42 results about "Oil analysis" patented technology

The invention relates to the technical field of wind power equipment monitoring, and discloses a wind power gear box intelligent fault early warning method and system based on machine learning. The method comprises the steps that multi-source monitoring data such as vibration signals, temperature data and oil analysis data of the wind power gear box are acquired, and multi-scale operation characteristics are extracted through time-frequency conjoint analysis; key fault sensitive features are determined through an adaptive feature selection algorithm, and a dynamic fault feature weight matrix is constructed in combination with a historical fault case library; multi-modal data fusion is adopted to generate an enhanced fault feature set, and modal decomposition is carried out on the enhanced fault feature set to obtain a trend component and a fluctuation component; a fault evolution feature space is constructed by using a deep neural network based on two components, then a fault development mode is identified by using a time sequence mode matching algorithm, and finally a graded early warning signal is generated according to a matching degree with a preset mode, so that fault features can be comprehensively captured, and safe operation of a wind power gear box is ensured.

A method to perform oil in produced water analysis allows measuring the large volume of oil in produced water reliably. In the method, a time-series and physics based machine learning model of a gas oil separation plant is generated, advisory actionable items for maintaining a crude oil quality within a pre-determined threshold are generated based on machine learning model coefficients and outputs of soft sensors, and then the advisory actionable items are presented to a user.

An on-site oil analysis method and system employs a rule-based diagnostic system to generate historical oil condition indicators for an asset used to model future oil condition indicators including probabilistic trajectories of continued oil degradation. Based on a user risk tolerance level, a modeled future oil condition indicator which will result in oil failure is determined. The oil condition indicator which will result in oil failure first and when is detected and provided as an output.

The present application provides an oil analyzer, comprising a shell, a sample storage module, a detection chamber, a near-infrared spectrum analysis module, a sampling module and a temperature adjusting module. The shell has a first cavity, when multiple oil samples need to be detected, the multiple samples can be simultaneously accommodated in the first cavity through a sample support and a sample tube, and the first cavity is refrigerated or heated through the temperature adjusting module, so that the first cavity is at the same temperature as the detection chamber. The oil analyzer provided by the present application can perform constant temperature treatment on the samples in advance, so that the temperature of the samples reaches a stable state when the samples are temporarily stored in the first cavity. In this way, when detection is performed, the samples first enter a cuvette through the sampling module, and then the cuvette is moved to the detection chamber through the first telescopic rod. After the samples enter the detection chamber, they no longer need to wait, and the near-infrared spectrum analysis module can directly perform spectrum analysis on the samples, eliminating the waiting time and improving the detection efficiency.

The application discloses a method for analyzing ferromagnetic abrasive particles by using a PQ instrument, a data processing system and a PQ instrument comprising the same. First, the PQ index of a sample to be measured in a uniform distribution state and a uniform deposition state is respectively tested by using the PQ instrument; then, a deposition-to-averaging ratio is calculated by using the PQ index; then, a calculation correlation coefficient of the PQ index and the ferromagnetic abrasive particle content of the sample is obtained by using the deposition-to-averaging ratio; finally, the ferromagnetic abrasive particle content of the sample is obtained by using a formula. The application can not only make up for the defect that the traditional detection method of the PQ instrument cannot detect the ferromagnetic abrasive particle content, but also can roughly judge the size range of the ferromagnetic abrasive particles in the sample, has higher ferromagnetic abrasive particle content detection precision, has good sensitivity for large-size abrasive particle detection, widens the use and research range of the PQ instrument, and makes the abrasive particle detection method in oil analysis more scientific and diversified.

The utility model discloses a high-capacity quartz combustion tube for oil product analysis. The high-capacity quartz combustion tube comprises a combustion tube I and a combustion tube II, the sleeve device convenient to disassemble is assembled on the combustion tube I and is used for connection; the pipe cap device is assembled on the sleeve device convenient to disassemble and is used for keeping air pressure balance; according to the device, the first rubber sealing sleeve is detachably installed on the top of the outer surface of the first combustion pipe. Secondly, a second combustion pipe is detachably installed on the inner surface of the first rubber sealing sleeve. And a mounting sleeve is fixed in the combustion pipe II. Meanwhile, a cap pipe body of the pipe cap device is fixedly installed on the top of the second combustion pipe, an air outlet thin pipe is fixed in the cap pipe body, and the outer surface of the air outlet thin pipe is connected to a limiting groove in the installation sleeve in a sleeved mode. Therefore, when the whole device works, gas is exhausted through the gas outlet thin pipe, the limiting groove ensures stable positioning of the gas outlet thin pipe, and the whole structure is convenient to disassemble and clean so as to maintain effective operation of the device.

A lubricating oil LIBS analysis and detection method based on an oil liquid film comprises the following steps: spraying micro oil drops on a metal substrate in a single drop manner, exciting the oil liquid film through an LIBS system to generate plasma, and collecting a plasma spectrum and analyzing spectrum data to realize analysis and detection. According to the method, the supply and movement of the aluminum foil are controlled, the operation time sequence of the aluminum foil, the oil drops and the LIBS system is regulated and controlled, the laser-induced plasma emission spectrum of the oil drops on the surface of the aluminum foil is collected, and then the element composition of the oil liquid to be detected is analyzed. According to the method, the oil pretreatment requirement of oil detection is reduced, the number of parameters of oil online detection is increased, and the oil analysis speed is increased.

The invention discloses a self-adaptive frequency modulation molten salt pump support stabilizing system, which belongs to the technical field of solar photo-thermal power generation, and comprises a support frame, a cross beam and a hydraulic damping mechanism, and is provided with a rigid adjusting system. The system outputs a vibration field coefficient based on rotation frequency, blade frequency, inherent frequency and vibration amplitude through a vibration field analysis module; the oil analysis module outputs an oil state coefficient based on oil viscosity, temperature and moisture; the gas state analysis module outputs a gas state coefficient based on the pipeline length, diameter and gas purity; and the gas content optimization module integrates the coefficients and the initial gas content, and outputs the target gas content through an established gas content optimization model, so that the gas pressure in the hydraulic buffer is dynamically adjusted, and the self-adaptive optimization of the system rigidity is realized. The resonance phenomenon in the operation of the molten salt pump is effectively restrained, and the accuracy and reliability of the vibration reduction effect are improved.

The invention relates to the technical field of oil quality analysis, in particular to an aviation oil property analysis method and system based on spectral oblique projection. According to the method, when the oblique projection operator is constructed, the limitation of a traditional oblique projection operator is broken through through dynamic multi-component cooperation and self-adaptive residual error separation, key information which is in complex association with properties in the aviation oil spectrum is extracted more accurately, the pertinence and robustness of feature extraction are improved, and the accuracy of feature extraction is improved. Higher-quality input variables are provided for an aviation oil property prediction model, and the method is a core technical support for realizing high-precision aviation oil property analysis.

The invention provides a steam turbine fault symptom identification method based on fuzzy vector mapping and independent element space reconstruction, relates to the field of steam turbine fault diagnosis, and aims to solve the problems that normal working conditions and fault features are difficult to distinguish and the non-linear and non-stationary signal processing capacity is weak in a traditional vibration analysis method, an oil analysis method and an independent element analysis method. The method comprises the following steps: collecting multivariable sensor data of a steam turbine in a normal state for preprocessing; establishing an initial independent element analysis model; a fuzzy observation vector is constructed by using a Gaussian membership function, and the influence of large-amplitude normal fluctuation is weakened; performing dynamic reconstruction in an independent element space through the hybrid matrix, and calculating a residual vector; and constructing a square prediction error statistic based on the residual vector to carry out fault judgment. According to the method, the problem of order and amplitude uncertainty in independent component analysis is effectively solved, the recognition accuracy of the early weak fault of the steam turbine is remarkably improved, and reliable technical guarantee is provided for safe and stable operation of a power system.

The invention relates to a portable insulating oil rapid analysis device and a detection method thereof. The portable insulating oil rapid analysis device comprises a data collector and a controller, the data collector is connected with the controller through the data transmission system; the data collector comprises a shell, a light path system and a signal conversion module, the light path system and the signal conversion module are both arranged in the shell, an insertion hole is formed in the top end of the shell, the insertion hole is communicated with the interior of the shell, a sample bottle filled with a sample is inserted into the light path system through the insertion hole, and a collection button is arranged at the top end of the shell; the light path system is used for acquiring a light signal of a sample in the sample bottle; the detection process comprises the following steps: inserting a sample bottle and obtaining a result; compared with a traditional insulating oil analyzer for a laboratory, the insulating oil analyzer is small in size and convenient to carry; meanwhile, operation is easy and convenient, and the test efficiency is improved.

The invention relates to a malfunction prediction system and a method for construction machines enabling prediction of faults based on the oil analysis values obtained from construction machines, and thus enabling the identification of maintenance needs for the machine.

1. The name of the design product: portable spectrum oil analysis instrument. 2. The use of the design product: an instrument for analyzing impurities in oil using spectrum. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective drawing.

The invention relates to the technical field of transformer automatic oil extraction, and discloses a transformer automatic oil extraction device which comprises an oil immersed transformer and an oil extraction assembly installed on one side of the bottom of the oil immersed transformer. Through three collecting pipes and a third connecting pipe on the oil extraction assembly, old oil and fresh oil are automatically separated and collected, oil sample pollution is avoided, and the oil extraction efficiency is improved. Accurate oiling test data is ensured, manual intervention is reduced, and the oil extraction efficiency is improved; through a splitter plate, a sealing plate and a spring, automatic sealing of the collecting pipe is achieved, air and impurities are prevented from being mixed in, and it is guaranteed that an oil sample is pure to support secondary detection; the L-shaped mounting plate and the splitter plate are matched to guide oil flow, and the exhaust valve and the pipeline are combined to exhaust air, so that bubbles are prevented from interfering with detection; three-section oil sampling is completed by means of the gravity of oil, extra power is not needed, energy consumption is reduced, the process is simplified, the device is adaptive to multiple scenes, and the accuracy and safety of transformer oil sample detection are comprehensively guaranteed.

The invention discloses an EDS-based aircraft oil system redundant material identification method and application, and relates to the technical field of aircraft oil analysis, and the method comprises the following steps: S1, collecting all material matrix components and surface treatment process components of actual aircraft oil system parts by using an EDS, establishing a part standard component database after the complete technological process; s2, cleaning particle redundant substances obtained by filtering the airplane oil needing to be identified; s3, acquiring component test data of the to-be-identified redundant substances by utilizing EDS, and performing standardized data processing on a test result; and S4, comparing the data in the step S3 with the standard component database in the step S2, and identifying the material of the redundant substances, so that the problems that in the prior art, a method for determining the redundant substances of the oil filter particles is limited by the sizes of the particles, or the determination result is inaccurate, the operation process is complicated, and the detection period is long are solved, and the method is suitable for popularization and application. The method can be applied to evaluation of the internal health state of the aircraft oil system.

The invention discloses a detection device for chemical oil product analysis, and belongs to the technical field of oil product detection, the detection device comprises an analysis detector, the analysis detector is provided with a display screen for operation, the analysis detector is internally provided with a detection cavity, a light shielding plate is slidably connected between the detection cavity and the analysis detector, and the light shielding plate is slidably connected with the analysis detector. According to the detection device for chemical oil product analysis, the driving assembly is arranged to work to vertically move the pushing rod, the pushing rod can push the piston when vertically moving, and the piston can slide in the sample measuring cylinder when being pushed; when the piston slides, an oil product in the sample measuring cylinder can be pushed into the sample vessel, and as the volume of the oil product in the sample measuring cylinder is slightly greater than that of the interior of the sample vessel, the oil product can fully spread the placing cavity when entering the sample vessel, so that the oil product can fully spread the placing cavity conveniently, the operation is convenient, and the detection accuracy is improved.

The invention relates to a method for maintaining a rotating machine in a thermal power generating unit, which comprises the following steps of: acquiring the running full life cycle data of the rotating machine in the thermal power generating unit, including multi-source information such as vibration monitoring, oil analysis, infrared temperature measurement, equipment performance parameter analysis and the like, and performing data fusion on the multi-source information after data preprocessing and normalization; a data set constructed by the method is input into a model constructed by the method, the constructed model is divided into a fault recognition model and an equipment service life prediction model, the constructed model is deployed in a unit intelligent maintenance system after being trained, tested and evaluated, equipment operation data input in real time is subjected to fault analysis and recognition through the fault recognition model, and the service life of the equipment is predicted. The fault type, position and degree can be accurately diagnosed, misdiagnosis and missed diagnosis are reduced, and the running reliability of the unit is improved; and the residual life and the fault risk of the equipment are pre-estimated through the life prediction model, so that scientific maintenance measures are formulated, and the fault risk and the maintenance cost are reduced.

The invention discloses a lubricating oil on-line monitoring and calibrating method based on oil analysis. The method comprises the steps that real-time monitoring is conducted through a sensor; analyzing oil in a laboratory to obtain oil analysis data; associating the corresponding sensor real-time data with the oil analysis data, storing to form an actual historical association database, and predicting to obtain a virtual historical association database; according to a timestamp, combining the actual historical association database with the virtual historical association database to obtain a historical association data total database; and performing relation mining by taking the historical association data general library as a sample set to obtain an effective association rule, and performing calibration operation according to the effective association rule. According to the lubricating oil on-line monitoring and calibrating method based on oil liquid analysis, the data blank period of laboratory analysis is filled through the virtual data model; and meanwhile, by utilizing an association rule mining technology, internal association between real-time data and laboratory data is deeply mined, and calibration is carried out based on the internal association, so that the reliability and the accuracy of online monitoring data are greatly improved.

A downhole fluid sampling tool may include an optical measurement tool and a viewing region disposed in the optical measurement tool. In examples, a bridge may be disposed in a transparent portion of the flow path between a light source and a light modifier and an optical detector. The bridge includes a structure comprising a substrate and a contrast agent, wherein the contrast agent is any molecule configured to interact with an analyte and alter a property of the analyte and / or contrast agent, wherein the property is detectable by the optical measurement tool.

The invention relates to the field of petroleum analysis instruments, in particular to a pretreatment device of a movable oil analyzer. The oil product analyzer mainly solves the problems that an existing oil product analyzer is not suitable for oil products with low water content, and analysis errors are large. A bearing plate (6) capable of moving up and down is arranged in the test box (1), a heating seat (2) is arranged at the upper part of the bearing plate (6), a test cup (9) is placed on the heating seat (2), and an elastic weighing assembly (12) is arranged below the bearing plate (6); the cup cover (18) is connected with a stirring assembly (8); the cup cover (18) is connected with the heating base (2) through a transmission assembly (10), and the transmission assembly (10) enables the heating base (2) to rotate reversely relative to the cup cover (18). And a light emitting module (14) and a receiving module (15) are arranged on the inner wall of the test box (1). When the pretreatment device of the movable oil analyzer is used for heating oil products, crude oil is uniformly heated, meanwhile, weighing is accurate, the pretreatment device is matched with the analyzer for use, and the analysis result error is small.

The invention relates to a motor vehicle (10), a fuel analysis device (18), and a method for determining the synthetic and fossil fuel content of a fuel for a motor vehicle (10), wherein a sensor device (20) is arranged in a fuel line (16) of the motor vehicle (10). The method comprises, as steps: determining at least one fuel parameter of the fuel by the sensor device (20) while fuel flows through the fuel line (16), the fuel parameter comprising at least one resistive measurement value; and determining the synthetic and fossil fuel content based on the determined fuel parameter and predetermined reference parameters by a control unit (22).

The application relates to the technical field of wind power equipment monitoring, and discloses a wind power gearbox intelligent fault early warning method and system based on machine learning. The method comprises the following steps: acquiring vibration signals, temperature data, oil analysis data and other multi-source monitoring data of a wind power gearbox, extracting multi-scale operation characteristics through time-frequency joint analysis; determining key fault sensitive characteristics through a self-adaptive feature selection algorithm, combining a historical fault case library to construct a dynamic fault characteristic weight matrix; generating an enhanced fault characteristic set through multi-modal data fusion, obtaining a trend component and a fluctuation component through modal decomposition; constructing a fault evolution characteristic space based on the two components through a deep neural network, identifying a fault development mode through a time sequence mode matching algorithm, and finally generating a graded early warning signal according to the matching degree with a preset mode, so that fault characteristics can be comprehensively captured, and the safe operation of the wind power gearbox is guaranteed.

A downhole fluid sampling tool may include an optical measurement tool and a viewing region disposed in the optical measurement tool. In examples, a bridge may be disposed in a transparent portion of the flow path between a light source and a light modifier and an optical detector. The bridge includes a structure comprising a substrate and a contrast agent, wherein the contrast agent is any molecule configured to interact with an analyte and alter a property of the analyte and / or contrast agent, wherein the property is detectable by the optical measurement tool.

The invention provides a motor sealing performance quantitative evaluation method, device and system based on oil analysis, and relates to the technical field of motor testing and fault diagnose.The method comprises the steps that test oil is injected into a shell of a tested motor, a reference oil sample is collected after circulation, and initial component data of the reference oil sample is obtained; executing a preset sealing performance test on the tested motor; after the test is completed, circulating the oil liquid in the shell, and collecting an oil sample after the test; performing component analysis on the tested oil sample to obtain post-component data, and comparing the post-component data with the initial component data to obtain quantitative variation of at least one component; and generating a quantitative evaluation conclusion for the sealing performance of the tested motor based on the quantitative variation. The sealing performance of the oil-cooled motor can be evaluated objectively, accurately, quantitatively and non-destructively.

This invention relates to spectroscopic technology, specifically providing a method for oil analysis in water based on the fusion of ultraviolet absorption spectroscopy and three-dimensional fluorescence spectroscopy, comprising the following steps: A1. Obtaining oil samples of different types and concentrations, and obtaining the corresponding ultraviolet absorption spectra and three-dimensional fluorescence spectra; A2. Expanding the three-dimensional fluorescence data and ultraviolet absorption spectral data, corresponding to the excitation wavelength, and stitching the two together to obtain the fused spectrum, with absorbance as a separate column; A3. Decomposing the fused spectrum X and the dependent variable matrix Y; obtaining a set of T and U with the maximum covariance, thereby obtaining the model B=(T T T) ‑1 T T U; A4. Obtain a water sample, obtain the corresponding fusion spectrum according to A1 and A2, and use the model to obtain Y, thereby determining the type of oil in the water and the corresponding concentration. This invention has advantages such as accuracy.

The utility model provides an oil-in-water treatment system and a cooling water system. The oil-in-water treatment system comprises a detection pipeline, a detection device and an oil-in-water analyzer, wherein the detection device and the oil-in-water analyzer are arranged on the detection pipeline; the oil-in-water analyzer is connected with the detection device; wherein the detection device comprises a first electromagnetic valve, an oil-water mixer, a peristaltic pump, a first conversion connector, a sensor probe detection chamber, an ultraviolet fluorescence sensor, a second conversion connector and a second electromagnetic valve, the oil-in-water treatment system is mounted on a main path of a cooling water system, and oil-in-water measurement of cooling water is completed once by opening and closing the electromagnetic valves; and the first electromagnetic valve and the second electromagnetic valve can be continuously opened to detect and obtain the change of the oil content in water of the cooling water within a period of time, so that the detection efficiency of oil in water in the cooling water system is improved.

A method of analyzing a lubricating oil may include: measuring a first concentration of components in a lubricating oil prior to introduction into a cylinder in a two-stroke engine using x-ray fluorescence, the components comprising: sulfur and total calcium; collecting a scrape-down lubricating oil that corresponds to the lubricating oil after having been passed through the cylinder during fuel combustion of a fuel comprising 0.5 wt % or less sulfur; measuring a second concentration of the components in the scrape-down lubricating oil using the x-ray fluorescence; and calculating an amount of acid neutralized during combustion based on the first and second concentration of the components. Based on said analysis a change to a property of the scrape-down lubricating oil and / or changing a feed rate of the lubricating oil into the cylinder based on the amount of acid neutralized may be implemented.

The invention relates to the technical field of machine vision and oil product analysis, and discloses a full-automatic oil product acidity detection system based on machine vision. According to the system, detection is realized through links of initial acquisition, feature conversion, time sequence segmentation, environment accumulation, anomaly judgment and result synthesis. The initial acquisition link synchronously acquires an oil product image and temperature and illumination data; in the feature conversion link, color and light transmittance features are analyzed and normalized, and an acidity feature value is output; in the time sequence segmentation link, the change rate of adjacent samples of the sequence is calculated, and stable and variable sections are divided; the environment accumulation link performs integral operation on the temperature and illumination trend in the stable section, and quantifies the accumulation effect; in the abnormity judgment link, an environment accumulation result and variation section information are integrated to verify abnormal points; and a result synthesis link generates a final report. According to the system, by analyzing the acidity dynamic change trend and quantifying the environmental cumulative influence, oil product deterioration and environmental interference are distinguished, and the detection accuracy and reliability are improved.

The utility model provides an excitation device of a rotating disk electrode emission spectrometer, which comprises an electric arc generator which is arranged on a bottom plate of an inner cavity of an instrument, generates high-voltage pulse electric arc and excites an oil sample. And the rod electrode excitation device is arranged in front of the excitation substrate and is used for being connected with a positive electrode of an output excitation power supply of the arc generator, and a fixed analysis gap is formed between a rod electrode and a disc electrode through one-button mechanical operation. The disc electrode excitation devices are mounted on the front side and the rear side of the excitation substrate, are connected with a negative electrode of an output excitation power supply of the arc generator, drive the graphite disc electrode to rotate, bring an oil sample in an oil boat placed on the oil boat support to an analysis gap between the graphite disc electrode and the graphite rod electrode, and excite the oil sample by utilizing a high-voltage arc generated between the two electrodes. The utility model has the beneficial effects of stable performance, long service life, simple structure, small volume and light weight, and is suitable for the technical field of oil analysis.

The invention discloses a microscopic remaining oil quantitative recognition method, device and equipment, a medium and a product, and relates to the technical field of oilfield development, and the method comprises the steps: obtaining an initial saturated oil image and a remaining oil image in a displacement process; pre-classifying the remaining oil image based on a machine learning model, and performing initial correction to obtain a pre-classification result of each type of remaining oil; querying the contour of the remaining oil according to the three-valued segmentation map, and calculating feature parameters of the remaining oil; carrying out category binding on the remaining oil contour and the pre-classification result, and carrying out secondary correction to obtain a category binding result; and performing corresponding category parameter mapping on the category binding result and the remaining oil characteristic parameters to obtain a microscopic remaining oil analysis report. According to the application, through high-precision remaining oil type identification, in combination with remaining oil occurrence state quantitative analysis of multi-dimensional characteristic parameters, data correction and deep learning technologies are fused; and precise classification and quantitative analysis of microscopic remaining oil occurrence forms are realized.