Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

26results about How to "Reliable diagnosis" patented technology

Aviation converter fault detection method based on information fusion algorithm

The invention discloses an aviation converter fault detection method based on an information fusion algorithm, and the method comprises the steps: collecting the operation data of an aviation converter, and constructing a data set; performing time information extraction and space information extraction on the data in the data set, and performing feature fusion on time features and space features based on a variational auto-encoder to obtain spatio-temporal data; constructing a Bayesian deep learning model, and training and optimizing the Bayesian deep learning model; inputting the spatio-temporal data into the trained and optimized Bayesian deep learning model for processing, outputting a numerical value representing a fault occurrence probability, and taking a variance based on the probability numerical value as uncertainty estimation; presetting a probability threshold, and when the output probability is greater than the threshold, determining that the converter has a fault; otherwise, judging that the operation state is normal; a more accurate and reliable diagnosis result is provided for fault detection, and the method has high adaptability and robustness in practical application.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Sugar net recognition system based on block chain and federal learning

The invention discloses a sugar net recognition system based on a block chain and federal learning, and the system comprises a data collection module which is used for collecting fundus image data and related medical data; the federal learning module is connected with the data acquisition module, the federal learning module comprises a plurality of participant nodes, and each participant node performs model training based on local data; the block chain module is connected with the federated learning module and used for storing model parameters, training data abstracts and data access record key information in the federated learning process; the sugar network identification module is used for receiving the global sugar network identification model trained by the federal learning module; and the result output and feedback module is connected with the sugar net identification module. According to the method, the data collaborative training model is integrated through federal learning, so that the sugar net recognition accuracy is improved, misdiagnosis and missed diagnosis are reduced, the block chain ensures the data to be safe and credible, the innovative formula assists optimization, the system application is wide, clinical and remote medical treatment is facilitated, and the sugar net diagnosis service quality is improved.
Owner:BEIHANG UNIV

Intelligent plunger pump fault diagnosis system and diagnosis method

The invention discloses an intelligent plunger pump fault diagnosis system and a diagnosis method, which realize accurate monitoring of the tilt angle of a swash plate, can adjust and accurately control the output flow of a pump in real time in combination with a built-in control operation unit, and meanwhile, outputs pressure data in cooperation with a proportional pressure reducing valve, and compares the pressure data with a threshold value in a first fault diagnosis module, so that the fault diagnosis accuracy is improved. Judging whether a proportional pressure reducing valve and a variable adjusting mechanism of the pump are abnormal or not; and in cooperation with shell pressure data, whether the leakage amount of the pump is abnormal or not is judged by comparing the pressure data with a threshold value in the second fault diagnosis module, and faults caused by flow fluctuation or abnormality are effectively prevented. And whether the volumetric efficiency of the pump is too low or not is judged by comparing with a threshold value in the third fault diagnosis module, so that the universality and accuracy of a volumetric efficiency diagnosis algorithm are remarkably improved.
Owner:JIANGSU ADVANCED CONSTR MASCH INNOVATION CENT LTD

Intelligent electric control valve fault diagnosis method

The invention discloses an intelligent electric control valve fault diagnosis method, which comprises the steps of performing data expansion based on cloud oversampling, capturing uncertainty in fault data, and constructing a new sample reflecting inherent randomness of original data in a cloud feature space; optimizing the new sample, and controlling inherent random fluctuation caused by cloud oversampling; a cloud membership function is adopted as a fitness calculation function; constructing a random configuration network fault diagnosis model with a parallel structure, wherein the models are respectively used for predicting the number and category of faults; in combination with a cloud model similarity calculation method, quantifying potential correlation between a single fault and a concurrent fault; and integrating output results to obtain a final fault diagnosis result. According to the method, random fluctuation caused by inherent uncertainty of the cloud model is effectively controlled, so that the adaptivity to different data sets is enhanced; a parallel network model is constructed to predict the number and types of faults respectively, and the problem that single faults and concurrent faults are difficult to distinguish is solved.
Owner:TIANJIN KAIJI VALVE CO LTD +1

Three-probe diagnosis system suitable for SCU-PSI plasma linear device and denaturation diagnosis method

The invention discloses a three-probe diagnosis system suitable for an SCU-PSI plasma linear device and a denaturation diagnosis method, relates to the technical field of plasmas, is developed based on a three-probe theory, and comprises a three-probe, a circuit, a data acquisition system and a transmission device, the three pins are coupled with the SCU-PSI plasma linear device through a lead and a flange; the circuit is connected with the three pins and is used for shielding electromagnetic interference from different electrical components; the data acquisition system is used for acquiring plasma parameters; and the transmission device is used for driving the probe to move in the radial direction in the cavity. The three-probe diagnosis system suitable for the SCU-PSI plasma linear device is developed and used for researching the shielding effect of the lithium vapor, the diagnosis result is reliable, and the physical mechanism of interaction between the lithium vapor and the plasma characteristics can be disclosed.
Owner:EAST CHINA UNIV OF TECH

Motor control anti-demagnetization protection system and method

The invention discloses an anti-demagnetization protection system and method for motor control. The method comprises the following steps: acquiring counter electromotive force of a motor winding and real-time counter electromotive force of each phase of winding of a motor under a fault-free condition; respectively subtracting the counter electromotive force of the motor winding under the fault-free condition from the real-time counter electromotive force of each phase winding of the motor to obtain the maximum difference value of the real-time counter electromotive force of the phase windings of the motor; and comparing the maximum difference value of the real-time counter electromotive force of the motor phase winding with a demagnetization fault threshold value to judge whether the motor is in a demagnetization fault, if the motor is not in the demagnetization fault state, the motor operates normally, and if the motor is in the demagnetization fault state, demagnetization protection is carried out. According to the invention, real-time on-line and high-sensitivity effective evaluation and identification can be carried out on the demagnetization fault degree and the fault mode of the motor.
Owner:ZHIXIN TECH CO LTD

Synchronous phase modifier fault diagnosis method based on knowledge graph and large language model

The invention discloses a synchronous phase modifier fault diagnosis method based on a knowledge graph and a large language model, and the method comprises the steps: obtaining the operation data of a synchronous phase modifier, and carrying out the preprocessing of the operation data, so as to form a unified corpus and a standardized data set; based on the unified corpus, using a BERT model to encode the corpus to obtain context perception vector representation, and based on the context perception vector representation, performing sequence labeling and relation extraction, and outputting structured knowledge data; based on the structured knowledge data, constructing a synchronous phase modifier fault diagnosis knowledge graph; based on a pre-trained large language model, performing model training and optimization by using the standardized data set, understanding and analyzing a fault phenomenon described by a natural language, and outputting a semantic analysis result; and in combination with the output of the knowledge graph and the semantic analysis result, performing hybrid reasoning to obtain a fault diagnosis result. The method has the advantages of high diagnosis precision, high diagnosis efficiency and the like.
Owner:DC TECHNICAL CENTER OF STATE GRID CORP OF CHINA +6

Direct-current converter fault diagnosis method, device, equipment, medium and program product

The invention discloses a DC converter fault diagnosis method and device, equipment, a medium and a program product, and the method comprises the steps: collecting historical operation data and fault sample data of a DC converter, carrying out the preprocessing of the historical operation data and the fault sample data, obtaining a data set, building a kernel function based on the data set, and building an original model, and training and optimizing the original model based on a kernel function to obtain a fault diagnosis model, the original model comprising a support vector machine, collecting real-time operation data of the DC converter, preprocessing the real-time operation data, and inputting the preprocessed real-time operation data to the fault diagnosis model for fault diagnosis. The fault probability and the fault type of the direct-current converter are obtained, so that the running state of the direct-current converter is monitored, the timeliness of fault diagnosis is ensured, the accuracy of fault diagnosis is effectively improved, a reliable diagnosis result is provided for fault processing, and the response speed of fault processing is improved.
Owner:HUNAN UNIV

Switch cabinet discharge detection method and system based on spectral characteristics, and computer equipment

The invention belongs to the technical field of power equipment fault diagnosis, and particularly relates to a switch cabinet discharge detection method based on spectral characteristics, which comprises the following steps: collecting partial discharge multispectral signals collected by a partial discharge multispectral sensor at different positions in a switch cabinet; performing feature extraction on the partial discharge multispectral signal to obtain a multispectral partial discharge feature quantity; the multispectral partial discharge characteristic quantity comprises a discharge pulse number, an average pulse amplitude, a maximum discharge pulse amplitude and an average discharge pulse amplitude after windowing; inputting the multispectral partial discharge characteristic quantity into a partial discharge diagnosis model, and carrying out partial discharge type identification and partial discharge severity division; the partial discharge diagnosis model adopts a k-means clustering algorithm used for dividing the severity of partial discharge and a deep neural network algorithm used for identifying the type of partial discharge. Multi-spectral information is fully mined, and reliable diagnosis of partial discharge can be realized without depending on phases.
Owner:GUANGZHOU POWER SUPPLY BUREAU GUANGDONG POWER GRID CO LTD

Newborn brain imaging system and method based on photoacoustic technology

The invention discloses a neonatal brain imaging system and method based on a photoacoustic technology, and belongs to the field of medical instruments. The system comprises a control module, an excitation source module, a newborn brain photoacoustic data acquisition module, a data output module and a quantitative calculation module. Wherein the control module comprises two computers and a laser control instrument; the excitation source module comprises a high-frequency laser and a water cooling system thereof; the neonatal brain photoacoustic data acquisition module comprises a focusing lens, an optical fiber, a wearable flexible ultrasonic transducer and a multi-channel acquisition card; the data output module comprises a computer matched with real-time imaging MarsonicsDAQ software and an imaging algorithm embedded in the software; the quantitative calculation module comprises a multi-spectral linear unmixing algorithm and imaging software. The invention provides high-resolution and high-contrast real-time imaging of the brain tissue structure and cerebral hemodynamic parameters of the newborn, and can be used as a supplementary mode of the existing brain imaging technology for auxiliary diagnosis.
Owner:BETA MEDICAL TECHNOLOGY (CHENGDU) CO LTD

A crop growth drought stress detection system and method

The invention discloses a crop growth drought stress detection system and method, belonging to the technical field of facility agriculture biological information detection. The system comprises an acquisition platform, a multi-spectral polarization imaging system, a power supply system, a control module, a whiteboard automatic correction device, a USB signal receiver, a signal reading circuit, a storage module and a processing module. By developing a portable multi-spectral polarization imaging system, optimizing data processing and fusion algorithms, the state of plant drought stress can be obtained in time, and accurate data support can be provided for agricultural production.
Owner:INTELLIGENT EQUIPMENT RESEARCH CENTER BEIJING ACADEMY OF AGRICULTURE AND FORESTRY SCIENCES

Medical auxiliary diagnosis method, device and equipment and storage medium

The invention relates to the technical field of artificial intelligence, in particular to a medical auxiliary diagnosis method and device, equipment and a storage medium, and the method comprises the steps: obtaining to-be-diagnosed medical data, generating a preliminary diagnosis result, matching a medical knowledge base, sorting and scoring diagnosis options, selecting an optimal diagnosis result, and feeding back the diagnosis result and a treatment suggestion. According to the medical auxiliary diagnosis system, by combining the medical data of the patient and the advanced artificial intelligence technology, the accuracy and efficiency of diagnosis can be improved, the burden of a doctor is relieved, the medical service quality is improved, the intelligent level and practicability of the medical auxiliary diagnosis system are improved, and the medical service quality is improved through a scientific method and technical means; the pressure of medical resources is relieved, and better-quality and more efficient medical services are provided for patients.
Owner:强小龙

LC-MS (liquid chromatography-mass spectrometry) detection method of alpha-hydroxybutyric acid

The invention discloses an LC-MS (liquid chromatography-mass spectrometry) detection method of alpha-hydroxybutyric acid, and belongs to the technical field of quantitative detection of alpha-hydroxybutyric acid. The detection method comprises the following steps: step 1, preparing a standard working solution; 2, preparing an internal standard working solution; step 3, pre-treating a sample; step 4, putting the sample treated in the step 3 into EP tubes, adding an internal standard working solution into each EP tube, slightly and uniformly mixing, continuously carrying out vortex oscillation on the mixture at the room temperature at the medium speed, then carrying out centrifugal treatment, and transferring supernatant liquid in a centrifugal tube into a special bottle for liquid chromatography; and 5, placing the special bottle for liquid chromatography on a sample introduction disc of a high performance liquid chromatography-tandem triple quadrupole mass spectrometer, carrying out data acquisition and quantitative analysis, recording a chromatogram and a mass spectrum, and carrying out peak area calculation by adopting an internal standard method to obtain a detection result. The 2-HB can be accurately detected and quantified, and the metabolic state of a patient can be more accurately evaluated.
Owner:BEIJING TIANTAN HOSPITAL AFFILIATED TO CAPITAL MEDICAL UNIV

Method for detecting faults in semiconductor switches

ActiveCN113597741Breliable diagnosisElectrical testingElectronic switching
The invention relates to a method for checking for faults in semiconductor switches, wherein the semiconductor switches are actuated with a PWM signal having a variable pulse duty factor. In order to reliably and cost-effectively detect faults in the semiconductor switches, it is provided that when the semiconductor switches are operated with a pulse duty factor of 100% or 0%, a current measurement of the entire system is evaluated, and when the semiconductor switches are operated with a pulse duty factor between 0% and 100%, a voltage pulse generated at the semiconductor switches is evaluated.
Owner:WEBASTO AG

A power equipment inspection method based on deep learning dual-light feature fusion

This invention discloses a power equipment inspection method based on deep learning dual-light feature fusion, comprising: simultaneously acquiring visible light images and infrared thermal imaging images of the power equipment using a binocular acquisition module mounted on an inspection robot; extracting significant straight line features from the two images using a gradient-based edge detection operator, and solving the homography matrix using line segment descriptors and geometric constraints to achieve online spatiotemporal registration without a calibration board; constructing a deep learning-based dual-stream feature extraction network to map the registered infrared image as a spatial attention mask, and performing weighted fusion of the visible light feature map using Hadamard product; finally, outputting equipment category, location, and temperature information based on the fused feature map, and determining faults using a dual threshold of confidence and temperature. This invention effectively solves the problems of texture loss in traditional infrared detection and the failure of visible light nighttime detection, achieving accurate location and diagnosis of power equipment faults.
Owner:NINGBO XINGBOYUAN INTELLIGENT TECHNOLOGY CO LTD

Analysis method of traditional Chinese medicine encephalopathy risk assessment data containing credibility factors

The invention discloses a method for analyzing traditional Chinese medicine encephalopathy risk assessment data containing credibility factors, and relates to the technical field of traditional Chinese medicine encephalopathy risk assessment, which comprises the following steps: S1, establishing a doctor experience assessment system: assessing experience levels for doctors according to quantitative standards by formulating the quantitative standards of doctor experience, and establishing the doctor experience assessment system; and obtaining a doctor weight experience level, and taking the doctor weight experience level as a credibility factor to be included in risk assessment. According to the traditional Chinese medicine encephalopathy risk assessment data analysis method containing the credibility factors, the credibility factors such as various symptom expressions, examination data, medical history and treatment compliance of the patient are comprehensively considered, the risk condition of the patient is comprehensively assessed, the one-sidedness of single-factor assessment is avoided, and the diagnosis result is more accurate and reliable; a multi-doctor consultation mechanism is implemented, doctors with different experience levels analyze and evaluate the condition of a patient from multiple angles, and a final result is determined by using a majority voting principle.
Owner:CHANGCHUN UNIV OF CHINESE MEDICINE

MP primer group, kit and application of MP primer group in mycoplasma pneumoniae nucleic acid detection

The invention provides an MP primer group, a kit and application of the MP primer group in mycoplasma pneumoniae nucleic acid detection, and relates to the technical field of mycoplasma pneumoniae detection. The MP primer group comprises at least one of a first primer group and a second primer group; the first primer group consists of a pair of outer primers F3-1 and B3-1, a pair of inner primers FIP-1 and BIP-1, and a pair of loop primers LF-1 and LB-1; and the second primer group consists of a pair of outer primers F3-2 and B3-2, a pair of inner primers FIP-2 and BIP-2, and a pair of loop primers LF-2 and LB-2. According to the MP primer group provided by the invention, the specificity and the flexibility of detection are improved, the reliability is ensured, and the sensitivity is improved by increasing the amplification speed. The constant temperature characteristic of the LAMP technology reduces cross contamination, so that the detection is rapid and safe, and the LAMP technology is suitable for on-site rapid diagnosis.
Owner:BEIJING GENSHU TECH CO LTD +1

ISFET-based single-chip integrated miniature wireless pH detection device and system

This application discloses a single-chip integrated miniature wireless pH detection device and system based on ISFET, relating to the field of in vivo pH detection technology. The device includes: a housing; a wireless sensing chip integrating a pH sensing module, the sensing interface of which is exposed to the measured environment through the housing; a signal processing module connected to the pH sensing module for processing the pH sensing signal detected by the pH sensing module; and a wireless communication and power supply module connected to the signal processing module for transmitting the pH sensing signal processed by the signal processing module and supplying power to the modules on the wireless sensing chip. This application integrates the pH detection module, signal processing module, and wireless communication module into a single on-chip system, utilizing CMOS technology, wireless power transfer technology, and backscattered reverse communication technology, effectively reducing the size of the pH detection device and improving the accuracy of pH detection.
Owner:BEIHANG UNIV

A shafting fault diagnosis method and system based on ship motor howling identification

The application discloses a kind of based on ship motor howling identification shafting fault diagnosis method, the method includes the following steps: collecting the sound signal of ship motor, and multi-source monitoring data;The sound signal is preprocessed to extract its time-frequency feature;The time-frequency feature is input to pre-trained identification model, and the discriminant result of motor howling is obtained;The discriminant result is processed with probability smoothing and threshold judgment, when meeting set condition, trigger shafting diagnosis;After triggering shafting diagnosis, the multi-source monitoring data is fused with the time-frequency feature, and based on fusion result, shafting fault is discriminated and positioned to obtain diagnostic result;The diagnostic result is displayed in real time on intelligent monitoring platform, and triggers hierarchical alarm and remote upload.The method and system provided by the application have the advantages of strong real-time, high anti-interference capability, reliable diagnostic result, low operation and maintenance cost, etc.
Owner:NANJING SMART WATER TRANSPORTATION TECH CO LTD

A device and method for stabilizing the energy of a pulsed ion beam from a high frequency ECR ion source

PendingCN122742244Asafe and stable operationmeet energy needs
This invention relates to an apparatus and method for stabilizing the pulsed ion beam energy of a high-frequency ECR ion source. The ECR ion source operates in pulsed mode. The apparatus includes a microwave radiation measurement system, an oscilloscope, a bremsstrahlung detection system, an electrostatic accelerator tube, a time-of-flight detector, and an industrial control computer. The microwave radiation measurement system receives and processes microwave signals emitted from the plasma arc cavity. The oscilloscope observes the converted voltage signal. The bremsstrahlung detection system detects and processes bremsstrahlung signals emitted when high-energy electrons are lost on the arc cavity wall of the plasma arc cavity. The electrostatic accelerator tube modulates the energy of the extracted ion beam from the plasma arc cavity when instability occurs. The time-of-flight detector measures the energy change of the extracted ion beam after energy modulation. The industrial control computer determines whether instability has occurred and reads back the measurement results from the time-of-flight detector. This invention can be widely used in the field of ECR ​​ion sources.
Owner:INST OF MODERN PHYSICS CHINESE ACADEMY OF SCI

Water area propulsion system, fault diagnosis method and equipment thereof and storage medium

A water area propulsion system, a fault diagnosis method and device thereof, and a storage medium, the water area propulsion system comprises a plurality of propulsion devices, each propulsion device is internally provided with a controller, or each propulsion device is externally connected with a controller, the method is applied to a target controller, and the target controller is connected with the controller. The target controller is one of the plurality of controllers, and the method comprises: determining a fault device type and a first fault level corresponding to a fault in the water area propulsion system (S101); determining a second fault level of the fault acting on the water area propulsion system on the basis of a preset mapping relationship, the fault device type and the first fault level, the mapping relationship comprising a correspondence relationship between the first fault level and the second fault level under each fault device type (S102); and generating a fault diagnosis result of the water area propulsion system according to the determined second fault level (S103).
Owner:DONGGUAN EPROPULSION INTELLIGENCE TECH LTD

Battery abnormality diagnosis apparatus and method

ActiveCN117355760Breliable diagnosisMinimize noise effects
Disclosed is an apparatus and method of diagnosing a battery abnormality. The apparatus according to the present invention includes a control device for diagnosing a lithium precipitation abnormality of a battery. The control device can be configured to: calculate a charge capacity and a discharge capacity of a kth charge / discharge cycle; determine a capacity difference corresponding to a difference between the charge capacity and the discharge capacity; determine a kth capacity difference change amount by subtracting the capacity difference of the kth charge / discharge cycle from a capacity difference of a (k-1)th charge / discharge cycle; update an accumulated capacity difference change amount by adding the kth capacity difference change amount to the accumulated capacity difference change amount; and diagnose that a lithium precipitation abnormality occurs if the updated accumulated capacity difference change amount is greater than or equal to a threshold value.
Owner:LG ENERGY SOLUTION LTD

Plunger pump wear fault detection method based on pressure-temperature layered trigger and physical prior mask self-attention

PendingCN122258011AHigh diagnostic sensitivityHigh robustness and low diagnostic sensitivityPump testingMeasurement devicesSignal correctionLow power dissipation
The application discloses a plunger pump wear fault detection method based on pressure-temperature layered triggering and physical prior mask self-attention, and belongs to the technical field of hydraulic system state monitoring and fault diagnosis. The method comprises the following steps: collecting vibration, pressure and temperature multi-source signals, and setting a default low power consumption of a main controller; realizing layered early warning and deep diagnosis awakening based on four dynamic characteristics of pressure and temperature and an abnormal proportion of a sliding window; performing synchronous compression wavelet transform on the vibration signal and performing temperature-pressure analytical linear real-time correction, block encoding and vibration Token sequence generation; generating an additive physical mask guided self-attention calculation based on a fault frequency band prior, and extracting wear sensitive features; comparing with a working condition grouping fault feature library to determine the fault type and grade. The application runs through the whole chain of signal correction, feature fusion and diagnosis decision with physical knowledge, and under the lightweight design of a model parameter quantity less than 500k, realizes a variable working condition diagnosis accuracy of 94.2% and an early wear false negative rate of 3.5%.
Owner:NINGBO INSTITUTE OF TECHNOLOGY BEIHANG UNIVERSITY

Follicular thyroid cancer-specific marker

A marker that can set a particularly clear cutoff value for distinguishing between follicular thyroid cancer (FTC) and follicular adenoma (FA), which is difficult in conventional pathological diagnosis is provided. Also provided are a method and a kit for diagnosing the development of FTC in a subject, comprising detecting expression of FAM19A2 in a sample derived from the thyroid tissue of the subject.
Owner:NIPPON MEDICAL SCHOOL FOUND +1

Multidimensional serum detection method and serum detection device based on surface enhanced Raman scattering substrate

The invention relates to a multi-dimensional serum detection method based on a surface enhanced Raman scattering substrate and a serum detection device.The serum detection method comprises the steps that a surface enhanced Raman scattering spectrum is obtained through the surface enhanced Raman scattering substrate; and obtaining a final detection result through a secondary discriminant analysis algorithm and a majority principle or a consistent agreement principle. By utilizing the serum detection method or the serum detection device, trace detection of the serum can be realized, a more reliable diagnosis result can be obtained, the whole process is simple and controllable, and the serum detection method or the serum detection device has a wide application prospect in the aspects of future practical clinical application and conventional serum screening. Meanwhile, the surface enhanced Raman scattering substrate disclosed by the invention has relatively high biochemical stability.
Owner:TSINGHUA UNIVERSITY

A method for quickly locating and diagnosing an inverter switch tube open circuit fault and a related device

The present invention is a method for rapid location diagnosis of an inverter switch tube open circuit fault and a related device, the method comprising: performing a fast S transformation FST on a specific harmonic of an open circuit fault of a T-type three-level grid-connected inverter to obtain the time domain dynamic characteristics of each harmonic of the current; performing a dq transformation on the three-phase current according to the time domain dynamic characteristics to solve the load current size, and then normalizing the three-phase current so that its harmonic characteristics are not affected by load changes; receiving the normalized three-phase current, training the collected current characteristic data of a known fault period, obtaining a random forest model, and using the random forest model to automatically identify and locate the open circuit fault online in real time. The present invention has the advantages of accurate fault location, reliable diagnosis results, good anti-interference performance, high intelligence, not being restricted by grid load, and adapting to different grid-connected environments.
Owner:STATE GRID HUBEI ELECTRIC POWER RES INST +2