates to the field of fingerprint positioning, and comprises the following steps: dividing a plurality of triangular areas, and carrying out signal intensity fitting on each triangular area by adopting a signal area fitting method to obtain a plurality of signal intensities in one-to-one correspondence with virtual reference points; calculating to obtain an obstacle area through an obstacle identification algorithm, calculating to obtain an AP fingerprint map with a passable area according to the obstacle area, and establishing a retrieval fingerprint database corresponding to the AP fingerprint map; selecting a passable area with the minimum distance in the retrieval fingerprint database, and matching a reference point in the AP fingerprint map to realize positioning; by adopting the method, the signal intensity fitting of the whole indoor area can be carried out only by measuring the sparse reference points. A double-layer fingerprint database is constructed, positioning errors can be remarkably reduced, the number of fingerprint database data is greatly reduced, and therefore the online matching duration is shortened.

The invention discloses a chip for genome breeding and variety identification of tilapia mossambica. The invention provides a group of SNP (Single Nucleotide Polymorphism) marker combination for tilapia mossambica, which comprises 50000 SNP markers which are respectively SNP1-SNP50000 markers. According to the invention, the SNP marker combination related to economic characters of tilapia mossambica is integrated, representative sites with uniform coverage are selected, a biological probe for site typing is developed, and the site coverage, typing accuracy and GS accuracy of the SNP marker combination are basically consistent with those of re-sequencing; the method can be applied to the aspects of tilapia germplasm resource identification, genetic relationship identification, SNP typing, variety identification, molecular breeding, DNA fingerprint database construction, variety purity detection, germplasm resource genetic analysis, whole genome selective breeding, functional gene positioning, genetic map construction, genetic evolution analysis, whole genome association analysis and the like.

The invention provides a leakage source positioning method and device based on gas concentration, and relates to the technical field of gas leakage detection.The method comprises the steps that an observable leakage path is finely determined by fusing a battery array topology and an air duct topology, characteristic gas sensors are arranged, a self-adaptive background concentration reference baseline is constructed under the normal working condition, and a gas leakage source is obtained; a concentration response fingerprint database is generated by using a concentration diffusion model under topological constraints, abnormal joint features are extracted by combining real-time multi-node multi-species concentration migration, the position of a leakage source is accurately inverted through fingerprint matching and iterative optimization, confidence coefficient verification is performed according to the running state of a battery cluster, and the reliability of the leakage source is improved. And finally, outputting the position of the leaked battery cluster, the leakage confidence coefficient and the multi-species abnormal intensity index, and realizing early warning and fine positioning of the thermal runaway threatened leakage of the battery. According to the invention, the accuracy of leakage source inversion can be improved.

The invention provides a method for detecting an abnormal state of an optical signal in an OPGW (Optical Fiber Composite Overhead Ground Wire) optical cable, which relates to the technical field of power transmission line anomaly detection and comprises the following steps: S1, hardware deployment; s2, multi-dimensional data acquisition is carried out; s3, signal preprocessing; s4, abnormal feature extraction and threshold dynamic optimization; s5, fault type identification; s6, fault positioning; and S7, performing active disposal and state evaluation. According to the method for detecting the abnormal state of the optical signal in the OPGW optical cable, the optical signal, the deformation signal, the environmental parameter and the operation parameter are synchronously collected to realize comprehensive coverage of fault influence factors, a CNN module captures local features such as polarization state sudden change amplitude and duration time, an LSTM module analyzes time sequence features such as stress concentration trend and icing periodical fluctuation, and the optical signal abnormal state detection method is used for detecting the abnormal state of the optical signal in the OPGW optical cable. A 128-dimensional multi-dimensional feature vector is formed through splicing, five types of faults can be accurately recognized in combination with a fingerprint database, meanwhile, a threshold value is dynamically corrected based on real-time parameters such as temperature and wind speed, the adaptability defect of a fixed threshold value is avoided, and the false alarm rate and the missing report rate are greatly reduced.

The invention relates to the technical field of tool machining data acquisition, and provides a broaching tool machining data acquisition method and system, and the method comprises the steps: obtaining original information flows from various mechanical sensors, carrying out the time alignment of the original information flows, and obtaining the aligned original information flows; identifying a transient event based on the aligned original information flow, and extracting multi-dimensional features of the transient event; constructing a multi-channel space-time correlation fingerprint database; constructing a real-time multi-channel event sequence on each channel based on the transient event and the multi-dimensional features, and matching the real-time multi-channel event sequence with a multi-channel space-time association fingerprint database to obtain a fingerprint matching result; and based on the real machining event fingerprints and the electromagnetic noise fingerprints, a real machining event and electromagnetic noise are distinguished in combination with a fingerprint matching result, so that the broaching tool state and machining abnormality are recognized. The method has the effect of improving the accuracy of broaching tool state recognition and machining abnormality diagnosis.

The invention discloses a dynamic self-adaptive network security protection method and device, equipment and a storage medium, relates to the technical field of network security, and aims to solve the problem that traditional network security protection is poor in initiative and adaptability. The method comprises the following steps: extracting microscopic behavior characteristics of real-time network traffic, constructing an attacker behavior fingerprint database in combination with an online learning model, and outputting an attack type classification result; in response to an attack type classification result, dynamically rotating the encryption key and associated elliptic curve mathematical parameters, and generating an encryption strategy; according to the network load state and the encryption strategy, dynamically switching communication ports and outputting a port state log; under the condition that the directional scanning attack is recognized, active defense operation is executed, and the active defense operation comprises the steps of closing unnecessary ports, injecting noise data, constructing a bait network and outputting attack traceability data.

The invention discloses a fault monitoring and positioning method for a high-voltage drop-out fuse, and relates to the technical field of power equipment fault monitoring, and the method comprises the steps: obtaining original monitoring sequences corresponding to current and voltage sensors disposed at upper and lower ports of a target fuse; activating a working mode recognizer to execute working mode recognition of the target fuse, establishing a global mode label, executing adaptive matching of a mode fingerprint database, and establishing a standard comparison fingerprint with a trust identifier; establishing residual spectrum characteristics; and establishing a fault discrimination vector, carrying out space fault positioning by using the fault discrimination vector, and generating a fault positioning result. According to the invention, the technical problems of insufficient fault monitoring and positioning accuracy, lack of visual presentation capability and low monitoring and positioning efficiency of the high-voltage drop-out fuse in the prior art are solved, and accurate positioning and visual presentation of the fault of the high-voltage drop-out fuse are realized. And the accuracy and efficiency of fault monitoring and positioning are improved.

The invention discloses an Internet of Things networking scheduling method for railway tunnel disaster prevention illumination and evacuation indication, and relates to the technical field of railway tunnel disaster prevention. Comprising the following steps: S1, tunnel end monitoring equipment actively initiates environmental channel detection through a power line carrier communication network, scans impedance characteristics, noise levels and attenuation characteristics of different line sections in a tunnel, establishes a dynamic channel fingerprint database, and records an optimal communication frequency point and a channel quality threshold; and S2, performing real-time linkage between the local center monitoring main station and a fire alarm system, and after receiving a fire alarm signal, immediately generating a dynamic evacuation path through a disaster evolution prediction model according to a fire alarm position, a smoke diffusion state and a real-time channel state. The power line carrier communication module is utilized to actively perform channel detection and electrical parameter acquisition, a state channel fingerprint database is established, and fault diagnosis and state grading are performed based on the state channel fingerprint database, so that the overall reliability and maintainability of the scheme are improved, and the availability of equipment in a disaster is ensured.

The invention belongs to the technical field of visible light positioning, and relates to a visible light sparse fingerprint positioning method and system based on MLS-WKNN and a medium, and the method comprises the steps: collecting the received signal strength of a sampling point; fitting a received signal strength prediction value of each light source at the interpolation point through a moving least square method; constructing a dense fingerprint database through the received signal strength of the sampling points and the received signal strength predicted values of the interpolation points; collecting the real-time receiving signal intensity of the target point; and based on the real-time received signal strength and the dense fingerprint database, obtaining an accurate position estimation value of the target point through a weighted K-nearest neighbor algorithm. The sparse fingerprint database is subjected to MLS interpolation, the precision of sparse visible light fingerprint positioning is improved, and compared with an existing interpolation mode, the positioning precision is higher.

The invention discloses a modified plastic processing temperature adaptive control method, and relates to the technical field of high polymer material processing control, and the method comprises the following steps: collecting the same frequency mapping of power grid disturbance and melt temperature response, capturing the transient power fluctuation of a heating unit with millisecond-level time precision by adopting a phase comb sampling technology, and constructing a power pulse fingerprint database; a parameter space for discriminating a pseudo-steady state is established based on a power pulse fingerprint database, a short-time power pulse signal and a stable signal are classified by using a phase lag and entropy increase dual-threshold method, and a pseudo-steady state confidence index is generated. According to the method, the power pulsation fingerprint database and the electrothermal coupling model are constructed, pseudo-steady-state temperature control abnormity is accurately recognized, reverse energy regulation and control are achieved in combination with a sensitivity track and a thermal write-back mechanism, the melt temperature stability is improved, the product warping rate is effectively reduced, and the size consistency and the mechanical property are remarkably optimized.

The invention discloses a wind power cabin fire early warning device and a wind power cabin fire early warning method based on multispectral fusion, and aims at the defects of high false alarm rate, insufficient motion artifact compensation and transient fire capture lag of single-spectrum detection in the prior art to construct a multispectral collaborative analysis architecture. A thermal deformation dynamic compensation model is constructed in combination with a main shaft rotating speed signal, and sub-pixel-level motion artifact elimination is achieved; an improved three-dimensional convolutional neural network is adopted to extract smoke diffusion trajectory, temperature conduction trend and arc pulse features, and multi-source feature adaptive fusion is realized through a cross-modal attention mechanism and a graph neural network; and establishing an oil stain reflection spectrum fingerprint database for false alarm filtering, and finally triggering third-level early warning according to an environment self-adaptive threshold value. According to the method, the electrical short circuit detection time can be greatly shortened, the false alarm rate is effectively reduced, the smoldering fire is warned in advance, and the industrial problem of accurate recognition of early fire in a complex cabin environment is solved.

The invention relates to the technical field of photovoltaic equipment diagnosis, in particular to a distributed photovoltaic diagnosis method and system based on multi-modal time sequence data. The invention discloses a distributed photovoltaic diagnosis system based on multi-modal time sequence data. The distributed photovoltaic diagnosis system comprises a multi-modal time sequence data acquisition module, an electrical feature vector extraction module, a single fault source judgment module and a fault source combination judgment module. According to the method, the electrical feature vector and the electrical feature fingerprint database are matched, the similarity is calculated, and the threshold value is set, so that the fault source can be directly judged under the condition of a single fault source, linear splitting is performed through a group optimization algorithm under the condition of multiple fault sources, and the fault source can be determined in combination with the contribution component and the occurrence frequency of the fault source. The occurrence probability of the fault sources is calculated and analyzed with a set fault source combination probability threshold value, it is ensured that fault source combination information is output only when contribution of the multiple fault sources reaches a certain threshold value, and then the diagnosis precision of the fault sources is optimized.