98results about How to "Achieve early warning" patented technology

The invention belongs to the technical field of fluid mechanical and intelligent diagnosis, and particularly discloses an intelligent water pump set monitoring and fault early warning method based on internet of things. According to the technical scheme, a water pump set testbed is built; a touch screen serves as site monitoring equipment, a PC machine serves as a monitoring platform, a data collection module is used for collecting signals of all sensors, and the touch screen and the PC machine read the data of the data collection module in real time and store and backup the data; The water pump set internet-of-things monitoring system is designed through an HMI, and remote intelligent monitoring of water pump sets on the basis of internet of things is achieved; and monitoring signals of the water pump sets are subjected to data analysis in real time, operational diagnosis and fault early warning. The internet of things technology, the spectral analysis technology and the fault diagnosis technology are effectively combined, early warning of faults of various water pump sets like centrifugal pumps, mixed-flow pumps, axial flow pumps and submersible electric pumps is achieved, and the water pump sets can operate safely and reliably.

The invention discloses an equipment failure early warning and optimizing method and system based on a similarity curve. The method comprises the steps of: screening normal operation real-time history data from equipment operation real-time history data; generating a data state set based on the normal real-time history data and carrying out extraction according to the distribution of data groups in the data state set to establish a normal operation data model reflecting real operating principles of equipment; comparing the real-time state value group of the equipment which is in online operation with the value groups of each state point in the normal operation data model, and calculating to generate the similarity curve; calculating the data state set of the equipment in normal state on the basis of the normal operation data model, and defining equipment potential failure early warning and optimizing rules corresponding to the change of the similarity curve; and combining the equipment potential failure early warning and optimizing principles, analyzing the change of the similarity curve, distributing the equipment potential failure early warn, and generating the equipment optimization operation guidance.

The invention relates to a polarization-based early warning system of a distributed optical fiber oil transporting pipeline, which comprises a laser. A forward-propagating optical signal sent from a laser is input from a first port of a polarization beam splitter, and output from a second port to sensing optical fiber connected with a Faraday polariscope. The forward-propagating optical signal is reflected by the Faraday polariscope, and becomes a backward-propagating optical signal after the polarization state of the signal rotates 90 DEG. The backward-propagating optical signal is input from the second port of the polarization beam splitter, and output from a third port to a photoelectric detector. The changed electrical signal is transmitted to a digital signal processing subsystem. The early warning system can position a sensing line perturbing point according the time information of electric power change so as to output alarm and positioning information. The early warning system has the advantages of low cost, high safety and reliability. Furthermore, the early warning system can early position and warn against acts of sabotage to the oil transporting pipeline.

The invention relates to a method and a device both based on annulus pressure measuring while drilling and for early monitoring gas invasion of a wellhole. The device is characterized in that the device comprises a drilling column arranged in the wellhole, the bottom of the drilling column is connected with an annulus pressure measuring while drilling device and a drilling bit, the annulus pressure measuring while drilling device comprises an annulus pressure sensor, an annulus temperature sensor, a signal monitoring circuit, a data storage circuit, a battery and a data connector, the top of the annulus pressure measuring while drilling device is connected with a measuring while drilling device which comprises a signal receiving module and a pulse generator, a drilling fluid returning flowmeter is arranged on the upper portion of the drilling column, one side of a wellhead is connected with a mud pump and a mud circulating pool through a pipeline, a mud pressure sensor is mounted on the mud pump, a mud level meter is arranged in the mud circulating pool, the drilling fluid returning flowmeter, the mud pressure sensor and the mud level meter are in wire connection with a well logging instrument respectively, a filter module and a signal measuring module are arranged in the well logging instrument, and the well logging instrument is connected with a data analyzing and alarming module through a wire. The method and the device can be applied to deepwater oil drilling operations.

The invention provides a detection method for a train bearing fault. The method comprises the following steps of: comprehensively detecting an integral fault characteristic spectrum so as to ensure the safety of a train bearing; and when detection signals are implemented, performing further processing by utilizing related methods after a measured spectrum result is obtained by sampling, conversion and calculation so as to overcome the interference of random vibratory impulses in measurement. The method has the effects that a KW2002 bearing fault diagnostic apparatus designed and manufactured by utilizing the method is used for realizing the static no-disassembly detection of faults comprising the abrasion of a bearing component, and a KW0021 train bearing monitor designed and manufactured by utilizing the method can be used for monitoring the status of the bearing in real time in the running of a train to realize the early warning of the bearing fault, so that the safety of railway traffic is greatly improved; and minor fault characteristics can be detected in the running of the train, and the long-lasting thinking mode that the inference produced in the running of the train cannot be overcome in China is broken.

The invention discloses a millimeter wave scanning entomological radar detection system and a millimeter wave scanning entomological radar detection method. The detection system comprises an antenna device, a transmitter, a receiver, a signal processor and a data acquisition terminal, wherein the antenna device is used for transmitting a microwave signal for detecting an insect and receiving the microwave signal reflected by the insect; the transmitter is used for producing a pulse modulated microwave signal for detecting the insect and transmitting the pulse modulated microwave signal for detecting the insect through the antenna device; the receiver is used for receiving the microwave signal reflected by the insect and processing the microwave signal; the signal processor is used for receiving, converting and processing the signal processed by the receiver, and acquiring insect intensity data; the data acquisition terminal analyzes and calculates the acquired insect intensity data and azimuth data to obtain the spatial distribution and time information of the insect. The millimeter wave scanning entomological radar detection system and the millimeter wave scanning entomological radar detection method provided by the invention are used for carrying out the real-time monitoring and the dynamic analysis of a migration process of important migratory injurious insects of rice so as to realize early-warning of insect pests.

The invention provides a temperature monitoring system and monitoring method capable of realizing early warning on breast pathological changes. The monitoring system has a concrete structure comprising two cups used for accommodating breasts, wherein a temperature sensor three-dimensional array is arranged on the surface or the inside of one side, for accommodating the breast, of each cup. The temperature monitoring system is characterized by also comprising an armpit temperature monitor used for monitoring the body temperature; the output ends of the temperature sensor three-dimensional array and the armpit temperature monitor are respectively and electrically connected with a receiving end of a microprocessor positioned on the cup; the microprocessor is in wireless connection with the intelligent terminal. The monitoring system can realize the early warning on the breast local pathological changes such as breast tumor in the early stage, and can also realize the early warning on the breast integral pathological changes such as hyperplasia of mammary glands in the early stage; the wearing and the monitoring are convenient; the monitoring precision is high; the cost is low.

The invention belongs to the technical field of subway tunnel construction safety management and relates to a method for demonstrating a surface collapse disaster caused by subway tunnel construction. The method comprises analyzing the current situation of the surface collapse disaster frequently caused by the subway tunnel construction, summarizing the reason, the mechanism, and the process of the surface collapse disaster caused by the subway tunnel construction; constructing and visualizing of the evolution process and the damage degree of the surface collapse disaster caused by the subway tunnel construction by using a scenario construction concept and method. By means of the demonstration animation, people understand the evolution process of the subway collapse more visually and specifically, coordinate and plan the duties of respective parties in the disaster in advance so that professionals know how to quickly and effectively solve their own technical problems in cooperation in order to minimize the losses of the people due to the disaster within the shortest time.

The invention relates to a perioperative period critical event prediction method based on cross-modal deep learning, and belongs to the field of artificial intelligence and medical application. The method comprises the following steps: step 1, constructing a multi-modal medical monitoring data set; 2, performing bimodal fusion feature learning on patient monitoring data and personalized data; 3, cross-modal collaborative learning feature extraction; 4, constructing a multi-modal critical event (death risk) prediction model; 5, verifying model feedback. The method serves as a critical adverse event prediction and early warning tool, and is an effective method for achieving real-time tracking, early diagnosis and early warning of main critical events after operation.

The invention provides a diagnostic kit for detecting active pulmonary tuberculosis. The kit consists of an RNA extract buffer solution, a specific serum miRNA composition for the active pulmonary tuberculosis, internal reference reverse transcription primers, polymerase chain reaction (PCR) primers and a fluorescent quantitative reverse transcription-polymerase chain reaction (RT-PCR) reaction solution, wherein the specific serum miRNA composition for the active pulmonary tuberculosis consists of four differential expression serum miRNAs, namely hsa-miR-29c, hsa-miR-22, hsa-miR-320b and hsa-miR-101. By using the specific serum miRNAs composition for the active pulmonary tuberculosis to detect the active pulmonary tuberculosis on the serum miRNAs level, the sensitivity is 90.2 percent, and the specificity is 75.0 percent; and the kit has early-stage diagnostic value for the active pulmonary tuberculosis, and can realize early warning and early diagnosis of the active pulmonary tuberculosis.

The invention discloses a preparation method of a paper-based electrochemical luminescence converter and applications of the electrochemical luminescence converter in carcino-embryonic antigen detection. Through wax printing technology, screen printing technology and the functionalization of paper chips, an input signal of protein is converted into an output signal of a specific aptamer chain to further cause the change of luminol electrochemical luminescence intensity, so that the high-sensitive and portable detection of low-concentration tumor markers can be realized.

The invention discloses a predicting method for a development trend of wildfire at the periphery of a power transmission line corridor. The method comprises the following steps: firstly, laying and installing a small-sized radar and a micro meteorological sensor by combining with the conditions of the power transmission line corridor; secondly, querying geographic and geomorphic data of the power transmission line corridor at the periphery of wildfire from a GIS (Geographic Information System) information platform; thirdly, setting a time interval delta t, extracting meteorological data by taking the time interval as a unit in real time, transmitting back and then caching into a database; fourthly, analyzing small-sized radar scanning data, and monitoring fire behavior in real time by using the small-sized radar; fifthly, predicting the trend of the wildfire at the periphery of the corridor by combining with a wildfire development trend simulation algorithm; sixthly, performing aid decision making on the development trend of the wildfire at a next stage by using wide-area meteorological monitoring data of the small-sized radar. According to the predicting method disclosed by the invention, refined fire behavior information of the periphery of the line corridor and medium-long term weather conditions are provided by the small-sized radar; meanwhile, the predicting method has the advantages of wide monitoring range, high meteorological data accuracy and the like.

The invention discloses a multi-level arc fault disconnection system comprising AFCI systems, arc fault intelligent algorithm analysis systems and arc fault intelligent interaction systems arranged atdifferent levels and branches, and each AFCI system comprises a multi-dimensional arc fault information detection and integration system, an arc fault intelligent primary analysis system and an arc fault circuit breaker. The multi-dimensional arc fault information detection and integration system performs multi-dimensional real-time monitoring on a user end, and the arc fault intelligent primaryanalysis system analyzes the monitored information. The arc fault intelligent algorithm analysis system analyzes abnormal signals, and the arc fault intelligent interaction system issues control commands to the arc fault circuit breaker. The present invention provides the multi-level arc fault disconnection system. The system can improve the accuracy and operational reliability of the ACFI system,and realize the selective coordination of the multi-level arc fault disconnection system to achieve the purpose of accurate power supply interruption.

The invention relates to a surge symptom identification method based on frequency band energy, which comprises the following steps of: segmenting a pressure time domain signal into continuously changing time slices by using a sliding window statistic method, locally detailing fine spectrum analysis by adopting a continuous Fourier transform so as to detail each stage of data of historical pressure signal surge symptom of a compressor pipe network; in a sensitive frequency band, inserting n-2 points at equal internals to divide the sensitive frequency band into n networks; then computing the amplitude of each fine frequency point by adopting the continuous Fourier transform, computing and monitoring sensitive frequency band energy; drawing a frequency band energy monitoring curve according to the frequency band energy obtained by the computation, setting an alarming threshold according the increase stage of the amplitudes of the monitoring curve, and realizing the surge symptom identification of real-time data of a compressor. The method reflects unstable energy disturbance in a containing cavity of a compression system through monitoring the change of the frequency band energy, and realizes the early-stage identification and the early warning of the surge symptoms.

The invention discloses an S100 family-based acute pancreatitis severity prediction model and detection method thereof, and belongs to the technical field of acute pancreatitis detection. The acute pancreatitis severity prediction model is established by utilizing S100A6, S100A8, S100S9, S100A11, S100A12 and S100P in the S100 protein family; and for severe acute pancreatitis, the prediction modelhas a diagnosis sensitivity of 92.30%, a specificity of 84.70%, a false positive rate of 15.30% and a false negative rate of 7.70%. Compared with the present clinically used scale detection and imaging diagnosis, the prediction model has reduced subjectivity, is more correct and has a quantitative detection effect.

The invention relates to an insulation state on-line integrated monitoring system for a switchgear. The insulation state on-line integrated monitoring system comprises a plurality of monitoring units which are connected with an operation management server through the Ethernet, wherein each monitoring unit includes a monitor, a star coupler, a light wave multiplexer and a plurality of optical temperature magnetic field composite sensors; an input optical port of the star coupler is connected with a broadband light source through fiber; each output optical port of the star coupler is connected with one input optical port of the light wave multiplexer through one optical temperature magnetic field composite sensor; and an output optical port of the light wave multiplexer is connected with an input optical port of the monitor through the fiber. By means of combination of the optical magnetic field sensing technology with the distributed fiber grating temperature sensing technology, the insulation state on-line integrated monitoring system for a switchgear realizes measurement of the temperature and the local signal at the same time. The insulation state on-line integrated monitoring system for a switchgear can timely discover the fault of the switchgear, can realize early warning and positioning of the fault, and is conductive to making a repair schedule reasonably and improving the operation reliability of an electric power system.

The present invention provides an indirect competition method for golden test paper for detecting micro-oxidation low density lipoprotein colloid. The competition method is applied to the test paper. A certain amount of golden dot antibody is covered on the golden dot antibody pad. The oxidation low density lipoprotein is covered on a detecting region. Through the observation of the color of the detecting region, whether the oxidation low density lipoprotein in the serum or the plasma of a human body being higher than a normal level can be detected. The present invention is convenient and quick; the detection of the oxidation low density lipoprotein can be directly carried out; and the present invention provides reliable evidence to the early diagnose of atherosclerosis.

The invention relates to a method for monitoring and early warning of flammable gas concentration, which mainly solves the problem of poor safety in the prior art. The present invention stores the flammable gas concentration data in the database by adopting a flammable gas concentration monitoring and early warning method, and processes the data as a time series to obtain the flammable gas concentration time series data, and then outputs it through a neural network, The concentration boundary value is set in advance, and when the boundary value is reached, the technical solution of automatic alarm by the system solves the above problems well, and can be used in flammable gas concentration monitoring and early warning.

The invention relates to a unit equipment temperature abnormity detection method. The method comprises the following steps that (1) establishing a unit equipment temperature abnormal state identification model based on WCA and Shepard interpolation based on analysis of historical data of unit equipment, wherein the historical data of the unit equipment comprises temperature state monitoring data of a unit under different environmental factors and operation conditions; (2) acquiring environmental parameters, operating condition parameters and corresponding measured temperature values of the unit equipment under the current working condition, and inputting the environmental parameters and the operating condition parameters of the unit equipment under the current working condition into the unit equipment temperature abnormal state identification model to obtain a health standard value output by the model; and (3) comparing the measured temperature value of the unit equipment under the current working condition with the health standard value, and determining the temperature running state of the unit equipment under the current working condition according to a comparison result. The method can be widely applied to the field of temperature abnormity detection of unit equipment.

The invention relates to the field of protein fingerprint detection technology, especially to a fingerprint model for liver cancer serum characteristic protein detection. Seven abnormal fucosylation glycoproteins which include four up-regulated proteins and three down-regulated proteins are screened from serum as a characteristic proteome. On the base of the characteristic proteome, the fingerprint model for liver cancer serum characteristic protein detection is built. The molecular weights of the four up-regulated proteins are 9290.06 Dalton, 2660.24 Dalton, 2764.18 Dalton and 1862.71 Dalton respectively. The molecular weights of the three down-regulated proteins are 4282.99 Dalton, 3963.52 Dalton and 6023.31 Dalton respectively. The fingerprint model provides a new method for early diagnosis of liver cancer, provides a foundation for further finds of new tumor markers, and is beneficial to improve the accuracy of diagnosis of liver cancer.

The invention discloses a transformer body oil leakage area detection system and method. The system is characterized by comprising a monitored transformer, a transformer oil leakage area detector, a display screen, a power socket, a communication and USB port, operation keys, an operation interface, an oil leakage area, a single-point fluorescence excitation source, an annular fluorescence excitation source, a rotating sleeve, a fluorescence detector, a high-precision movement controller, a main control panel and a stepping motor. According to the system, whether leakage oil of the transformerbody is rapidly judged and the oil leakage area is calculated. According to the system, the principle that the ultraviolet light beam irradiates to the leakage oil area of the transformer body and then excites the oil surface fluorescence imaging is adopted, so that the leakage oil insulation problem of equipment can be rapidly and accurately detected in real time.

The invention discloses a gas turbine combustion system online monitoring method based on an exhaust temperature measuring point correlation. The invention relates to the gas turbine combustion system online monitoring method. The invention mainly aims at solving a problem that early warning for a combustion system cannot realized in the prior art, and discloses the gas turbine combustion system online monitoring method based on the exhaust temperature measuring point correlation. The method comprises following steps: 1, achieving the temperature of n temperature measuring points at the time t; 2, obtaining a-hat and b-hat according to the temperature of the n temperature measuring points at the time t; 3, determining the [Ti]'-hat according to the a-hat and the b-hat obtained in the step 2; 4, defining the relation coefficient [alpha]i according to a formula that [alpha]i = [Ti]'-hat / T-hat; 5, setting the range of the [alpha]i being [[alpha]i1, [alpha]i2]; and 6, drawing dots with the upper limit [alpha]i1, the lower limit [alpha]i2 and the [alpha]i being polar radiuses and with (2[pi]*i) / n being the polar angle in polar coordinates, sequentially connecting the dots drawn from i=1 to i=n by straight lines, and connecting the dot drawn when i=1 and the dot drawn when i=n by a straight line, so that an enclosed polygon is obtained. If the range of the polar radius [alpha]i is [[alpha]i1, [alpha]i2], a gas turbine is in a normal operation state. The monitoring method is applicable to the field of gas turbine combustion system online monitoring.

The invention discloses a GSM-based automatic fire alarm system. The system is composed of an alarm, an alarm host and a user mobile phone. The alarm is a photoelectric smoke-sensing type fire detection alarm, and the alarm, when detecting a fire, can send wireless alarm signals to the alarm host while emitting both acoustic and optical alarm signals by itself; the alarm host comprises a host casing, a host control circuit board and a host power supply, and the host control circuit board is integrated with an RF receiving module, an MCU master control module and a GSM communication module used for sending an alarm short message to the user mobile phone through a 2G network; the host casing is provided with a toggle switch and a Learn key; the alarm is provided with a TEST key; and a mode state comprises a work mode and a mobile phone arrangement mode. According to the invention, the GSM-based automatic fire alarm system can be applied to work at any places with GSM signals, wiring is unnecessary, the application is convenient, the operation is simple, and the alarm demand of household fire prevention can be met.

The invention relates to a proportion coefficient analysis-based momentum wheel fault diagnosis method. The objective of the invention is to solve the problem that an existing momentum wheel fault detection method cannot effectively and timely detect faults, and can only diagnose serious faults, and cannot realize early warning of small faults. The method includes the following steps that: 1, with the telemetry data of motor current adopted as reference, segmentation time points of all telemetry data are obtained; 2, the average control input voltage value of each segment of the motor current is obtained; 3, the proportion coefficient of the average control input voltage value of the j-th segment of the motor current and the value of the motor current is k(j)=U(j) / I(j); 4, an abnormality threshold value is set; and 5, when fault detection is performed on a momentum wheel according to the abnormality threshold value, the telemetry data are processed according to the step 1, step 2 and step 3, so that k' is obtained, if the k' is larger than the abnormality threshold value, it is indicated that a fault occurs. The proportion coefficient analysis-based momentum wheel fault diagnosis method of the invention is applied to the momentum wheel fault diagnosis field.

The invention discloses a Parkinson's disease early warning system based on daily behavior analysis, relates to the technical field of computer vision and deep learning, and comprises a video acquisition module, a video analysis module, a controller, a database, a processing terminal, a behavior analysis module, an alarm module and a specific behavior task module. According to the invention, a multi-azimuth high-spatial-resolution camera is adopted, computer vision and a deep learning technology are utilized, other hardware equipment is not needed, and behavior characteristics of TIA related symptoms, such as sleep disorder, balance loss, cognitive dysfunction and dyskinesia, are accurately captured by carrying out recognition tracking and skeleton analysis on 19 joint points of the trunk of a person, so that daily activity behavior capture and specific behavior task module scoring analysis are realized, and are compared with normal daily behaviors and behavior scoring values to objectively judge whether a testee suffers from the risk of Parkinson's disease or not; and then the effect of early warning of patients suffering from the Parkinson's disease is achieved.

According to the embodiment, the invention provides a household physical examination monitoring system, which comprises a cabinet and a console, wherein a physical examination instrument cabin and computers are arranged in the console; physical examination sensors are arranged in the physical examination instrument cabin; a data processing equipment cabin, specimen cabins, a test equipment cabin, a transmitting and positioning device and a controller are arranged in the cabinet; data processing equipment is installed in the data processing equipment cabin, and the data processing equipment is used for receiving physical examination signals acquired by the physical examination sensor and for converting the physical examination signals into physical examination data; physical examination specimens are kept in the specimen cabin; test equipment is installed in the test equipment cabin; by virtue of the transmitting and positioning device, the physical examination specimens are tested by virtue of the test equipment, so that physical examination data is obtained; and the controller is used for turning on or off the physical examination sensors, the data processing equipment and the test equipment, acquiring the physical examination data and uploading the physical examination data to the computers. The household physical examination monitoring system disclosed by the invention integrates mainstream technology for disease diagnosis at present; and the household physical examination monitoring system is simple to operate and is applicable to household use, so that the convenience of the general public in physical examination is greatly improved.

The invention relates to the field of gene detection, in particular to a method for detecting colorectal cancer driving genes and susceptible SNPs based on nucleic acid mass spectrometry technology. The present invention selects 25 CRC hot spot mutation sites and 22 SNP sites that are significantly related to the risk of lung cancer in Asian populations and have independent functions by analyzing the whole genome sequence of colorectal cancer and analyzing the positive samples of Asian population in GWAS research. To assess the risk of an individual developing CRC. Compared with TaqMan-PCR and second-generation platform sequencing, the detection method has the characteristics of simplicity, flexibility, high throughput, low cost, and the like. In addition to being used for early assessment and large-scale screening of CRC, the present invention provides an important reference basis for risk assessment and diagnosis of CRC, so as to realize early warning of colorectal cancer disease, and at the same time, according to the detection results, CRC patients can be assessed. Personalized treatment.

The invention, which belongs to the technical field of structural health monitoring, provides a long-term reinforcing steel bar corrosion monitoring sensor based on a long-period fiber bragg grating sleeve structure. The long-term reinforcing steel bar corrosion monitoring sensor comprises long-period fiber bragg gratings, steel sleeves, epoxy resin parts and protective hoses. Since the sensor isbased on the high sensitivity of the long-period fiber bragg gratings to the external environment refractive index and is provided with the steel sleeves with the same components as a steel bar, the changes of resonance wavelengthes lambda 0 of the long-period fiber bragg gratings wrapped by the multiple steel sleeves with different radial lengths in the sleeve structure are monitored to realize nondestructive, long-term and quantitative monitoring of changes of the corrosion thickness of the measured reinforcing steel bar along with time, so that early warning of the corrosion state of the reinforcing steel bar is realized and the safety of a major engineering structure is guaranteed. Moreover, the sensor having a simple structure is easy to make; the monitoring process does not need complex test equipment; and the applicability is high.

The invention relates to an optimum mass spectrometry model and a preparation method thereof for detecting the feature protein of nasopharyngeal cancer, belonging to the field of mass spectrometry detection technique. The invention is characterized in that six up-regulated proteins and five lower-regulated proteins are screened from the blood serum to be used as the feature proteins; any two or more proteins of the eleven proteins are chosen so as to establish a blood serum feature protein mass spectrometry model of identification with two in a group for patients with nasopharyngeal cancer and normal people, and patients with benign nasopharyngeal cancer disease, lymphatic metastasis of nasopharyngeal cancer and remote metastasis of nasopharyngeal cancer according to the mass-charge ratio m / z of each protein peak and the critical peak average value of the protein; the preparation method of the invention provides a foundation for discovering new nasopharyngeal cancer biological marks. The method of the invention is better than any single detection method adopted currently for the detection of the nasopharyngeal cancer, and provides a non-invasive technique for the early detection and early treatment of the nasopharyngeal cancer, thus providing a new method for reducing the mortality of the nasopharyngeal cancer, improving the cure rate of the nasopharyngeal cancer and screening and examining the nasopharyngeal cancer for high-risk population further.

The invention relates to an optimum mass spectrometry model and a preparation method thereof for detecting the feature protein of renal cancer, belonging to the field of mass spectrometry detection technique. The invention is characterized in that seven up-regulated proteins and three lower-regulated proteins are screened from the blood serum to be used as the feature proteins; any two or more proteins of the ten proteins are chosen so as to establish a blood serum feature protein mass spectrometry model of identification with two in a group for patients with renal cancer and normal people, and patients with benign renal cancer disease, lymphatic metastasis of renal cancer and remote metastasis of renal cancer according to the mass-charge ratio m / z of each protein peak and the critical peak average value of the protein; the preparation method of the invention provides a foundation for discovering new renal cancer biological marks. The method of the invention is better than any single detection method adopted currently for the detection of the renal cancer, and provides a non-invasive technique for the early detection and early treatment of the renal cancer, thus providing a new method for reducing the mortality of the renal cancer, improving the cure rate of the renal cancer and screening and examining the renal cancer for high-risk population further.