RussianPatents.com

Method for statistical prognosis of equipment characteristic

IPC classes for russian patent Method for statistical prognosis of equipment characteristic (RU 2261473):

G06F17 - Digital computing or data processing equipment or methods, specially adapted for specific functions

Another patents in same IPC classes:

Method for preliminary and/or current indication of cost of transfer of inter-network or operative data / 2260844
Method, for transferring large quantities of data, offers insertion of additional provider-offered protocol element, which can contain at least a volume of data of planned transfer, and also other cost criterions, while protocol element as it is recognized by relay nodes taking part in transfer (routers) and is summed with appropriate share of own cost of transfer, ad finally protocol element 9 is estimated at user personal computer, for example in browser, and appropriate cost of planned transfer sis indicated, after that user can initiate transfer or performed automatic initiation of transfer in more profitable time, insertion of protocol element is advisable for all planned data transfers, to protect from meaningless receipt of pages with multiple images.

System for controlling electronic circulation of documents in information-marketing center / 2260843
System has first and second registers, operation mode setting block, device for identifying base address of confirmed requests, device for modified base address of confirmed requests, device for identification of base address of clients, block for forming recording control signals and data reading, decoder, device for identification of base address of user notifications, device for identification of base address of contest requests, block for commutation of channels for data dispensing and OR elements of group.

Statistical analyzer of quality and recording of electric power flow / 2260842
Device has current input clamp and mating input clamp, current counter with inbuilt pulse sensor, converter of alternating voltage to direct voltage, analog=digital converter, register, digital memory block, pulse counter, selection pulse generator, second and first D-triggers, first, second and third and fourth AND elements, SR-trigger, OR element, clock pulse generator, pulse distributor.

Method for determining number of targets in a group / 2260196
Method includes analog-digital conversion of reflected from targets and received signal, calculating complex correlation sums of selection of received signal and support quadrature signals with values of parameter of resolution of support signal, taken on e even mesh, maximal by width intervals of values of resolution parameter, inside which all modules of correlation sums exceed threshold of detection, decision is taken about match of each local maximum to one target in the ranges, in which number of local maximums is more than one, width of range is calculated, inside which one local maximum is placed, decision about match of one local maximum to two targets is taken in case, if width of range is more than threshold width, in opposite case minimal non-square non-match of counts of complex correlation sums and count s of standard correlation sums of signal of one target are calculated, and decision is taken about match of local maximum inside range of one target in case, if non-match is less than non-match threshold, and two targets - in opposite case.

System for determining cost of project / 2259593
System for estimating cost of project, realized as computer software, has type module for receiving user input, determining type of project, and for forming requirements to project, project module receives requirements for project and compiles a project, including given data, operating characteristics data receives data from calculations and generates parameters of working characteristics, cost module receives data and determines cost, client cost module takes in working characteristics and determines cost of project for client.

Method and system for computerized advertisement / 2259588
Method includes method for modification of image, generated by software application for presenting on display of computer system, which controls application in operating system with graphic user interface; method includes: receiving by computer system of executable code from outside, structure of which code depends on which other code is already present in this computer system, creation of multimedia animated object on basis of executable code received by computer system for insertion of said object into image, produced by said software application, while insertion of animated multimedia object is performed in such a way, that object is in form of changing image, appearing onscreen in intrusive and unpredictable form for computer system user.

Method for controlling purchases, payments and credits / 2259587
After receiving command from mobile communication device through communication network, communication is stopped and for communication between terminal, present at consumer side, and module, mounted in a shop, local radio communication is used. During purchase a unique identifier is created, after that registration list is formed. Module receives input data received from barcode reader, included in user terminal composition. These data include information about each product, then registration list is renewed with use of data, associated with products. These data can also be displayed at terminal display. On basis of renewed registration list and series identifier, payment or credit transaction is performed.

System for assisting in processing of auction and performing of auction / 2259586
System has computer, which receives information about process of auction, characterizing auction, performed by first participant of auction, and information about quoting of auction, characterizing performed auction by second participant, database of characteristics of auction participant, made with possible querying by computer; characteristics of auction participant characterize acceptable parameters of auction for each auction participant. Computer executes a program for comparing information about performing of auction to information about quoting of auction, and to determine presence of coincidence, if information about performing of auction and information about quoting of auction corresponds to each other within limits of acceptable auction parameters, presented in characteristics of auction participant for first participant and second participant.

Method and system for computerized advertising / 2259585
Method includes stages for inputting to user computer system from outside relatively to this signal system, which forms multimedia animated sign in image, formed under control of operation system, after displaying of image, while multimedia sign is inserted in such a way, that it appears on screen in intrusive way in position, in moment of time or with dimension, which can not be determined by user of computer by viewing image prior to inputting of said mark, while the mark is fully out of user control.

Help system for information-marketing center / 2259584
System has first and second registers, three addresses selection devices, synchronization channels commutator, database records addresses forming block, data refresh files receipt block, refreshed database records identification block, data output block, AND element.

Method for formation and check-out of payment document / 2244957
The information meaningful for the payment document is introduced in the computer of the financial settlements and check-out center, the payment document is formed in the form a text and the first dot-and-dash code line and introduced in the electronic data base, the document is displayed for payment to the payer, the payer introduces the information on the quantity of consumed resources and the sum of payments to the document according to the acting tariff rates, these data are introduced in the cash register of the payment reception center with the date of payment, types and sums of payments, these data and the second dot-and-dash code line with these data on the document are represented by means of the cash register, it is sent to the financial settlements and check-out center, the first and second dot-and-dash code lines are read out, the information is compared with the electronic base, entered together with the information on reception of the payment in its electronic data base.

Electronic message board and mail server / 2245577
Electronic message board is provided with database in form of several known words, which are selected in specific order, while each word is connected to respective URI. Message text from user computer is checked using a plurality of known words. When message text does not include a known word of plurality of known words, message is placed at electronic board. Each known word is found in text, known in text is converted to hypertext format with URI connected to word, as destination of link, and message is placed at message board.

Method and system for providing access to data in network with use of message pseudonym functions, having shadow back call functions / 2245578
Method includes assignment of simplified network address, recording URL and converting numbers into storage system with net access, inputting assigned number into computer, transferring inputted number to storage system, converting number to URL, receiving page matching URL, and displaying it. Method for use in operation systems for message transfer include intercepting system level messages to certain objects and forming pseudonym messages during that. Systems realize said methods.

Parallel search and replace system / 2245579
System has entries memory block, words memory block, control block, substitutions block, n blocks for searching and replacing.

Method of measuring speed of motion of pedestrian before run-over of transportation vehicle / 2246117
Method can be used for criminal and official inquires of road accidents. Method is based upon measurement of speed of pedestrian and calculation its arithmetical mean. Method differs from known ones, as speed of motion is measured experimentally 10 to 30 times with three different pedestrians having like age and physical condition as victim of run-over. Results are processed as small sample by using central deviations and those deviations are used to determine average meaning of speed of motion, standard deviation, error and truth of the average mean. Upon finding truth of average mean the necessary number of trials is calculated which number has to be compared with real number of trials. Additional trials are conducted if necessary. Factor of truth of experimental data is calculated from speeds of motion of pedestrians taking part in experiment. Probability and factor of confidence is determined accordingly to speed of motion of injured person and speeds of motion of pedestrians involved into experiment, as well as according to truth of preset limit values of this parameter. If values of preset factors correspond to legitimate values or limits admitted for investigation of road accidents, statistically true minimal and maximal values of speed of motion of injured pedestrian are calculated on the base of normal distribution law by means of subtraction the speed from its average value and addition of product of factor of confidence with standard deviation. Limit values of speed of motion of injured pedestrian are presented for forensic examination to make calculations determining availability or lack of availability of prevention of run-over. For this purpose the statistically truthful minimal and maximal values of speed of motion of injured pedestrian should be calculated in relation to accessible values or limits of probability which is higher than 0,95 and if confidence with speed of motion of injured pedestrian and pedestrians involved into experiment correspond to each other. Preset precision of pedestrian's speed of motion should be within limits of +-0,5 km/hour.

System for data transfer for governmental population recording system / 2246130
System has nine registers, four address selectors, triggers, AND elements, OR elements and delay elements.

Device for modeling a multimode system / 2246131
Device has control trigger, random pulse generators, block for forming program of functioning of modeled multimode system, working modes and technological mode blocks, operation time counters, random pulses generators, OR block, orders counters.

Method and device for fast computing of discontinuous wavelet-conversion of signal with random discretization step of scale coefficients / 2246132
Invention is based on representation of mother wavelet in spectral plane with following logarithmical scaling of mother wavelet.

FIELD: equipment characteristics prognosis technologies.

SUBSTANCE: device provides forming of statistical model for prognosis of characteristics of equipment. Device gets input data, in form of equipment parameter, which includes multiple values, appropriate for parameter. Input data is inputted into model and data set is formed, appropriate for model response to input data, equations system if formed being a model of equipment characteristic, received data is statistically processed for forming probability image of equipment characteristic.

EFFECT: higher efficiency.

6 cl, 4 dwg

The level of technology

The invention relates to a method for predicting the characteristics of the equipment and, in particular, to the use of statistical methods, and models to predict the expected distribution characteristics of the equipment as a function of the variability of the input data. One method for predicting the characteristics of the equipment based on the application of the model of point definitions of input values. The result is a series of point definitions representing a single value for a set of input values. Point definitions used to model equipment, implement, for example, with the aid of a computer. The model generates a single-point response representing the predicted characteristics of equipment.

The disadvantage of this method for predicting the characteristics is that the actual equipment characteristic is a more precise set of values based on a set of input values. Use this method to get many responses would be voluminous task. This task would include statistically variable input variable input in the model, the operation model, the entry point of the response and the subsequent repetition of the process for the next aggregate the input data. As you can imagine, to complete this RA is the notes with an acceptable resolution would have to spend a lot of time and effort.

The invention

An exemplary implementation of the invention is directed to a method for predicting the characteristics of the equipment. Receive input data representing a parameter of the equipment. The input data include a set of values corresponding to the parameter of the equipment. The input data is introduced into the model to form a set of data corresponding to the response of the model to the input data. Derive the system of equations, representing the totality of the data. The system of equations is statistically processed to generate the probabilistic representation of the characteristics of the equipment.

Brief description of drawings

Refer now to the drawings, in which similar elements have the same numerical designation on multiple drawings, in which:

figure 1 depicts a block diagram of the method for predicting the characteristics of the equipment, in an exemplary implementation of the invention;

figure 2 depicts a block diagram of a method for predicting the characteristics of the equipment in an exemplary implementation of the invention;

figure 3 illustrates the probabilistic response when using the set of input data;

figure 4 illustrates the probabilistic response using an alternative set of input data.

Detailed description of the invention

Figure 1 shows the structural diagram illustrating the procedure of predicting the characteristics of the equipment in an exemplary implementation of the invention. As shown in figure 1, the input data is introduced into the scheme of experiments (DoE), which runs through computer software and used to predict the characteristics of the equipment, usually called the model 22.

In the exemplary implementation shown in figure 1, the model is a thermodynamic model that represents a characteristic of a steam turbine. It is obvious that the invention may be applicable to a variety of models and is not limited to steam turbines. The term equipment refers to different objects, including vehicles (e.g., turbines) and articles of manufacture (for example, a turbine blade). The input data 20 represent the distribution of input values, but not the only input variable. The distribution of input values corresponds to the equipment, such as characteristics of the equipment (for example, dimensional data) or input equipment (e.g., fuel consumption). Model 22 includes an expected set of input values and the result of the model is a large set of data that describes the multi-dimensional surface representing the characteristic of the equipment.

A set of data created by the model represented by the system of equations 24, shown in the form of the function f (x), by fitting a series of equations to sovocool the data. Essentially, these equations are used to describe the model output 22 (e.g., machine code) in algebraic expressions, so you can easily use statistical software and spreadsheets. Once the machine code is converted to a system of equations 24, builds a model 25, based on equations 24, by location of equations 24 in the spreadsheet. After building the model 25 is used the statistical program 26 (for example, analysis by Monte-Carlo) to complete the process. Statistical program 26 provides a description of each input parameter in the form of a statistical distribution and control of any relevant output variable. Performing statistical program 26 provides for the adoption of a statistically correct values for these input distributions, holds value composed of equations and traces the resulting distribution on the output variables. Modeling is usually done for 10000 iterations and response with high resolution.

The execution result of the statistical program 26 is a probabilistic response 28 in the form of a distribution or set of output values and statistics corresponding to the number of output values. Shown as an example in figure 3 and 4 is STATISTICA includes the average value, the median, standard deviation and variance. Probabilistic response 28 provides a powerful tool for optimizing the design characteristics. The interaction and influence between input parameters and output parameters can be easily defined, so you can find the true optimal design. By using distributions of the input data 20, and not individual points, you can understand what the tolerances on the input variables to achieve the desired output.

Figure 2 shows the block diagram of the process of predicting the characteristics of the equipment in accordance with an exemplary implementation of the invention. At operation 30 receives input data representing the distribution of input values. At operation 32, the input data is included in the model equipment. As noted above, the model can have many forms, such as the simulation of the operation of the machine or the modeling characteristics of the object. When the model operation 32 creates a set of data, and for operations 34 shows the system of equations for the approximation of data sets. Equations derived at operation 34, are used to create the model 36 and operations 38 aggregate equations. Statistical processing at operation 38 leads to probabilistic response, which includes the allocation of the giving and statistics for each output value.

Let us now describe the application of an exemplary embodiment of the invention to a steam turbine. Was performed in the process shown in figure 1 and 2, with the General model of a steam turbine and here is the results. For this example was used seven input data 20 (the gap between the guide and the rotor blades, the gap of the shaft seal, square holes for turbine wheel, the thickness of the trailing edge of the nozzle, the area of the throat of the nozzle, the minimum cross-section of the blade and the coefficient of turbulence (half-DoE 22) to create aggregate data used for derivation of the equations 24. Also for this study were simulated input data 20 as having a normal distribution of values with limits ±3σ and ±1σ. As described below with reference to figure 3 and figure 4, the use of two different limits for the input data illustrates the importance of the impact of changes in input data on the distribution of the output.

Figure 3 and 4 shows a frequency histogram generated in accordance with the present invention for the output value (labeled uint32_t) for the input distributions restricted to specified limits ±3σ and ±1σ respectively. 3 and 4 illustrate that the probabilistic response 28 is in the form of the distribution. When using the present invention, the result is a distribution, not detachedly response. In the present invention are actual known distribution of input values to obtain the expected distributions of the projected values.

Creating probabilistic response in the form of distribution facilitates the understanding of the effects of changes in the input parameter. Figure 3 shows the distribution with a standard deviation of 0.11, while in figure 4 the standard deviation is increased to 0.5. This change in variation is important and usually not accounted for, using the above-described single-point method. In addition, the present invention takes into account the variation of the distribution of individual parameter to assess the benefits of process improvement.

As noted above, the invention may be applicable to other types of equipment. For example, the model can provide a medical clamp, and the input data can represent the statistical distribution of the sizes of the clamp and the output of the probabilistic response may represent a voltage clamp. The present invention will allow the user to change the manufacturing tolerances on the input data and see the impact on the statistical distribution of the voltage clamp.

The present invention can be implemented in the form performed using computer methods and devices for implementing these methods. The present invention can be also R is alisoun in the form of machine code, contains commands that are placed on physical media, such as floppy disks, CD-ROMs, hard drives, or any other machine-readable storage medium, when loaded into the computer's machine code and executes it, the computer becomes a device for carrying out the invention. The invention can also be implemented in the form of machine code, for example, or stored in a storage medium, loaded into and/or executed by a computer or transmitted through some medium, such as air line or cable, through an optical fiber or via electromagnetic radiation, when loaded into the computer's machine code and executing it by the computer, the computer becomes a device for carrying out the invention. When implemented on a universal microprocessor segments of machine code form the configuration of the microprocessor to create specific logic circuits.

The invention provides probabilistic response with high resolution (compared to single-point answer) and reduces the amount of time required to complete the process. Analysis input distributions in contrast to the entry point provides more optimized calculation and appreciation is nnow resistance to changes in components. Thus, the invention leads to a more thorough analysis of the system, with the result that he becomes more accurate and complete.

While the invention has been described with reference to a preferred implementation, specialists in the art should understand what can be done various changes and its elements can be replaced by equivalents within the scope of the invention. Additionally, there may be proposed numerous modifications to adapt a particular situation or material to the idea of the invention without going beyond its scope. Therefore, it is assumed that the invention is not limited to a particular implementation, is presented as the best way to implement this invention, but that the invention will include all implementation within the scope of the invention covered by the present claims.

1. The device for implementing the method for predicting the characteristics of equipment such as a steam turbine or a medical clamp, the method encoded in the form of a machine readable code on the recording medium, and when loading the recording media in the above-mentioned device and performing the said program code mentioned device implements the following operations: receive (30) of the input data representing the parameter of the equipment is being transported, moreover, the input data include a set of values corresponding to the parameter of the equipment; enter (32) of the input data in the model, representing a steam turbine or a medical clamp, and form a set of data corresponding to the response of the model to the input data, and the above-mentioned data set describes a set of data representing characteristics of the equipment, derive (34) the system of equations representing the said set of data is statistically processed (38) the above system of equations to generate the probabilistic representation of the characteristics of the equipment, create a model (25) in the spreadsheet in response to the above system of equations

moreover, the above-mentioned stage aggregation perform the above mentioned model in the spreadsheet.

2. The device according to claim 1, characterized in that when deriving the system equations are approximated equation to the data set.

3. The device according to claim 1, characterized in that, when aggregated implementing the program of Monte Carlo.

4. The device according to claim 1, characterized in that the said set value limit specified limit.

5. The device according to claim 1, wherein said probabilistic representation of the hardware characteristics of yavlyaetsyasredstvom output values.

6. The device under item 5, wherein said probabilistic representation of the characteristics of the equipment includes statistics corresponding to the above distribution.