87 results about "Characteristic relation" patented technology

The invention relates to a user identity identification method and system. Through basic information, comprising user ID, user name, Email, telephone number, computer IP and the like, formed by user registration, and carrying out extraction on website user behavior data, and by combining information, such as user ID, user name, Email, telephone number, Cookie, computer IP and the like, related in the behavior data, a user information relevance relationship between the two is established and an unique identification identity is given, unified identity identification of users in a B2B website at present can be carried out, identity characteristic relation is established, old and new users can be identified, and user behaviors can be effectively tracked, and thus a series of applications can be established for the users, and user experience is improved.

The invention discloses positioning and velocity measuring method and device for an underwater target in an unknow sound velocity environment. The positioning and velocity measuring method specifically includes: (1) placing transceiving duplexing array elements and the underwater target, and emitting a detect signal; (2) by the aid of the array elements, receiving and detecting echoes reflected back after reaching the target; (3) seeking real-time velocity speed of a detecting path; (4) seeking coordinates of the target in various dimensions, and integrating the coordinates to obtain a real-time three-dimensional coordinate of the target; (5) measuring velocity of the target according to doppler shift. Compared with an existing underwater sound positioning technology in which inaccurate sound velocity measurement results to larger positioning error, the positioning and velocity measuring method and device have the advantages that a theoretically feasible real-time sound velocity measuring method is provided by an algorithm on the basis of angle characteristic relations between the array elements and the target, the sound velocity in the target detecting path can be determined accurately in real time, and great significance to improvement of positioning accuracy of the underwater sound positioning technology is realized.

The invention discloses a method for correcting a synchronous phasor under the condition of frequency shift of voltage of a power grid, and a current signal. By a uniform approximation method in a fonctionelle, an expression is reasonably corrected, a formula is corrected by the same method in an amplitude-phase space, and a quantized correction expression is finally given. A calculated amount is greatly simplified by an amplitude-phase characteristic relation approximation ellipse. By the uniform approximation method, the correction formula of amplitude is solved, and a practical function expression of engineering is given. Compared with the conventional algorithm, the method mainly solves the problem of 0 / 0 data shift, which is caused by conventional amplitude correction and the problem of sudden change of phase angle, which is caused by discontinuity of a tan function. The research result has certain engineering application value.

A test system and a method used for testing the mechanical properties of a linear motor belong to the technical field mechanical property detection of linear motors. The system includes two parts of a data acquisition platform and a data processor, wherein the data acquisition platform includes a pressure transducer and a displacement transducer which are linked with the output end of the linear motor, as well as a data acquisition card which is connected with the pressure transducer for acquiring a pressure signal and also connected with the displacement transducer for synchronously acquiring a displacement signal. After the acquired signals are processed by the data processor, the relation curve between the speed and output force of the linear motor and relative output characteristics thereof are obtained. The system is simple in structure and highly efficient in acquiring the output force and displacement quantity of the linear motor, and directly and effectively reflects the characteristic relation between the push power and speed of the linear motor and the output characteristics thereof.

The invention puts forward a positioning method and a positioning system based on signal emitting device antenna direction correction. The positioning method comprises the following steps: S1, processing a signal emitted by a signal emitting device to a to-be-positioned point into basic positioning information; S2, calculating out the preliminary positioning location of the to-be-positioned point using a signal attenuation calculation model and a positioning algorithm based on a propagation model; S3, acquiring the attenuation characteristic of the signal emitting device through measurement, wherein the attenuation characteristic includes a plurality of pieces of constant-amplitude attenuation information, and each piece of constant-amplitude attenuation information records the propagation characteristic relation between angle and distance under the same attenuation signal intensity; and S4, correcting the preliminary positioning location according to the attenuation characteristic to realize accurate positioning. According to the invention, the directivity of a signal source propagation antenna is taken into full consideration, and the existing positioning result is corrected using a measured antenna radiation signal attenuation model instead of an ideal attenuation model, which greatly improves the positioning accuracy. The positioning method and the positioning system are especially suitable for indoor Wi-Fi positioning, and have a broad market application prospect.

The invention discloses a method for testing actual flow characteristics of a steam turbine valve. The method relates to testing contents, testing conditions, testing steps and specific methods. The testing steps comprise the following steps that firstly, characteristic relation tests between total steam turbine valve steam inlet adjustment valve instructions and steam inlet flow are carried out according to a working mode in order; secondly, actual flow characteristic tests of single steam inlet adjustment valve is carried out. The method is easy and convenient to adopt and practical, can accurately finish the actual flow characteristic tests of steam turbine steam inlet adjustment valves in the field in the technical process to acquire accurate flow characteristics, is helpful in finding out problems and safety hazards or potential problems and potential safety hazards in the thermal power generating unit active load control process, provides evidence for an active load control system of a power generating unit, and improves comprehensive performance of active load control of the unit, safe and economical operation of power grids and power plants and electric energy quality.

The invention provides an electrical equipment energy efficiency chaos analysis method based on massive measurement data, belonging to the technical field of electrical engineering, particularly relating to an electrical equipment energy efficiency chaos analysis method based on massive measurement data. The invention provides the electrical equipment energy efficiency chaos analysis method based on massive measurement data, an advanced measurement data analysis method and a test detection system are combined, the association relation between the use condition of user electrical equipment and user power consumption data is analyzed, thus the power consumption habit of a user and the load characteristic relations of different electrical equipment are obtained. The method comprises the steps of (1) using the membership degree for a fuzzy C-means clustering (FCM) to determine that the integrated load characteristic of the user belongs to which degree of clustering, dividing n industry users xi (i=1,2,,,n) into c fuzzy classes, and obtaining the clustering center of each class such that a class inner weighted error square sum function is minimized.

The invention discloses a method for suppressing low-frequency oscillation of high-speed rail based on model predictive current control, comprising the following steps: constructing an Electric Multiple Units network side rectifier AC-side voltage and current dynamic characteristic relation; getting a current prediction model under a d-q two-phase rotating coordinate system through decoupling by a second-order generalized integrator; making compensation for control calculation delay through a two-step prediction method; calculating the partial derivative with respect to voltage variation for a quality function, and getting a voltage variation value minimizing the quality function; and carrying out SPWM modulation on the control voltage to get a control pulse. The fast dynamic response characteristic and the harmonic suppression effect of control are improved. Moreover, the total harmonic distortion is low, the current distortion is low, the DC voltage overshoot is small, and the dynamic response is fast. The electrical low-frequency oscillation problem of the traction network EMU can be suppressed. When the external parameters of the system change in a small range, the train network system does not oscillate compared with the transient DC oscillation mode and the oscillation peak.

The invention discloses a method for matching a generalized Hough transform image based on local invariant geometrical characteristics to achieve the purpose of matching a target image with any rotating angle. The method is characterized by comprising the step of preprocessing a template image and the step of matching the target image through the processed result of the template image. The step of processing the template image comprises the step of extracting all edge points of the image and establishing an edge point matching characteristic relation. When the matching process is carried out on the target image, the edge points of the target image are extracted, the extracted image is matched through the established edge point matching characteristic relation, accordingly, the matching position points and the corresponding rotation angles are acquired, and the target image is matched. A traditional Hough transform is improved, an improved reference table is established, the target image rotated by any angles can be matched, and a very high matching speed and matching precision are achieved.

The invention discloses a method for optimizing the main steam pressure of a large steam turbine set, which belongs to the field of learning, modeling and optimizing algorithms of machines. The method comprises the following steps of: firstly, learning and modeling a heat loss characteristic sample set obtained by a machine set performance test by a support vector machine method; obtaining a parameter relation of machine set heat loss, main steam pressure, main steam temperature, ambient temperature and a machine set load; then learning a subset in the sample set, establishing a heat loss model and carrying out increment analysis; establishing a steam turbine set pressure optimizing model and optimizing and solving the steam turbine set pressure optimizing model by a genetic algorithm to obtain main steam pressure optimizing value and curve and an optimizing data set; and finally, carrying out secondary modeling on the optimizing data set to obtain a pressure optimizing characteristic relation. The method gives an optimized main steam pressure set value according to the current running condition of the machine set, greatly amplifies the optimizing range and is particularly beneficial to the energy saving and the consumption reduction of the large power station steam turbine set.

The invention discloses a gas concentration measuring method based on spectral absorptivity second harmonics feature extraction. The method disclosed by the invention realizes calculation of integralabsorbance by virtue of harmonic characteristics by building a spectral absorptivity second harmonics peak height-peak width characteristic relation applicable to any modulation coefficient and considering a Voith line type, thus gas parameter information is obtained; meanwhile, in an implementation process of the method, a logarithm processing technology is adopted, influence of residual amplitude modulation on harmonic signal distortion is directly eliminated, and measurement accuracy is improved; the measuring method disclosed by the invention does not need to perform complex least-squaresiteration fitting calculation and only needs to perform filtering processing once, thus requirements on a hardware system are reduced; information of feature points of a waveform still can be relatively accurately extracted when a complete harmonic signal can not be obtained, and a lower measurement limit is lower; and excessive parameters such as a self-broadening coefficient, collision broadening coefficients of various other components and a temperature-dependent index in a database do not need to be utilized, dependence on database parameters is reduced, and application range is wider.

The invention relates to a switch reluctance machine (SRM) torque pulse control method and system of a torque-current neutral network model. According to the method, a torque-current conversion relation is obtained by an inductance model of an SRM, each phase control current is obtained by a current allocation function, so that torque pulse is prevented. According to a non-linear characteristic relation between the SRM torque and the current, a function of describing basic change rule of an SRM current is used as an implication layer simulation function, a torque-current neutral network modelof describing the strong non-linear characteristic of the SRM is designed, the total reference current corresponding to torque is calculated by self-learning of the torque-current neutral network model, a reference current corresponding to each phase is obtained by the current allocation function, and the SRM is controlled. A program storage device of a system microprocessor designed by the methodis provided with each program module for executing the method, each sensor signal on the SRM is connected to the microprocessor, and the SRM is connected and controlled by a power converter. By the method, effective control on torque pulse of the SRM is achieved.

The invention relates to a calibration method for SF6 gas density relay. An absolute pressure transducer and / or a relative pressure transducer can be adopted for measuring an absolute pressure relay and / or a relative pressure relay, and then a pressure value when the SF6gas density relay acts is obtained; according to the type of the relay to be tested, namely the absolute pressure relay or the relative pressure relay, the type of the transducer used for measurement, namely the absolute pressure transducer or the relative pressure transducer, the temperature value during measurement, and the pressure-temperature characteristic relation of the SF6 gas, a corresponding pressure value at 20 DEG C is obtained after data processing, and thus the accurate test on the performance of the SF6 gas density relay is completed. The calibration method for SF6 gas density relay provided by the invention can calibrate SF6 gas density relays of various measurement philosophies under various circumstances without being affected by located atmosphere pressure.

The invention discloses a synchronous acquisition device and method of an atom and molecular spectrum. The method comprises the following steps: striking the surface of a to-be-detected sample repeatedly by focused energy of a laser device, stimulating the to-be-detected sample to be at a plasma state, and collecting an atom spectrum transmitted by the to-be-detected sample at the plasma state by an optical fiber collector via a visible spectrograph; striking the surface of the to-be-detected sample repeatedly by the focused energy of the laser device, and collecting an infrared spectrum transmitted externally by the surface of the to-be-detected sample by an infrared optical fiber collector via the visible spectrograph so as to obtain a molecule spectrum; transmitting the molecular spectrum to a signal collecting control system by the atom spectrum and the infrared spectrograph via the visible spectrograph; and matching the atom spectrum and the molecular spectrum by the signal collecting control system so as to obtain the corresponding relationship between the atom spectral line and a functional group. The method can be used for obtaining the molecule and atom spectrum with the same size synchronously within a short time, and achieving the correlation of the characteristic relation of the atom spectrum and the molecular spectrum.

The invention discloses an internal temperature on-line monitoring method for SF6 high-voltage electrical equipment. The method comprises the following steps: measuring the first pressure value and the first temperature value of gas inside SF6 high-voltage electrical equipment, and obtaining the density of gas inside the SF6 high-voltage electrical equipment according to the first pressure value and the first temperature value; measuring the second pressure value of gas inside the SF6 high-voltage electrical equipment, and obtaining the internal temperature of the SF6 high-voltage electrical equipment. Through continuous monitoring and system modification, the accurate density of gas inside the SF6 high-voltage electrical equipment is obtained in time, and data processing is conducted by utilization of the SF6 gas pressure-temperature characteristic relation so as to obtain the corresponding SF6 high-voltage electrical equipment internal temperature value. The invention further provides an SF6 high-voltage electrical equipment internal temperature on-line monitoring device and system, real-time and accurate measurement on the internal temperature and / or density of the electrical equipment is realized, the detection cost is reduced, and the suitability for engineering application is higher.

The invention discloses a method for configuring recommend information in a webpage and an index service. The method includes: receiving a page request from a front desk server and acquiring matched recommend information from a data source through the page request; for acquiring calculating correlation of the recommend information: determining a data description type of the recommend information, determining a trigger identify through the data description type and reading characteristics and characteristic value from a corresponding characteristic relation table through the trigger identify; calculating the characteristic value of the characteristics in the page request and the characteristic value of the characteristics corresponding to the characteristic relation table, taking a calculating result as the final characteristic value of the corresponding characteristics, and calculating the correlation of the corresponding recommend information through the final characteristic value of the acquired characteristics; ranking the recommend information according to high-to-low sequence of the correlation, extracting the recommend information with the set number from the highest value of the correlation, feeding back the recommending information to the front desk service, and configuring the same into the webpage. By the method, the accuracy in configuring the recommend information in the webpage can be improved.

The invention embodiment provides an oil reservoir water content and oil recovery percentage relation determining method and device; the method comprises the following steps: building an oil recovery percentage and water recovery percentage relation of a target oil reservoir according to a Tong A-type water drive characteristic relation; determining the target oil reservoir water content and oil recovery percentage relation according to the oil recovery percentage and water recovery percentage relation, wherein the water content and oil recovery percentage relation comprises the water content history initial value and oil recovery percentage history initial value of the target oil reservoir. The novel method can fuse the history production data of the target oil reservoir into the oil reservoir water content and oil recovery percentage relation, thus further complying with real production conditions; the oil reservoir water content and oil recovery percentage relation determined by the method can be applied to accurately analyze low penetration oil reservoir water flooding exploitation effect, and to accurately predict oil reservoir recovery efficiency parameters.

The invention relates to a fault diagnosis rule extraction method, in particular to an imperfection fault diagnosis rule extraction method based on the quantitative characteristic relation. The method solves the problem that according to an existing imperfection fault diagnosis rule extraction method, fault diagnosis rules cannot be extracted from a decision table containing various unknown attribute values, solves the problems that according to the existing imperfection diagnosis rule extraction method, similarity degrees among examples are not considered, and the similarity relation among the examples is not measured, and solves the problem that original information will change due to an existing manual data filling process. The imperfection diagnosis rule extraction method based on the quantitative characteristic relation comprises the steps of (1) preprocessing original imperfection fault diagnosis data, (2) determining the type of an unknown attribute value, (3) analyzing an imperfection fault diagnosis decision table, (4) conducting reduction, and (5) extracting fault diagnosis rules. The imperfection fault diagnosis rule extraction method is applied to the field of fault diagnosis rule extraction.

An SF6 gas density relay check meter comprises a gas source supplier, a pressure transducer, a temperature transducer and a computer data processing system, wherein the gas source supplier capable of adjusting pressure comprises a pressure adjusting cylinder, a piston, an adjusting bar and a hand wheel, the hand wheel drives the adjusting bar which consequently drives the piston to move in the pressure adjusting cylinder, thereby realizing gas source pressure adjustment in the pressure adjusting cylinder; according to the type of the relay to be tested, the type of the transducer used for measurement, the temperature value during measurement and the pressure-temperature characteristic relation of the SF6 gas, the computer data processing system carries out data processing and obtains a corresponding pressure value at 20 DEG C, and thus the accurate test on the performance of the SF6 gas density relay is completed. The SF6 gas density relay check meter provided by the invention can calibrate SF6 gas density relays of various measurement philosophies under various circumstances without being affected by located atmosphere pressure.

The invention provides a three-dimensional reconstruction system and reconstruction method based on PAL cameras. The reconstruction system comprises two industrial cameras respectively provided with a PAL lens, the two PAL lenses are arranged in a perpendicular manner, and the two industrial cameras are connected with a computer through USB data wires. The three-dimensional reconstruction method comprises the following steps of: arranging the two industrial cameras respectively provided with one PAL lens in the perpendicular manner and connecting the two industrial cameras with the computer; b, using the industrial cameras to collect image data, and transmitting the image data to the computer; c, carrying out processing and calculation on the image data, and obtaining optical characteristic relations of the cameras; d, correcting image distortion based on the optical characteristic relations of the cameras; e, utilizing a dynamic programming algorithm to match two images obtained by shooting; f, converting points of a panoramic image in a cylindrical coordinate system into points in a three-dimensional coordinate system; and g, drawing a three-dimensional scene to be reconstructed. The three-dimensional reconstruction system and reconstruction method have the advantages that the structure is simple, the operation speed is high, and the system and the method are applicable to the reconstruction of a large-range scene.

A workpoint adjusting method of straightening exocoel laser is provided, the processes are that: firstly, the output light efficiency of the straightening exocoel laser is nominal output efficiency; secondly, the temperature of a tube core is adjusted to make the output light wavelength reach the nominal wavelength; thirdly, the corresponding adjustment quantity value of the tube core when reaching the nominal wavelength in the previous step; fourthly, testing process; fifthly, if the temperature of middle tube core is correct, when reducing the temperature of the tube core in single direction continuously, the changes of the wavelength is linetype, if the temperature of the tube core is correct, otherwise, incorrect; sixthly, if the temperature of the tube core is correct, the recording value is recovered; if incorrect, returning to the second process; seventhly, the extinction ratio of the laser is adjusted. An adjusting device which is composed of a straightening exocoel laser, a laser drive circuit, an automatic control circuit and an automatic efficiency control circuit is provided. Aiming to the characteristic relation between the temperature of the tube core and the wavelength of the straightening exocoel laser, the adjusting processes are provided, therefore ensuring the transmission performance and the adaptation on light transmission system.

The invention discloses a probability statistics-based method for modeling generalized node characteristics. The method comprises the steps of performing uniformly-spaced sampling on annual data of the voltage and active power at a root bus which is directly connected with a fan; performing compromised segmentation on active power data of annual root bus; performing numerical statement on probability distribution of the active power data of the annual root bus of a wind electric field; extracting a probability characteristic relation expression under each power segment by using a nerve network algorithm; establishing a final node characteristic model of the wind electric field; evaluating the fitting effect of each power segment and the fitting effect of an overall sample respectively. The method disclosed by the invention covers an annual sample rule and does not need to correct the model frequently, so that the method is superior to the conventional method in the aspects of self-description capability and generalization capability, and trend results of all power scenes under wind power fluctuation can be solved according to the segment probability model so as to provide a theoretical guidance for researching probability stability calculation, risk assessment, economic dispatch, wind power absorptive capability and the like.

The invention discloses an on-line measurement method for the pressure drop ratio of an adjusting valve. The method comprises the following steps of: (1) obtaining a new standard working flow characteristic relation of the adjusting valve at different pressure drop ratios by taking a point with opening of h0 as a datum point according to the working flow characteristic functional expression of the adjusting valve, wherein h0 meets the requirement that h0 is more than 0 and less than 1.0; (2) selecting a measurement point h from a relative travel of the adjusting valve when the adjusting valve runs, wherein the measurement point h meets the requirement that h is more than 0 and less than 1.0 and is not equal to h0; obtaining the flow corresponding to the datum point and the flow corresponding to the measurement point; and further obtaining the working flow characteristic function value of the measurement point; and (3) in the new standard working flow characteristic relation, taking the working flow characteristic relation closest to the crossing point of the relative travel of the measurement point and the working flow characteristic function value of the measurement point as the target working flow characteristic relation, wherein the pressure drop ratio corresponding to the target working flow characteristic relation is the actual pressure drop ratio of the adjusting valve.

The invention relates to a method for automatically testing and recording a rated value for an SF6 gas density relay and includes a checking apparatus. The checking apparatus includes a gas source supplying mechanism with adjustable pressure, at least one pressure sensor, a temperature sensor, a computer data processing system and a display screen. The computer data processing system is provided with a relay action signal input port. The method includes the following steps: step 1, the indicating value of a test product is observed according to a pointer of the test product and the pressure is regulated just to a rated value of the test product, namely the pointer of the test product just points at the rated value Pe; step 2, a command key is tested according to the rated value; the checking apparatus automatically records a pressure value P and a temperature value T of the current pressure sensor and the temperature sensor; step 3, corresponding pressure value Pe test is converted automatically at 20 DEG C according to the pressure-temperature characteristic relation of the SF6 gas; step 4, the checking apparatus automatically carries out correcting on the tested Pe test according to the linear relation of the pressure sensor and the temperature sensor and stores the test result.

The invention relates to an extracting method for gas sensor output characteristic and a gas concentration measuring device using the extracting method and a method thereof, comprising: process of respectively measuring output voltages of two ends of load resistor corresponding to internal resistance of each gas sensor and each gas concentration, selecting a maximal voltage regulation from calculated output voltage regulation changing along time, in order to extract gas sensor output characteristic data; process of obtaining a characteristic relation formula among the gas concentration, the internal resistance of gas sensor and the maximal voltage regulation via using obtained gas sensor output characteristic data; process of using characteristic relation formula of the maximal voltage regulation to measure gas concentration. The output characteristic of the gas sensor according to the invention is relative to the gas concentration and internal resistance of the gas sensor, thus, the invention can be used for function evaluation for gas concentration measuring device and gas sensor.

The invention discloses a user-read community application data processing method. The user-read community application data processing method includes establishing a network community by various users in a social network; capturing reading behavior information of the users and interactive learning behavior information among other users, establishing data structure models of reading behavior events, and storing the data structure models of the reading behavior events; excavating and analyzing involvement degree of the reading behavior events of the users in the network community according to the data structure models. By the user-read community application data processing method, data elements are connected and organized according to logics to establish the data models of related characteristic relations of the users, reading behaviors, the events, time and states, and more valuable data information is recommended through an involvement degree algorithm and the involvement degree.

The invention discloses a method of testing the frequency static characteristic coefficient of a grid under the condition of large non-grid disturbance, comprising the following steps: (1) exiting from the AGC of a grid-connected unit in a grid and other secondary frequency modulation control operations; (2) selecting a test unit serving as grid power disturbance in the grid: gradually increasing / decreasing the output of the test unit, and after each increase or decrease in output, stabilizing the output for a period of time to form a new steady-state frequency of the grid through adjustment; and (3) after the test, analyzing the total output and steady-state frequency of steady operation condition points of the grid in the test process, drawing a relational graph of the total output of the grid and the steady-state frequency of the grid, and getting a frequency static characteristic relation curve of the grid in different frequency bands through data fitting, wherein the slope of the curve is the measured frequency static characteristic coefficient of the grid. The problem that the existing grid frequency static characteristic coefficient test method is easily affected by secondary frequency modulation due to high restriction and uncertainness or is of high test difficulty and high security risk is solved.

A method for extracting data association characteristic value mode or template comprises the steps of I, carrying out language determination and preprocessing on a data resource, tagging parts of speech, and tagging nouns and verbs of each sentence, performing grammatical analysis, and tagging a subject, a predicate and an object of each sentence; II, extracting a word group which is repeatedly tagged as the subject and the noun, a word group which is repeatedly tagged as the predicate and the verb and a word group which is repeatedly tagged as the object and the noun in a sentence set, and respectively obtaining a noun set as the subject, a verb set as the predicate and the noun set as the object, and a correlation characteristic relation corresponding to the subject-predicate / predicate-subject in the sentence; and III, respectively counting the accumulative word frequency of the subject nouns, the predicate verbs and the subject nouns, tagging the subject nouns, the predicate verbs and the subject nouns to measure weight characteristic value size of the subject noun set to the predicate verb set / the predicate verb set to the object noun word group with association relation, wherein the ratio of nouns to verbs is approximately equal to the ratio of word frequency n:v, and the ratio of verbs to nouns is approximately equal to the ratio of word frequency v:2n.

The invention relates to a pressure-blood flow characteristic relation measuring instrument for soles at standing positions and sitting postures. The pressure-blood flow characteristic relation measuring instrument comprises a support platform, a hand rod, a load bearing table, a seat table, a dynamic pressure loading device, laser speckle blood flow measuring equipment and a control and computation unit. The support platform is a cuboid panel supported by cuboid columns; the hand rod, the load bearing table and the seat table are respectively sequentially mounted on the upper side of the support platform; the dynamic pressure loading device and the laser speckle blood flow measuring equipment are fixed to the lower side of the support platform; the dynamic pressure loading device comprises a cylindrical support rotary arm, a telescopic rod and a pressure sensor and is used for applying pressures to sole tissues of test persons; the laser speckle blood flow measuring equipment comprises a support rotary arm and a laser probe and is used for measuring the blood flow volumes of the sole tissues of the test persons; the applied pressures can be controlled by the control and computation unit, measured blood flow volume data can be recorded by the control and computation unit, and pressure-blood flow characteristic relations can be computed and displayed by the control and computation unit.

The invention discloses an industrial soft measurement method based on multiple NPE (neighborhood preserving embedding) regression models. The method aims to comprehensively mine the local neighboring characteristic relation of data and establish multiple regression models to realize on-line soft measurement of product quality. Specifically, the method comprises steps as follows: firstly, distance neighborhood, time neighborhood and angle neighborhood are searched for each sample point of input data; then, a distance NPE regression model, a time NPE regression model and an angle NPE regression model are established correspondingly; next, an estimation value for output by each NPE regression model is taken as input again, and regression models between the estimation values and the output are established again by use of a partial least-squares algorithm; finally, the established regression models are used for on-line soft measurement. The method is a preferred soft measurement implementation scheme due to the fact that more potential useful information can be more comprehensively mined and the generalization ability of the soft measurement models is guaranteed by use of the multiple regression models during soft measurement.