WO2021104216A1 - Method and device for evaluating device model trend similarity - Google Patents

Abstract

A method and device for evaluating a device model trend similarity. The method comprises: performing segmentation processing on an obtained reference value and an obtained simulation value of a device model to obtain a first time sequence and a second time sequence (S10); obtaining weights according to the first time sequence, the second time sequence, and a hierarchical analysis model (S20); obtaining a reduced multiple of a sampling rate for each time period in the first time sequence and the second time sequence according to the weights (S30); according to the multiple, resampling the first time sequence and the second time sequence to obtain a third time sequence and a fourth time sequence, respectively (S40); obtaining a trend similarity according to the third time sequence and the fourth time sequence (S50); and evaluating the credibility of the device model according to the trend similarity (S60). The method lays a good foundation for design, planning, operation and analysis decision of the device, reduces the influence on normal operation of the device, and improves evaluation accuracy.

Description

Method and device for evaluating similarity of equipment model trends Technical field

The invention belongs to the field of energy technology, and in particular relates to a method and device for evaluating the similarity of equipment model trends.

Background technique

Under the tide of the industrial Internet of Things, the simulation of equipment model parameters is becoming more and more important. The study of its mathematical model is the basis of design, planning, operation, and analysis and decision-making, and has great practical significance. For a long time, in order to verify and obtain a more accurate equipment model, people generally use the method of equipment field testing to obtain its characteristic parameters. For example, in the WECC (Western Electric Power Coordinating Council) system, about 80% of the power generation equipment has been tested; and the NERC (North American Electric Reliability Council) policy document stipulates that the generator set should be tested every 5 years. However, such testing is time-consuming and labor-intensive, and will also affect the normal operation of the equipment, and the parameters measured on site will be inaccurate due to various errors. In view of the above situation, how to evaluate the credibility of the equipment model simulation verification work is a key technical problem that needs to be solved at present.

technical problem

The purpose of the embodiments of the present invention is to provide a method, a device, a terminal device, and a computer-readable storage medium for evaluating the trend similarity of equipment models, so as to solve the current technical problem that the reliability of equipment models cannot be simulated and verified.

Technical solutions

The first aspect of the embodiments of the present invention provides a method for evaluating the similarity of equipment model trends, including:

Perform segmentation processing on the obtained reference value and simulation value of the equipment model to obtain the first time series and the second time series;

Obtaining weights according to the first time series, the second time series, and the analytic hierarchy model;

Acquiring, according to the weight, the multiple of the sampling rate reduction in each time period in the first time series and the second time series;

According to the multiple, resample each time period in the first time series and the second time series to obtain a third time series and a fourth time series respectively;

Obtaining trend similarity according to the third time series and the fourth time series;

According to the trend similarity, the credibility of the equipment model is evaluated.

In a second aspect of the embodiments of the present invention, there is provided an apparatus for evaluating the similarity of equipment model trends, including:

The information determination module is used to perform segment processing on the obtained reference value and simulation value of the device model to obtain the first time series and the second time series;

A weight acquisition module, configured to acquire weights according to the first time series, the second time series, and the analytic hierarchy model;

A multiple obtaining module, configured to obtain a multiple of the sampling rate reduction for each time period in the first time series and the second time series according to the weight;

A time series acquisition module, configured to resample each time period in the first time series and the second time series according to the multiple, and respectively acquire a third time series and a fourth time series;

A trend acquisition module, configured to acquire trend similarity according to the third time series and the fourth time series;

The credibility acquisition module is used to evaluate the credibility of the device model based on the trend similarity.

A third aspect of the embodiments of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor executes the computer program The steps of the method for evaluating the trend similarity of equipment models are realized at the time.

In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the device model trend similarity is realized Steps of the evaluation method.

Beneficial effect

The method for evaluating the similarity of equipment model trends provided by the embodiments of the present invention has beneficial effects at least as follows: the embodiments of the present invention perform validity verification and credibility evaluation on the dynamic curve of actual operating variables of the equipment according to the trend similarity. , The establishment of numerical similarity mathematical model has laid a good foundation for equipment design, planning, operation and analysis and decision-making; it reduces the waste of traditional testing manpower and material resources, which is different from traditional methods, reduces the impact on the normal operation of equipment, and improves the evaluation Accuracy: The method is quick to evaluate, simple to implement, and intelligent processing is realized.

Description of the drawings

In order to explain the technical solutions in the embodiments of the present invention more clearly, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only of the present invention. For some embodiments, those of ordinary skill in the art can obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic diagram of the implementation process of the method for evaluating the similarity of equipment model trends according to an embodiment of the present invention;

2 is a schematic diagram of an implementation process of obtaining trend similarity according to the third time series and the fourth time series in the method for evaluating trend similarity of equipment models provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of an implementation process of performing weighting processing on the fifth time series and the sixth time series to obtain weighted correlation coefficients in the method for evaluating the similarity of device model trends according to an embodiment of the present invention;

FIG. 4 is a schematic diagram of a device for evaluating similarity of equipment model trends according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a trend acquisition module in an apparatus for evaluating trend similarity of equipment models provided by an embodiment of the present invention;

6 is a schematic diagram of a weighted correlation coefficient obtaining module in an apparatus for evaluating similarity of equipment model trends according to an embodiment of the present invention;

Fig. 7 is a schematic diagram of a terminal device provided by an embodiment of the present invention.

Embodiments of the present invention

In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are proposed for a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from obstructing the description of the present invention. Based on the described embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art fall within the protection scope of the present invention. Unless otherwise specified, the technical means used in the embodiments are conventional means well known to those skilled in the art.

It should be understood that when used in this specification and appended claims, the term "comprising" indicates the existence of the described features, wholes, steps, operations, elements and/or components, but does not exclude one or more other features , The existence or addition of a whole, a step, an operation, an element, a component, and/or a collection thereof.

It should also be understood that the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in the specification of this application and the appended claims, unless the context clearly indicates other circumstances, the singular forms "a", "an" and "the" are intended to include plural forms.

It should be further understood that the term "and/or" used in the specification and appended claims of this application refers to any combination of one or more of the items listed in the associated and all possible combinations, and includes these combinations .

As used in this specification and the appended claims, the term "if" can be construed as "when" or "once" or "in response to determination" or "in response to detection" depending on the context . Similarly, the phrase "if determined" or "if detected [described condition or event]" can be construed as meaning "once determined" or "in response to determination" or "once detected [described condition or event]" depending on the context ]" or "in response to detection of [condition or event described]".

In order to illustrate the technical solutions of the present invention, specific embodiments are used for description below.

Referring to FIG. 1, it is a schematic diagram of the implementation process of the method for evaluating the similarity of equipment model trends according to an embodiment of the present invention. The method may include:

Step S10: Perform segmentation processing on the obtained reference value and simulation value of the device model to obtain the first time series and the second time series.

The reference value can be the information when the device leaves the factory, such as the information on the nameplate, the information on the manual, and so on.

The reference value is:

X={x _i ,i=1,2,...,N}

Wherein, X represents the reference value, x _i represents an achievable value, i represents the number of achievable values, and N represents the Nth number of achievable values.

It should be understood that the information of the above-mentioned equipment when it leaves the factory is not limited to the nameplate or manual, but can be various basic information that can correctly indicate the equipment when it leaves the factory, and there is no restriction here.

According to the measured value of the actual device on site, the actual device can include external equipment. This on-site measurement method is different from the measurement method commonly used in the prior art or conventional means. The traditional measurement method not only requires shutdown, some also need to The equipment undergoes destructive testing, and this measurement method will not produce the above adverse effects.

It should be understood that the external measurement equipment here is not limited to the external equipment, and may also be any other equipment, device, etc. that is convenient for measuring related data, and there is no limitation here.

According to the measured simulation data combined with the mechanism model (including classic formulas, etc.) to calculate a value, it is used for comparison with the reference value, that is to say X is the reference value, Y is the simulation value, and the simulation value is generated according to the actual The measured value is calculated.

The simulation value is:

Y={y _i ,i=1,2,...,N}

Wherein, Y represents the simulation value, y _i represents the achievable value, i represents the number of achievable values; N represents the Nth number of achievable values.

It should be understood that the mechanism model here can be understood as follows: one and/or more classic models will be used according to different equipment or equipment parameters, or one and/or more classic models will be used according to different equipment. Therefore, the equipment, equipment parameters and/or classic models here are not fixed according to different projects or purposes, and need to be determined according to the situation, and there is no restriction here.

Both the obtained first time series and the second time series have been processed, including dividing the reference value and the simulation value into n segments and pre-selecting the selected time k.

The first time series is:

X _A ＝{X _k ,k＝1,2,...,n}

Among them, X _k ={x _ki ,i=1, 2,...,N _k }, and

Wherein, X _A represents the first time series, X _k represents the obtainable value, x _ki represents the value obtainable in the X _k set, and N _k represents the N _k value obtainable in the X _{k set,} k represents the preset time, and n represents the number of time series segments.

The second time series is:

Y _A ＝{Y _k ,k＝1,2,...,n}

Among them, Y _k ={Y _ki ,i=1, 2,...,N _k }, and

Among them, Y _A represents the second time series, Y _k represents the obtainable value, Y _ki represents the obtainable value; N _k represents the N _k value obtainable in the X _k set, and k represents the preset time , N represents the number of time series segments.

It should be understood that the number of segments and the preset time are based on specific circumstances or the problem can be any number or time period, and there is no limitation here.

Please refer to Figure 1. Further, after the first time series and the second time series, the following steps can be performed:

Step S20: Obtain weights according to the first time series, the second time series and the analytic hierarchy model.

Further, in order to obtain weights, analytic hierarchy process is required. In this embodiment, a judgment matrix is established; according to the judgment matrix, the maximum eigenvalue of the judgment matrix and the normalized eigenvector of the maximum eigenvalue are obtained; the consistency check is performed on the judgment matrix to obtain the Determine the consistency ratio of the matrix; determine whether the consistency ratio meets the preset requirements; if the consistency ratio meets the preset requirements, determine the normalized feature vector as the weight; if the consistency ratio does not meet the preset requirements According to the preset requirement, return to the step of obtaining the maximum eigenvalue of the judgment matrix and the normalized eigenvector of the maximum eigenvalue according to the judgment matrix.

_{AHP model: Analytic hierarchy process (AHP) can calculate the influence weight β k} of the similarity of the k-th time period on the similarity of the entire time series.

One way of obtaining weights may also include the following steps:

Build a judgment matrix:

In the formula, b _ij represents the relative importance of the time period X _i (Y _i ) compared to the time period X _j (Y _{j ), and b ij} =1/b _ji . The value of b _ij follows the 1-9 scale method, see Table 1 below for the value table of the judgment matrix:

Element contrast importance	Judgment matrix value
Equally important	1
Slightly important	3
Obviously important	5
Strongly important	7
Extremely important	9
Neighboring judgment compromise	2, 4, 6, 8

Table 1

After obtaining the judgment matrix, the following steps can be performed:

According to the judgment matrix, the maximum eigenvalue of the judgment matrix and the normalized eigenvector of the maximum eigenvalue are obtained.

For judgment matrix B, find the characteristic root and characteristic phasor _{satisfying BW B} = λ _max W _{B , where λ max} is the maximum eigenvalue of B; W _B is the normalized eigenvector corresponding to λ _max ; the kth of _{W B} The element W _{Bk is the weight β k of} the k-th time period.

After obtaining the maximum eigenvalue and the normalized eigenvector, the following steps can be performed:

The consistency test is performed on the judgment matrix, and the consistency ratio of the judgment matrix is obtained.

The consistency ratio is;

CR=CI/RI

Among them, CR characterization consistency ratio;

RI represents the random consistency index, Table 2 Judgment matrix average random consistency index RI

Order	3	4	5	6	7	8	9
RI value	0.58	0.90	1.12	1.24	1.32	1.41	1.45

Table 2

CI characterization consistency index;

The formula for calculating the consistency index CI is:

CI=(λ _max -m)/(m-1)

Among them, λ _max represents the maximum eigenvalue;

m represents the dimension of the judgment matrix.

After obtaining the consistency ratio of the judgment matrix, the following steps can be performed:

Determine whether the consistency ratio meets the preset requirements, if the consistency ratio meets the preset requirements, the normalized feature vector is determined as the weight, if the consistency ratio does not meet the preset requirements, then return to the judgment matrix according to the , The step of obtaining the maximum eigenvalue of the judgment matrix and the normalized eigenvector of the maximum eigenvalue.

When CR<0.10, the consistency of the judgment matrix is considered acceptable, otherwise the judgment matrix should be appropriately modified.

If the preset requirements are met, the following steps can be performed:

If the consistency ratio meets the preset requirements, the normalized feature vector is determined as the weight.

Refer to Figure 1. Further, after obtaining the weights, the following steps can be performed:

Step S30: According to the weight, obtain the multiple of the sampling rate reduction for each time period in the first time series and the second time series.

The calculation of trend similarity of time series is based on the correlation coefficient method. For example, the correlation coefficient of two time series X _E and Y _E :

among them,

They are the mean values of time series X _E and Y _E respectively, which are:

The linear correlation between the two sequences X _E and Y _E is a relationship in the sense of probability. The so-called X _E and Y _E have a linear correlation Y=aX+b, which is essentially _{the scattered points of random points (x, y) in the plane X E} OY _E distributed in the vicinity of the straight line Y=aX+b, from the scattered points In terms of the distribution trend, they are similar to the shape of Y=aX+b. The degree of similarity is completely determined by the size of the correlation coefficient. If the correlation coefficient is larger (smaller), the degree of similarity is higher (lower), the degree of linear correlation is also higher (lower), and the probability P(Y=aX+b) is larger (smaller). It can be seen that considering the weighting problem of trend similarity based on correlation coefficients, we should _{think from the scatter plot of the X E} OY _E plane. If the weight of a certain period of time is small, the corresponding points on the scatter plot can be reduced to reduce The effect of this period on the probability P(Y=aX+b).

Based on this idea, an improvement to the correlation coefficient method is proposed, which is called the weighted correlation coefficient method. The calculation method is as follows: convert the weight β _{k into a multiple M k} that reduces the sampling rate in each time period:

β _max ＝max(β _k ),k＝1,2,...,n

Wherein, M _k represents the multiple by which the weight is reduced in each time period, [] represents an integer, β _max represents the maximum value of the weight corresponding to each time period, β _k represents the weight, and k represents the time period , N represents the number of segments of the time series.

Refer to Figure 1. Further, after obtaining the multiple of the sampling rate reduction for each time period, the following steps can be performed:

Step S40: Resample each time period in the first time sequence and the second time sequence according to the multiple, and obtain a third time sequence and a fourth time sequence respectively.

The third time series acquisition method is:

Wherein, X _Rk represents the third time series after resampling, x _ki represents the obtainable value, and i represents the number of obtainable values;

The fourth time series acquisition method is:

Wherein, Y _Rk represents the fourth time series after resampling, y _ki represents the obtainable value, and i represents the number of obtainable values.

Please refer to Figure 1. Further, after obtaining the third time series and the fourth time series, the following steps can be performed:

Step S50: Obtain trend similarity according to the third time series and the fourth time series.

Further, in order to obtain the trend similarity, the third time series and the fourth time series need to be spliced separately. Please refer to FIG. 2, which is a schematic diagram of the implementation process of obtaining trend similarity according to the third time series and the fourth time series in the method for evaluating trend similarity of equipment models provided by an embodiment of the present invention. The third time series and the fourth time series are respectively spliced to obtain a fifth time series and a sixth time series; the fifth time series and the sixth time series are respectively weighted to obtain a weighted correlation coefficient ; Perform mapping processing on the weighted correlation coefficient to obtain the trend similarity between the first time series and the second time series. One way of obtaining trend similarity may include the following steps:

Step S501: Perform splicing processing on the third time sequence and the fourth time sequence, respectively, to obtain a fifth time sequence and a sixth time sequence.

The fifth time series acquisition method is:

X _R ＝{X _Rk ,k＝1,2,...,n}

Wherein, X _R represents the fifth time sequence, X _Rk represents an achievable value, k represents a time period, and n represents the number of segments of the time sequence;

The sixth time series acquisition method is:

Y _R ＝{Y _Rk ,k＝1,2,...,n}

Wherein, Y _R represents the sixth time sequence, Y _Rk represents an achievable value, k represents a time period, and n represents the number of segments of the time sequence.

After obtaining the fifth time series and the sixth time series, the following steps can be performed:

Step S502: Perform weighting processing on the fifth time sequence and the sixth time sequence to obtain weighted correlation coefficients.

Further, in order to obtain the weighted correlation coefficient, it is necessary to obtain the mean value. Please refer to FIG. 3, which is a schematic diagram of the implementation process of performing weighting processing on the fifth time series and the sixth time series to obtain weighted correlation coefficients in the method for evaluating the similarity of equipment model trends according to an embodiment of the present invention. , According to the fifth time series and the sixth time series, the mean value of the fifth time series and the mean value of the sixth time series are respectively obtained; according to the mean value of the fifth time series and the sixth time series The mean value of the time series, to obtain the weighted correlation coefficient. One way of obtaining the weighted correlation coefficient may include the following steps:

Step S5021: Obtain the mean value of the fifth time series and the mean value of the sixth time series respectively according to the fifth time series and the sixth time series.

After obtaining the mean value, the following steps can be performed:

Step S5022: Obtain a weighted correlation coefficient according to the average value of the fifth time series and the average value of the sixth time series.

The weighted correlation coefficient is:

Among them, X _R = {X _Rk ,k =1,2,...,N _R }, Y _R ={Y _Rk ,k =1,2,...,N _R },

_{Wherein, R (X R, Y R} ) characterized weighted correlation coefficient, N _R characterizing the set value of the time series,

Characterize the mean value of the fifth time series,

Characterize the mean value of the sixth time series.

After obtaining the weighted correlation coefficient, the following steps can be performed:

Step S503: Perform mapping processing on the weighted correlation coefficients to obtain the trend similarity between the first time series and the second time series.

Mapping the weighted correlation coefficient R(X _R ,Y _R ) from [-1,1] to [0,1], the trend similarity is:

Wherein, R′(X _R , Y _R ) represents the trend similarity between the first time series and the second time series.

Refer to Figure 1. Further, after obtaining the trend similarity, the following steps can be performed:

Step S60: Evaluate the credibility of the equipment model according to the trend similarity.

The value range of trend similarity is 0%-100%. The closer to 100%, the more accurate the reference value.

For trend similarity less than the 80% threshold, the reference value can be considered inaccurate, and for the numerical similarity greater than or equal to the 80% threshold, the reference value can be considered accurate.

It should be understood that the above threshold may be changed according to different project or situation requirements, for example, it may be 50% or 95%, etc., which is not limited here.

It should be understood that the above English letters and/or symbols are only used to clearly illustrate the meaning of the specific parameters referred to in the method, and other letters or symbols may also be used to represent them, and there is no limitation here.

It should be understood that the size of the sequence number of each step in the foregoing embodiment does not mean the order of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any implementation process of the embodiment of the present invention. limited.

The beneficial effect of the method for evaluating the similarity of equipment model trends provided by the embodiment of the present invention is at least that: the embodiment of the present invention performs segmentation processing on the obtained reference value and simulation value of the equipment model, and obtains the first time series and the first time series. Two time series; according to the first time series, the second time series and the analytic hierarchy model, obtain weights; according to the weights, obtain each time period in the first time series and the second time series Reduce the multiple of the sampling rate; according to the multiple, resample each time period in the first time series and the second time series to obtain the third time series and the fourth time series respectively; according to the first time series The third time series and the fourth time series acquire a trend similarity; according to the trend similarity, the credibility of the equipment model is evaluated. According to the trend similarity, the validity verification and credibility evaluation of the dynamic curve of the actual operating variables of the equipment are carried out. The establishment of the mathematical model of the numerical similarity lays a good foundation for the design, planning, operation and analysis and decision-making of the equipment; it reduces the traditional The waste of testing manpower and material resources is different from the traditional method, which reduces the impact on the normal operation of the equipment and improves the accuracy of the evaluation; the method is quick to evaluate, the implementation process is simple, and the intelligent processing is realized.

The embodiment of the present invention also aims to provide an apparatus for evaluating equipment model trend similarity. FIG. 4 is a schematic diagram of the apparatus for evaluating equipment model trend similarity provided by an embodiment of the present invention. For ease of description, only shown The parts related to the embodiments of the present application are shown.

Referring to FIG. 4, the apparatus for evaluating trend similarity of equipment models includes an information determining module 71, a weight acquiring module 72, a multiple acquiring module 73, a time series acquiring module 74, a trend acquiring module 75, and a credibility acquiring module 76. Wherein, the information determining module 71 is used to perform segment processing on the obtained reference value and simulation value of the device model to obtain the first time series and the second time series; the weight obtaining module 72 is used to obtain the first time series and the second time series according to the The second time series and the analytic hierarchy model are used to obtain weights; the multiple obtaining module 73 is configured to obtain, according to the weights, the multiple of the sampling rate reduction in each time period in the first time series and the second time series; The sequence acquisition module 74 is configured to resample each time period in the first time sequence and the second time sequence according to the multiple, to obtain the third time sequence and the fourth time sequence respectively; the trend acquisition module 75 It is used to obtain trend similarity according to the third time series and the fourth time series; the credibility obtaining module 76 is used to evaluate the credibility of the device model according to the trend similarity.

Referring to FIG. 5, further, the trend obtaining module 75 includes a time series obtaining unit 751, a weighting processing unit 752, and a trend similarity obtaining unit 753. Wherein, the time sequence acquiring unit 751 is configured to perform splicing processing on the third time sequence and the fourth time sequence to acquire the fifth time sequence and the sixth time sequence; the weighting processing unit 752 is configured to combine the fifth time sequence The time series and the sixth time series are respectively weighted to obtain weighted correlation coefficients; the trend similarity obtaining unit 753 is configured to perform mapping processing on the weighted correlation coefficients to obtain the first time series and the second time series. The trend similarity of the sequence.

Please refer to FIG. 6, further, the weighting processing unit 752 includes an average value obtaining unit 7521 and a weighted correlation coefficient obtaining unit 7522. Wherein, the mean value obtaining unit 7521 is configured to obtain the mean value of the fifth time series and the mean value of the sixth time series respectively according to the fifth time series and the sixth time series; the weighted correlation coefficient obtaining unit 7522 uses According to the mean value of the fifth time series and the mean value of the sixth time series, a weighted correlation coefficient is obtained.

Fig. 7 is a schematic diagram of a terminal device provided by an embodiment of the present invention. As shown in FIG. 7, the terminal device 8 includes a processor 80, a memory 81, and a computer program 82 that is stored in the memory 81 and can run on the processor 80. The processor 80 executes the The computer program 82 implements steps such as the method of obtaining the state of the target object. For example, steps S10 to S60 shown in Figs. 1-3.

The terminal device 8 may be a computing device such as a desktop computer, a notebook, a palmtop computer, and a cloud server. The terminal device may include, but is not limited to, the processor 80 and the memory 81. Those skilled in the art can understand that FIG. 7 is only an example of the terminal device 8 and does not constitute a limitation on the terminal device 8. It may include more or less components than those shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, and so on.

The so-called processor 80 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.

The memory 81 may be an internal storage unit of the terminal device 8, such as a hard disk or memory of the terminal device 8. The memory 81 may also be an external storage device of the terminal device 8, such as a plug-in hard disk equipped on the terminal device 8, a Smart Media Card (SMC), or a Secure Digital (SD) card. Flash Card, etc. Further, the memory 81 may also include both an internal storage unit of the terminal device 8 and an external storage device. The memory 81 is used to store the computer program and other programs and data required by the terminal device. The memory 81 can also be used to temporarily store data that has been output or will be output.

If the integrated module/unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, this application implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the program is executed by the processor, it can implement the steps of the foregoing method embodiments. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate forms. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory) , Random Access Memory (RAM, Random Access Memory), electrical carrier signal, telecommunications signal, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately added or deleted according to the requirements of the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to the legislation and patent practice, the computer-readable medium Does not include electrical carrier signals and telecommunication signals.

The details may be as follows. Embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium may be the computer-readable storage medium included in the memory in the above-mentioned embodiment; A computer-readable storage medium assembled into a terminal device. The computer-readable storage medium stores one or more computer programs:

The computer-readable storage medium includes the computer-readable storage medium storing a computer program, and the computer program is executed by a processor to realize the steps of the data simulation method of the IoT device.

Those skilled in the art can clearly understand that for the convenience and conciseness of description, only the division of the above functional units and modules is used as an example. In practical applications, the above functions can be allocated to different functional units and modules as needed. Module completion, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist alone physically, or two or more units can be integrated into one unit. The above-mentioned integrated units can be hardware-based Formal realization can also be realized in the form of a software functional unit. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the foregoing system, reference may be made to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in an embodiment, reference may be made to related descriptions of other embodiments.

A person of ordinary skill in the art may realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered as going beyond the scope of the present invention.

In the embodiments provided by the present invention, it should be understood that the disclosed device/terminal device and method may be implemented in other ways. For example, the device/terminal device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units. Or components can be combined or integrated into another system, or some features can be omitted or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

The above-mentioned embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that it can still implement the foregoing The technical solutions recorded in the examples are modified, or some of the technical features are equivalently replaced; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in Within the protection scope of the present invention.

Claims (10)

1. A method for evaluating the similarity of equipment model trends, which is characterized in that it includes:

   Perform segmentation processing on the obtained reference value and simulation value of the equipment model to obtain the first time series and the second time series;

   Obtaining weights according to the first time series, the second time series, and the analytic hierarchy model;

   Acquiring, according to the weight, the multiple of the sampling rate reduction in each time period in the first time series and the second time series;

   According to the multiple, resample each time period in the first time sequence and the second time sequence to obtain a third time sequence and a fourth time sequence respectively;

   Obtaining trend similarity according to the third time series and the fourth time series;

   According to the trend similarity, the credibility of the equipment model is evaluated.
2. The method for evaluating the similarity of equipment model trends according to claim 1, wherein said first time series and said second time series are down-sampled for each time period obtained according to said weight Among the multiples of the rate, the multiple acquisition method is:

   

   β _max ＝max(β _k ),k＝1,2,...,n

   Wherein, M _k represents the multiple by which the weight is reduced by the sampling rate in each time period;

   [] Characterization takes an integer;

   β _max represents the maximum value of the weight corresponding to each time period;

   β _k represents the weight;

   k represents the time period;

   n represents the number of segments of the time series.
3. The method for evaluating the similarity of equipment model trends according to claim 2, wherein, according to the multiple, each time period in the first time series and the second time series is reproduced. In sampling and separately acquiring the third time series and the fourth time series, the third time series acquisition method is:

   

   Wherein, X _Rk represents the third time series after resampling, x _ki represents the obtainable value, and i represents the number of obtainable values;

   The fourth time series acquisition method is:

   

   Wherein, Y _Rk represents the fourth time series after resampling, y _ki represents the obtainable value, and i represents the number of obtainable values.
4. The method for evaluating trend similarity of equipment models according to claim 3, wherein said obtaining trend similarity according to said third time series and said fourth time series comprises:

   Performing splicing processing on the third time sequence and the fourth time sequence, respectively, to obtain a fifth time sequence and a sixth time sequence;

   Performing weighting processing on the fifth time series and the sixth time series respectively to obtain a weighted correlation coefficient;

   The weighted correlation coefficient is subjected to mapping processing to obtain the trend similarity between the first time series and the second time series.
5. The method for evaluating the similarity of equipment model trends according to claim 4, wherein the third time series and the fourth time series are respectively spliced to obtain the fifth time series and the first time series. In the six time series, the fifth time series acquisition method is:

   X _R ＝{X _Rk ,k＝1,2,...,n}

   Wherein, X _R represents the fifth time sequence, X _Rk represents an achievable value, k represents a time period, and n represents the number of segments of the time sequence;

   The sixth time series acquisition method is:

   Y _R ＝{Y _Rk ,k＝1,2,...,n}

   Wherein, Y _R represents the sixth time sequence, Y _Rk represents an achievable value, k represents a time period, and n represents the number of segments of the time sequence.
6. 5. The method for evaluating the similarity of equipment model trends according to claim 5, wherein said performing weighting processing on said fifth time series and said sixth time series respectively to obtain weighted correlation coefficients comprises:

   Respectively acquiring the mean value of the fifth time series and the mean value of the sixth time series according to the fifth time series and the sixth time series;

   According to the mean value of the fifth time series and the mean value of the sixth time series, a weighted correlation coefficient is obtained, and the weighted correlation coefficient is:

   

   Among them, X _R = {X _Rk ,k =1,2,...,N _R }, Y _R ={Y _Rk ,k =1,2,...,N _R },

   

   Among them, R(X _R , Y _R ) represents the weighted correlation coefficient;

   N _R characterizing the set value of the time series;

   

   Characterize the mean value of the fifth time series;

   

   Characterize the mean value of the sixth time series.
7. The method for evaluating the similarity of equipment model trends according to claim 6, wherein the weighted correlation coefficients are mapped to obtain the trends of the first time series and the second time series In the similarity, the trend similarity is:

   

   Wherein, R′(X _R , Y _R ) represents the trend similarity between the first time series and the second time series.
8. A device for evaluating the similarity of equipment model trends, which is characterized in that it comprises:

   The information determination module is used to perform segment processing on the obtained reference value and simulation value of the device model to obtain the first time series and the second time series;

   A weight obtaining module, configured to obtain weights according to the first time series, the second time series, and the hierarchical analysis model;

   A multiple obtaining module, configured to obtain a multiple of the sampling rate reduction for each time period in the first time series and the second time series according to the weight;

   A time series acquisition module, configured to resample each time period in the first time series and the second time series according to the multiple, and respectively acquire a third time series and a fourth time series;

   A trend acquisition module, configured to acquire trend similarity according to the third time series and the fourth time series;

   The credibility acquisition module is used to evaluate the credibility of the device model based on the trend similarity.
9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program as described in claim 1. The steps of the method.
10. A computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of the method according to claim 1.

Images