CN111811567A - Equipment detection method based on curve inflection point comparison and related device - Google Patents
Equipment detection method based on curve inflection point comparison and related device Download PDFInfo
- Publication number
- CN111811567A CN111811567A CN202010704985.1A CN202010704985A CN111811567A CN 111811567 A CN111811567 A CN 111811567A CN 202010704985 A CN202010704985 A CN 202010704985A CN 111811567 A CN111811567 A CN 111811567A
- Authority
- CN
- China
- Prior art keywords
- curve
- inflection point
- inflection
- real
- data curve
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D9/00—Recording measured values
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The application provides a device detection method and a related device based on curve inflection point comparison, and relates to the field of industrial automatic control data processing. The method comprises the following steps: matching a real-time data curve of the equipment to be detected with a historical data curve to obtain a segmented inflection point group; segmenting the real-time data curve and the historical data curve into a plurality of curve segment groups according to the segmented inflection point groups; sequentially acquiring curve comparison parameters of each curve segment group according to the sequence identification; and when all the curve comparison parameters are matched with the preset comparison threshold value, determining that the equipment to be detected is in a first working condition. The method comprises the steps of obtaining a segmented inflection point group of a real-time data curve and a historical data curve, and automatically carrying out segmented comparison on the two curves to determine that the current running state of the equipment to be detected is a first working condition, so that the reason for the difference of the two curves can be specifically analyzed, and the detection accuracy of the equipment is improved.
Description
Technical Field
The application relates to the field of industrial automatic control data processing, in particular to a device detection method based on curve inflection point comparison and a related device.
Background
In the field of industrial automation, in order to detect the operating conditions of the equipment, the data collected by the sensors need to be processed and analyzed.
Analyzing common curve analysis on data collected by a sensor, and integrally comparing two or more curves to further determine the running condition of the equipment; the method can only compare the overall difference of two curves, return the comparison result under the whole curve, and can only compare and analyze two curves with similar shapes by manual topping. How to compare two sets of data of equipment in different time spans and automatically judge the running condition of the equipment is a problem to be solved urgently at present.
Disclosure of Invention
In view of the above, an object of the present application is to provide a method and a related apparatus for detecting devices based on knee-point comparison.
In order to achieve the above purpose, the embodiments of the present application employ the following technical solutions:
in a first aspect, an embodiment of the present application provides an apparatus detection method based on knee-point comparison, where the method includes:
matching a real-time data curve of the equipment to be detected with a historical data curve to obtain a segmented inflection point group; the real-time data curve represents the current operation condition of the equipment to be detected, and the historical data curve represents the operation condition of the equipment to be detected under a first working condition;
segmenting the real-time data curve and the historical data curve into a plurality of curve segment groups according to the segmented inflection point groups; each curve segment group is provided with a sequence identification, and each curve segment group comprises a first curve segment of the real-time data curve in a first time window corresponding to the sequence identification and a second curve segment of the historical data curve in the first time window;
sequentially acquiring curve comparison parameters of each curve segment group according to the sequence identification; the curve comparison parameters comprise curve comparison conditions of the first curve segment and the second curve segment in the first time window;
and when all the curve comparison parameters are matched with a preset comparison threshold value, determining that the equipment to be detected is in the first working condition.
In an optional embodiment, the obtaining of a segmented inflection point group obtained by matching a real-time data curve of a device to be detected with a historical data curve includes:
acquiring the real-time data curve and the historical data curve;
acquiring at least one first curve inflection point of the real-time data curve and at least one second curve inflection point of the historical data curve; the first curve inflection point is an extreme point of which the variation degree in the real-time data curve is greater than or equal to a preset fluctuation threshold value, and the second curve inflection point is an extreme point of which the variation degree in the historical data curve is greater than or equal to the preset fluctuation threshold value;
and combining all the first curve inflection points and all the second curve inflection points to obtain the segmented inflection point group.
In an alternative embodiment, combining all of the first inflection points and all of the second inflection points to obtain the set of piecewise inflection points includes:
acquiring distance matrixes of all the first curve inflection points and all the second curve inflection points; the distance matrix characterizes distance information of each first curve inflection point and each second curve inflection point;
acquiring the pairing distance of the distance matrix according to a dynamic time normalization algorithm; the pairing distance is the minimum cumulative distance from the first curve inflection point to the last second curve inflection point in the distance matrix;
determining the segmented inflection point group according to the pairing distance and an inflection point comparison threshold; the inflection point comparison threshold is a similarity threshold determined according to the real-time data curve and the historical data curve.
In an alternative embodiment, the real-time data curve has M of the first inflection points, the historical data curve has N of the second inflection points, M and N are both positive integers greater than or equal to 1;
determining the segmented inflection point group according to the pairing distance and an inflection point comparison threshold, wherein the step of determining the segmented inflection point group comprises the following steps:
judging whether the pairing distance is smaller than or equal to the inflection point comparison threshold;
if so, combining the curve inflection points corresponding to the pairing distances to serve as the segmented inflection point group; the curve inflection point combination is the inflection point combination from the first curve inflection point to the last second curve inflection point according to the minimum accumulated distance;
if not, judging whether M and N are equal;
and if the M and the N are not equal, combining the first curve inflection point and the second curve inflection point corresponding to the pairing distance, and taking the combined curve inflection point as the segment inflection point group.
In a second aspect, an embodiment of the present application provides an apparatus for detecting a device based on knee-point comparison, where the apparatus includes:
the inflection point determining unit is used for matching a real-time data curve of the equipment to be detected with a historical data curve to obtain a segmented inflection point group; the real-time data curve represents the current operation condition of the equipment to be detected, and the historical data curve represents the operation condition of the equipment to be detected under a first working condition;
the curve segmentation unit is used for segmenting the real-time data curve and the historical data curve into a plurality of curve segment groups according to the segmented inflection point groups; each curve segment group is provided with a sequence identification, and each curve segment group comprises a first curve segment of the real-time data curve in a first time window corresponding to the sequence identification and a second curve segment of the historical data curve in the first time window;
the processing unit is used for sequentially acquiring curve comparison parameters of each curve segment group according to the sequence identification; the curve comparison parameters comprise curve comparison conditions of the first curve segment and the second curve segment in the first time window;
the processing unit is further configured to determine that the device to be detected is in the first working condition when all the curve comparison parameters are matched with a preset comparison threshold.
In an optional embodiment, the inflection point determining unit is further configured to obtain the real-time data curve and the historical data curve;
the inflection point determining unit is further used for acquiring at least one first curve inflection point of the real-time data curve and at least one second curve inflection point of the historical data curve; the first curve inflection point is an extreme point of which the variation degree in the real-time data curve is greater than or equal to a preset fluctuation threshold value, and the second curve inflection point is an extreme point of which the variation degree in the historical data curve is greater than or equal to the preset fluctuation threshold value;
the inflection point determining unit is further configured to combine all of the first inflection points and all of the second inflection points to obtain the set of piecewise inflection points.
In an alternative embodiment, the inflection point determining unit is further configured to obtain a distance matrix of all the first inflection points and all the second inflection points; the distance matrix characterizes distance information of each first curve inflection point and each second curve inflection point;
the inflection point determining unit is further used for acquiring the pairing distance of the distance matrix according to a dynamic time normalization algorithm; the pairing distance is the minimum cumulative distance from the first curve inflection point to the last second curve inflection point in the distance matrix;
the inflection point determining unit is further configured to determine the segmented inflection point group according to the pairing distance and an inflection point comparison threshold; the inflection point comparison threshold is a similarity threshold determined according to the real-time data curve and the historical data curve.
In an alternative embodiment, the real-time data curve has M of the first inflection points, the historical data curve has N of the second inflection points, M and N are both positive integers greater than or equal to 1;
the inflection point determining unit is further configured to determine whether the pairing distance is less than or equal to the inflection point comparison threshold;
the inflection point determining unit is further configured to, if the pairing distance is smaller than or equal to the inflection point comparison threshold, combine curve inflection points corresponding to the pairing distance as the segment inflection point group; the curve inflection point combination is the inflection point combination from the first curve inflection point to the last second curve inflection point according to the minimum accumulated distance;
the inflection point determining unit is further configured to determine whether M and N are equal to each other if the pairing distance is greater than the inflection point comparison threshold;
and the inflection point determining unit is further configured to perform a merging operation on the first inflection point and the second inflection point corresponding to the pairing distance if M and N are not equal to each other, and use the merged inflection point as the segment inflection point group.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory, where the memory stores machine executable instructions that can be executed by the processor, and the processor can execute the machine executable instructions to implement the method described in any one of the foregoing embodiments.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the method of any one of the foregoing embodiments.
Compared with the prior art, the method and the device for detecting the equipment based on the curve inflection point comparison relate to the field of data processing of industrial automatic control. The method comprises the following steps: matching a real-time data curve of the equipment to be detected with a historical data curve to obtain a segmented inflection point group; the real-time data curve represents the current operation condition of the equipment to be detected, and the historical data curve represents the operation condition of the equipment to be detected under a first working condition; segmenting the real-time data curve and the historical data curve into a plurality of curve segment groups according to the segmented inflection point groups; each curve segment group is provided with a sequence identification, and each curve segment group comprises a first curve segment of the real-time data curve in a first time window corresponding to the sequence identification and a second curve segment of the historical data curve in the first time window; sequentially acquiring curve comparison parameters of each curve segment group according to the sequence identification; the curve comparison parameters comprise curve comparison conditions of the first curve segment and the second curve segment in the first time window; and when all the curve comparison parameters are matched with a preset comparison threshold value, determining that the equipment to be detected is in the first working condition. The method comprises the steps of obtaining a segmented inflection point group of a real-time data curve and a historical data curve, and automatically carrying out segmented comparison on the two curves to determine that the current running state of the equipment to be detected is a first working condition, so that the reason for the difference of the two curves can be specifically analyzed, and the detection accuracy of the equipment is improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flowchart of an apparatus detection method based on knee-point comparison according to an embodiment of the present application;
fig. 2 is a schematic flowchart of another apparatus detection method based on knee-point comparison according to an embodiment of the present application;
fig. 3 is a schematic diagram of a curve inflection point provided in an embodiment of the present application;
FIG. 4 is a schematic diagram of another inflection point of a curve provided in an embodiment of the present application;
fig. 5 is a schematic flowchart of another apparatus detection method based on knee-point comparison according to an embodiment of the present application;
fig. 6 is a schematic flowchart of another apparatus detection method based on knee-point comparison according to an embodiment of the present application;
FIG. 7 is a schematic view of another inflection point of a curve provided in an embodiment of the present application;
FIG. 8 is a schematic view of another inflection point of a curve provided in an embodiment of the present application;
fig. 9 is a schematic block diagram of an apparatus detection device based on knee-point comparison according to an embodiment of the present application;
fig. 10 is a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
It is noted that relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In the field of industrial control, no technology exists for automatically judging the operation condition of equipment and giving possible reasons by comparing two sets of data of the same sensor in different time spans at present. The prior curve comparison technology in other fields has the following defects: the curves cannot be processed in a segmented mode, only the overall difference of the two curves can be compared, and a comparison result under the whole curve is returned; manually appointing two line segments with similar shapes for comparison; the returned result is a difference scalar, and the reason of the specific difference of the two curves cannot be judged.
In order to solve the above problems and the disadvantages of the background art, an embodiment of the present application provides a device detection method based on knee-point comparison, please refer to fig. 1, where fig. 1 is a schematic flow diagram of the device detection method based on knee-point comparison provided by the embodiment of the present application, and the device detection method may include the following steps:
and S31, matching the real-time data curve of the device to be detected with the historical data curve to obtain a segmented inflection point group.
The real-time data curve represents the current operation condition of the equipment to be detected, and the historical data curve represents the operation condition of the equipment to be detected under the first working condition. In a possible implementation manner, if the device to be detected has no historical data, a historical data curve of other devices of the same type as the device to be detected may be used as a reference, and a data curve under a standard operating condition set by the factory of the device to be detected may also be used.
And S32, segmenting the real-time data curve and the historical data curve into a plurality of curve segment groups according to the segmented inflection point groups.
Each curve segment group is provided with a sequence identification, and each curve segment group comprises a first curve segment of the real-time data curve in a first time window corresponding to the sequence identification and a second curve segment of the historical data curve in the first time window. It is to be understood that the sequence identifier can be used to determine whether the real-time data curve and the historical data curve have the same or similar stations, such that an alignment of the real-time data curve and the historical data curve over a first time window (or other designated time window, data stations, etc.) has practical significance.
And S33, sequentially acquiring curve alignment parameters of each curve segment group according to the sequence identification.
The curve comparison parameter comprises curve comparison conditions of the first curve section and the second curve section in the first time window. For example, the curve alignment may be calculated information of mutation direction, mutation size, mutation rate, etc. of each curve segment group.
And S34, when all the curve comparison parameters are matched with the preset comparison threshold value, determining that the equipment to be detected is in the first working condition.
For example, the preset comparison threshold may be calculated according to information such as variance, range, skewness, abundance, median, mode and the like of an original curve (a real-time data curve and a historical data curve), and may also be set according to an operation attribute of the device to be detected, and the user may also adjust the preset comparison threshold according to an actual operation condition of the device to be detected.
Judging whether the curve comparison condition is in a reasonable range or not according to a preset comparison threshold value so as to determine that the equipment to be detected is in a first working condition when the curve comparison parameter is matched with the preset comparison threshold value; and when the curve comparison condition and the preset comparison threshold value have large difference, namely are not matched, analyzing the current operation condition of the equipment to be detected, and giving the reason for the abnormality of the equipment to be detected. It should be noted that, because the device detection method provided in the embodiment of the present application performs segmented detection on the real-time data curve of the device to be detected, a specific difference reason between the two curves can be determined when the device to be detected is analyzed.
It should be understood that the segmented inflection point groups of the real-time data curve and the historical data curve are obtained, and the two curves are automatically segmented and compared to determine that the current operation state of the device to be detected is the first working condition, so that the reason for the difference of the two curves can be specifically analyzed, and the detection accuracy of the device is improved.
In an optional embodiment, it is impossible to obtain an accurate detection result of the device to be detected when two data curves with different measurement points and different working conditions are analyzed, and in order to avoid manually selecting a similar curve for analysis and improve the automation of device detection, a possible implementation manner is provided on the basis of fig. 1, please refer to fig. 2, fig. 2 provides another schematic flow diagram of a device detection method based on curve inflection point comparison for the embodiment of the present application, and S31 may include:
s311, acquiring a real-time data curve and a historical data curve.
S312, at least one first curve inflection point of the real-time data curve and at least one second curve inflection point of the historical data curve are obtained.
The first curve inflection point is an extreme point of which the variation degree in the real-time data curve is greater than or equal to a preset fluctuation threshold, and the second curve inflection point is an extreme point of which the variation degree in the historical data curve is greater than or equal to a preset fluctuation threshold. For example, a preset fluctuation threshold may be used
It is shown that it is possible to control the number of the first and second inflection points and the degree of sensitivity of the first and second inflection points.
And S313, combining all the first inflection points and all the second inflection points to obtain a segmented inflection point group.
Before acquiring the segmented inflection point group, selecting an optimal time window t according to the whole time span and sampling frequency of the real-time data curve and the historical data curve, and smoothing and denoising the real-time data curve and the historical data curve on the whole curve according to the time t; the time window can be set by itself if it is desired to optimize the degree of curve smoothing. The preset fluctuation threshold may be a real-time data curve and a historical data curve after smooth noise reduction, and the optimal inflection point fluctuation threshold is determined according to the variance, range, skewness, kurtosis, median, mode and other information of the preset fluctuation threshold
For the above S311 to S313, the embodiment of the present application provides a possible implementation manner: in the two curves, all the numerical value points are traversed, and all the observed values are found to have fluctuation amplitude larger than that of the observed value
And the observed value is a numerical point of the local extremum and is marked as an inflection point of the curve. Referring to fig. 3, fig. 3 is a schematic view of a curve inflection point provided in the present application. The curve shown in (a) of fig. 3 is a historical data curve Line1, and the curve shown in (b) of fig. 3 is a real-time data curve Line2, Line1 and Line2, which may be in the format of "[ [ tp1, x1 ]]，[tp2,x2]....[tpn,xn]]"represents, where tp is a timestamp (time stamp) and xn is an observed value; with continued reference to fig. 3, the abscissa is the timestamp tp, the ordinate is the observed value xn, Line1 includes one inflection point (no head-to-tail point is calculated), and Line2 includes two inflection points (no head-to-tail point is calculated).
For example, the preset fluctuation threshold may be used
Is shown, the preset fluctuation threshold value
The smaller the number of acquired curve views; the preset fluctuation threshold
The larger the number of curve inflection points acquired, i.e. the preset fluctuation threshold
The larger the curve points, the more sparse the curve points in the real-time data curve and the historical data curve are, and the more severe the change of each curve point is. Referring to fig. 4, fig. 4 is a schematic view of another inflection point of a curve provided in the present embodiment, where (a) in fig. 4 is a schematic view of an inflection point obtained by a smaller preset fluctuation threshold, and the number of inflection points of the curve is larger; FIG. 4 (b) shows a preset fluctuation thresholdValue of
The larger obtained inflection points indicate that the number of the inflection points of the curve is smaller, and the variation degree of each inflection point of the curve is larger.
In an alternative embodiment, the real-time data curve and the historical data curve may include more curve inflection points, and in order to accurately compare the real-time data curve and the historical data curve, a possible implementation manner is provided on the basis of fig. 2, please refer to fig. 5, where fig. 5 is a schematic flow chart of another device detection method based on curve inflection point comparison provided by the embodiment of the present application, and the above S313 may include:
s313a, a distance matrix of all first inflection points and all second inflection points is obtained.
The distance matrix characterizes distance information for each first knee point and each second knee point.
S313b, obtaining the pairing distance of the distance matrix according to the dynamic time integration algorithm.
The pair distance is the smallest cumulative distance from the first knee point to the last second knee point in the matrix. For example, the inflection points of two curves are known as:
real-time data curve Line 1: [ a1, a2, a3, a4, a5 ];
historical data curve Line 2: [ b1, b2, b3, b4 ];
the distance between the inflection points is respectively calculated pairwise, and the obtained matrix is a distance matrix of the inflection points of the two curves, and the form is as follows:
the minimum cumulative distance of the inflection point pairs between Line1 and Line2 is found from the matrix according to the distance, namely the pair distance in the S313b, such as a1-b1 → a2-b1 → a3-b2 → a4-b3 → a5-b 4.
S313c, determining a segmented inflection group according to the matching distance and the inflection point comparison threshold.
The inflection point comparison threshold is a similarity threshold determined according to a real-time data curve and a historical data curve. For example, the inflection point comparison threshold may be a similarity threshold automatically determined by integrating information such as variance, range, skewness, kurtosis, median, mode, and the like of two curves (a real-time data curve and a historical data curve).
In an alternative embodiment, to facilitate understanding of the above S313c, on the basis of fig. 5, taking an example that the real-time data curve has M first inflection points, the historical data curve has N second inflection points, and M and N are both positive integers greater than or equal to 1, a possible implementation is given, please refer to fig. 6, fig. 6 provides a schematic flow chart of another device detection method based on inflection point comparison, and the above S313c may include:
s313c-1, determine whether the matching distance is less than or equal to the inflection point alignment threshold.
If yes, go to S313 c-2; if not, S313c-3 is performed.
And S313c-2, combining the curve inflection points corresponding to the paired distances to form a segmented inflection point group.
The knee point combination is a combination of knee points from a first knee point to a last second knee point according to a minimum cumulative distance. For example, when the pair distance is less than or equal to the inflection point alignment threshold, an optimal primary curve fitting Line1 and Line2 may also be calculated as a curve (curve segment group) of the final alignment calculation.
S313c-3, judge whether M and N are equal.
If M and N are not equal, executing S313 c-4; if M is equal to N, S313c-5 is performed.
And S313c-4, merging the first curve inflection point and the second curve inflection point corresponding to the pairing distance, and taking the merged curve inflection point as a segmented inflection point group.
S313c-5, determining that the device to be detected is not in the first working condition.
It should be noted that when M and N are not equal and the matching distance is greater than the inflection point comparison threshold, it is determined that the two curves are not similar; and as long as the pairing distance is smaller than or equal to the inflection point comparison threshold, whether M and N are equal or not, the two curves (the real-time data curve and the historical data curve) are determined to be integrally similar, and the inflection points of the curves are not merged. For example, referring to fig. 7, fig. 7 is a schematic view of another inflection point of a curve provided in the embodiment of the present application, after the inflection point merger is performed, the number of inflection points of the real-time data curve and the historical data curve after the inflection point merger is the same, that is, only one inflection point of the curve is reserved (no beginning point and end point is calculated).
In order to facilitate understanding of the device detection methods corresponding to S313c-1 to S313c-5, on the basis of fig. 3, taking inflection point merging as an example, please refer to fig. 8, where fig. 8 is a schematic diagram of another inflection point provided in the embodiment of the present application, if a pairing distance between a real-time data curve and a historical data curve is smaller than an inflection point comparison threshold, the first inflection point and the second inflection point are not merged, and 3 first inflection points (an upper side curve shown in fig. 8) and 2 second inflection points (a lower side curve shown in fig. 8) are respectively reserved.
In order to implement the device detection methods corresponding to S31-S34, an embodiment of the present application provides a device detection apparatus based on knee-point comparison, please refer to fig. 9, and fig. 9 is a block diagram of the device detection apparatus based on knee-point comparison provided in the embodiment of the present application. The device detection apparatus 40 includes: an inflection point determining unit 41, a curve slicing unit 42, and a processing unit 43.
The inflection point determining unit 41 is configured to match a real-time data curve of the device to be tested with a historical data curve, and obtain a segmented inflection point group. The real-time data curve represents the current operation condition of the equipment to be detected, and the historical data curve represents the operation condition of the equipment to be detected under the first working condition.
The curve segmentation unit 42 is configured to segment the real-time data curve and the historical data curve into a plurality of curve segment groups according to the segmented inflection point groups. Each curve segment group has a sequence identifier, and the curve segment group comprises a first curve segment of the real-time data curve in a first time window corresponding to the sequence identifier and a second curve segment of the historical data curve in the first time window.
The processing unit 43 is configured to sequentially obtain the curve alignment parameters of each curve segment group according to the sequence identifier. The curve comparison parameters comprise curve comparison conditions of the first curve section and the second curve section in the first time window.
The processing unit 43 is further configured to determine that the device to be detected is in the first working condition when all the curve comparison parameters are matched with the preset comparison threshold.
It should be understood that the inflection point determining unit 41, the curve slicing unit 42 and the processing unit 43 may cooperatively implement the above-described S31 to S34 and possible sub-steps thereof.
In an alternative embodiment, the inflection point determining unit 41 is further configured to obtain a real-time data curve and a historical data curve. The inflection point determining unit 41 is further configured to obtain at least one first inflection point of the real-time data curve and at least one second inflection point of the historical data curve. The first curve inflection point is an extreme point of which the variation degree in the real-time data curve is greater than or equal to a preset fluctuation threshold, and the second curve inflection point is an extreme point of which the variation degree in the historical data curve is greater than or equal to a preset fluctuation threshold. The inflection point determining unit 41 is further configured to combine all the first inflection points and all the second inflection points to obtain a segmented inflection point group.
In an alternative embodiment, the inflection point determining unit 41 is further configured to obtain a distance matrix for all first inflection points and all second inflection points. The distance matrix characterizes distance information for each first knee point and each second knee point. The inflection point determining unit 41 is further configured to obtain a pairing distance of the distance matrix according to a dynamic time normalization algorithm. The pair distance is the smallest cumulative distance from the first knee point to the last first knee point in the matrix. The inflection point determining unit 41 is further configured to determine a segmented inflection point group according to the pairing distance and the inflection point comparison threshold. The inflection point comparison threshold is a similarity threshold determined according to the real-time data curve and the historical data curve.
In an alternative embodiment, the real-time data curve has M first knee points, the historical data curve has N second knee points, and M and N are both positive integers greater than or equal to 1. The inflection point determining unit 41 is further configured to determine whether the pairing distance is less than or equal to an inflection point alignment threshold. The inflection point determining unit 41 is further configured to combine curve inflection points corresponding to the paired distances as a segmented inflection point group if the paired distances are smaller than or equal to the inflection point comparison threshold. The knee point combination is a combination of knee points from the first knee point to the last second knee point according to the minimum cumulative distance. The inflection point determining unit 41 is further configured to determine whether M and N are equal to each other if the pairing distance is greater than the inflection point comparison threshold.
The inflection point determining unit 41 is further configured to, if M is not equal to N, perform a merging operation on the first inflection point and the second inflection point corresponding to the matching distances, and use the merged inflection points as a segment inflection point group.
An electronic device is provided in an embodiment of the present application, and as shown in fig. 10, fig. 10 is a block schematic diagram of an electronic device provided in an embodiment of the present application. The electronic device 60 comprises a memory 61, a processor 62 and a communication interface 63. The memory 61, processor 62 and communication interface 63 are electrically connected to each other, directly or indirectly, to enable transmission or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 61 may be used to store software programs and modules, such as program instructions/modules corresponding to the device detection method provided in the embodiment of the present application, and the processor 62 executes the software programs and modules stored in the memory 61, so as to execute various functional applications and data processing. The communication interface 63 may be used for communicating signaling or data with other node devices. The electronic device 60 may have a plurality of communication interfaces 63 in this application.
The Memory 61 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The processor 62 may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc.
The electronic device 60 may implement any of the device detection methods provided herein. The electronic device 60 may be, but is not limited to, a cell phone, a tablet computer, a notebook computer, a server, or other electronic device with processing capabilities.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In summary, the present application provides a method and a related apparatus for detecting devices based on knee-point comparison, and relates to the field of data processing of industrial automatic control. The method comprises the following steps: matching a real-time data curve of the equipment to be detected with a historical data curve to obtain a segmented inflection point group; the real-time data curve represents the current operation condition of the equipment to be detected, and the historical data curve represents the operation condition of the equipment to be detected under the first working condition; segmenting the real-time data curve and the historical data curve into a plurality of curve segment groups according to the segmented inflection point groups; each curve segment group is provided with a sequence identification, and each curve segment group comprises a first curve segment of the real-time data curve in a first time window corresponding to the sequence identification and a second curve segment of the historical data curve in the first time window; sequentially acquiring curve comparison parameters of each curve segment group according to the sequence identification; the curve comparison parameters comprise curve comparison conditions of the first curve section and the second curve section in a first time window; and when all the curve comparison parameters are matched with the preset comparison threshold value, determining that the equipment to be detected is in a first working condition. The method comprises the steps of obtaining a segmented inflection point group of a real-time data curve and a historical data curve, and automatically carrying out segmented comparison on the two curves to determine that the current running state of the equipment to be detected is a first working condition, so that the reason for the difference of the two curves can be specifically analyzed, and the detection accuracy of the equipment is improved.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. An apparatus detection method based on curve inflection point comparison is characterized in that the method comprises the following steps:
matching a real-time data curve of the equipment to be detected with a historical data curve to obtain a segmented inflection point group; the real-time data curve represents the current operation condition of the equipment to be detected, and the historical data curve represents the operation condition of the equipment to be detected under a first working condition;
segmenting the real-time data curve and the historical data curve into a plurality of curve segment groups according to the segmented inflection point groups; each curve segment group is provided with a sequence identification, and each curve segment group comprises a first curve segment of the real-time data curve in a first time window corresponding to the sequence identification and a second curve segment of the historical data curve in the first time window;
sequentially acquiring curve comparison parameters of each curve segment group according to the sequence identification; the curve comparison parameters comprise curve comparison conditions of the first curve segment and the second curve segment in the first time window;
and when all the curve comparison parameters are matched with a preset comparison threshold value, determining that the equipment to be detected is in the first working condition.
2. The method of claim 1, wherein obtaining a set of segmented inflection points obtained by matching a real-time data curve of the device under test with a historical data curve comprises:
acquiring the real-time data curve and the historical data curve;
acquiring at least one first curve inflection point of the real-time data curve and at least one second curve inflection point of the historical data curve; the first curve inflection point is an extreme point of which the variation degree in the real-time data curve is greater than or equal to a preset fluctuation threshold value, and the second curve inflection point is an extreme point of which the variation degree in the historical data curve is greater than or equal to the preset fluctuation threshold value;
and combining all the first curve inflection points and all the second curve inflection points to obtain the segmented inflection point group.
3. The method of claim 2, wherein combining all of the first inflection points and all of the second inflection points to obtain the set of piecewise inflection points comprises:
acquiring distance matrixes of all the first curve inflection points and all the second curve inflection points; the distance matrix characterizes distance information of each first curve inflection point and each second curve inflection point;
acquiring the pairing distance of the distance matrix according to a dynamic time normalization algorithm; the pairing distance is the minimum cumulative distance from the first curve inflection point to the last second curve inflection point in the distance matrix;
determining the segmented inflection point group according to the pairing distance and an inflection point comparison threshold; the inflection point comparison threshold is a similarity threshold determined according to the real-time data curve and the historical data curve.
4. The method of claim 3, wherein the real-time data curve has M of the first inflection points, the historical data curve has N of the second inflection points, M and N each being a positive integer greater than or equal to 1;
determining the segmented inflection point group according to the pairing distance and an inflection point comparison threshold, wherein the step of determining the segmented inflection point group comprises the following steps:
judging whether the pairing distance is smaller than or equal to the inflection point comparison threshold;
if so, combining the curve inflection points corresponding to the pairing distances to serve as the segmented inflection point group; the curve inflection point combination is the inflection point combination from the first curve inflection point to the last second curve inflection point according to the minimum accumulated distance;
if not, judging whether M and N are equal;
and if the M and the N are not equal, combining the first curve inflection point and the second curve inflection point corresponding to the pairing distance, and taking the combined curve inflection point as the segment inflection point group.
5. An apparatus detecting device based on knee-point comparison, the apparatus comprising:
the inflection point determining unit is used for matching a real-time data curve of the equipment to be detected with a historical data curve to obtain a segmented inflection point group; the real-time data curve represents the current operation condition of the equipment to be detected, and the historical data curve represents the operation condition of the equipment to be detected under a first working condition;
the curve segmentation unit is used for segmenting the real-time data curve and the historical data curve into a plurality of curve segment groups according to the segmented inflection point groups; each curve segment group is provided with a sequence identification, and each curve segment group comprises a first curve segment of the real-time data curve in a first time window corresponding to the sequence identification and a second curve segment of the historical data curve in the first time window;
the processing unit is used for sequentially acquiring curve comparison parameters of each curve segment group according to the sequence identification; the curve comparison parameters comprise curve comparison conditions of the first curve segment and the second curve segment in the first time window;
the processing unit is further configured to determine that the device to be detected is in the first working condition when all the curve comparison parameters are matched with a preset comparison threshold.
6. The apparatus of claim 5, wherein the inflection point determining unit is further configured to obtain the real-time data curve and the historical data curve;
the inflection point determining unit is further used for acquiring at least one first curve inflection point of the real-time data curve and at least one second curve inflection point of the historical data curve; the first curve inflection point is an extreme point of which the variation degree in the real-time data curve is greater than or equal to a preset fluctuation threshold value, and the second curve inflection point is an extreme point of which the variation degree in the historical data curve is greater than or equal to the preset fluctuation threshold value;
the inflection point determining unit is further configured to combine all of the first inflection points and all of the second inflection points to obtain the set of piecewise inflection points.
7. The apparatus of claim 6, wherein the inflection point determining unit is further configured to obtain a distance matrix for all of the first inflection points and all of the second inflection points; the distance matrix characterizes distance information of each first curve inflection point and each second curve inflection point;
the inflection point determining unit is further used for acquiring the pairing distance of the distance matrix according to a dynamic time normalization algorithm; the pairing distance is the minimum cumulative distance from the first curve inflection point to the last second curve inflection point in the distance matrix;
the inflection point determining unit is further configured to determine the segmented inflection point group according to the pairing distance and an inflection point comparison threshold; the inflection point comparison threshold is a similarity threshold determined according to the real-time data curve and the historical data curve.
8. The apparatus of claim 7, wherein the real-time data curve has M of the first inflection points, wherein the historical data curve has N of the second inflection points, and wherein M and N are positive integers greater than or equal to 1;
the inflection point determining unit is further configured to determine whether the pairing distance is less than or equal to the inflection point comparison threshold;
the inflection point determining unit is further configured to, if the pairing distance is smaller than or equal to the inflection point comparison threshold, combine curve inflection points corresponding to the pairing distance as the segment inflection point group; the curve inflection point combination is the inflection point combination from the first curve inflection point to the last second curve inflection point according to the minimum accumulated distance;
the inflection point determining unit is further configured to determine whether M and N are equal to each other if the pairing distance is greater than the inflection point comparison threshold;
and the inflection point determining unit is further configured to perform a merging operation on the first inflection point and the second inflection point corresponding to the pairing distance if M and N are not equal to each other, and use the merged inflection point as the segment inflection point group.
9. An electronic device comprising a processor and a memory, the memory storing machine executable instructions executable by the processor to implement the method of any one of claims 1-4.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010704985.1A CN111811567B (en) | 2020-07-21 | 2020-07-21 | Equipment detection method based on curve inflection point comparison and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010704985.1A CN111811567B (en) | 2020-07-21 | 2020-07-21 | Equipment detection method based on curve inflection point comparison and related device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111811567A true CN111811567A (en) | 2020-10-23 |
| CN111811567B CN111811567B (en) | 2022-03-01 |
Family
ID=72860838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010704985.1A Active CN111811567B (en) | 2020-07-21 | 2020-07-21 | Equipment detection method based on curve inflection point comparison and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111811567B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113656270A (en) * | 2021-07-30 | 2021-11-16 | 招商银行股份有限公司 | Application performance testing method, device, medium and computer program product |
| CN114636828A (en) * | 2022-05-07 | 2022-06-17 | 深圳市帝迈生物技术有限公司 | Sample real-time detection method and device, sample analyzer and storage medium |
| CN116595426A (en) * | 2023-07-17 | 2023-08-15 | 济南大陆机电股份有限公司 | Industrial Internet of things data intelligent acquisition management system |
| CN117870016A (en) * | 2024-03-13 | 2024-04-12 | 梁山恒源热力有限公司 | Real-time monitoring method and system for heating system based on Internet of things |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007062941A (en) * | 2005-08-31 | 2007-03-15 | Daifuku Co Ltd | Article transporting device |
| JP2010093047A (en) * | 2008-10-08 | 2010-04-22 | Ulvac Japan Ltd | Management system of processing device |
| CN102381340A (en) * | 2010-08-27 | 2012-03-21 | 卡斯柯信号有限公司 | Power curve-based speed-raising turnout fault information processing method and device |
| CN103324913A (en) * | 2013-05-29 | 2013-09-25 | 长安大学 | Pedestrian event detection method based on shape features and trajectory analysis |
| CN105243304A (en) * | 2015-08-07 | 2016-01-13 | 厦门美图移动科技有限公司 | Mobile terminal unlocking method and apparatus |
| CN107133343A (en) * | 2017-05-19 | 2017-09-05 | 哈工大大数据产业有限公司 | Big data abnormal state detection method and device based on time series approximate match |
| CN107451004A (en) * | 2017-07-01 | 2017-12-08 | 南京理工大学 | A kind of switch breakdown diagnostic method based on qualitiative trends analysis |
| CN108416362A (en) * | 2018-01-29 | 2018-08-17 | 同济大学 | A kind of track switch abnormity early warning and method for diagnosing faults |
| CN108446184A (en) * | 2018-02-23 | 2018-08-24 | 北京天元创新科技有限公司 | Analyze the method and system of failure root primordium |
| CN110852200A (en) * | 2019-10-28 | 2020-02-28 | 华中科技大学 | Non-contact human body action detection method |
-
2020
- 2020-07-21 CN CN202010704985.1A patent/CN111811567B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007062941A (en) * | 2005-08-31 | 2007-03-15 | Daifuku Co Ltd | Article transporting device |
| JP2010093047A (en) * | 2008-10-08 | 2010-04-22 | Ulvac Japan Ltd | Management system of processing device |
| CN102381340A (en) * | 2010-08-27 | 2012-03-21 | 卡斯柯信号有限公司 | Power curve-based speed-raising turnout fault information processing method and device |
| CN103324913A (en) * | 2013-05-29 | 2013-09-25 | 长安大学 | Pedestrian event detection method based on shape features and trajectory analysis |
| CN105243304A (en) * | 2015-08-07 | 2016-01-13 | 厦门美图移动科技有限公司 | Mobile terminal unlocking method and apparatus |
| CN107133343A (en) * | 2017-05-19 | 2017-09-05 | 哈工大大数据产业有限公司 | Big data abnormal state detection method and device based on time series approximate match |
| CN107451004A (en) * | 2017-07-01 | 2017-12-08 | 南京理工大学 | A kind of switch breakdown diagnostic method based on qualitiative trends analysis |
| CN108416362A (en) * | 2018-01-29 | 2018-08-17 | 同济大学 | A kind of track switch abnormity early warning and method for diagnosing faults |
| CN108446184A (en) * | 2018-02-23 | 2018-08-24 | 北京天元创新科技有限公司 | Analyze the method and system of failure root primordium |
| CN110852200A (en) * | 2019-10-28 | 2020-02-28 | 华中科技大学 | Non-contact human body action detection method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113656270A (en) * | 2021-07-30 | 2021-11-16 | 招商银行股份有限公司 | Application performance testing method, device, medium and computer program product |
| CN113656270B (en) * | 2021-07-30 | 2024-03-08 | 招商银行股份有限公司 | Method, device, medium and computer program product for testing application performance |
| CN114636828A (en) * | 2022-05-07 | 2022-06-17 | 深圳市帝迈生物技术有限公司 | Sample real-time detection method and device, sample analyzer and storage medium |
| CN114636828B (en) * | 2022-05-07 | 2022-10-25 | 深圳市帝迈生物技术有限公司 | Sample real-time detection method and device, sample analyzer and storage medium |
| CN116595426A (en) * | 2023-07-17 | 2023-08-15 | 济南大陆机电股份有限公司 | Industrial Internet of things data intelligent acquisition management system |
| CN116595426B (en) * | 2023-07-17 | 2023-09-26 | 济南大陆机电股份有限公司 | Industrial Internet of things data intelligent acquisition management system |
| CN117870016A (en) * | 2024-03-13 | 2024-04-12 | 梁山恒源热力有限公司 | Real-time monitoring method and system for heating system based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111811567B (en) | 2022-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111811567B (en) | Equipment detection method based on curve inflection point comparison and related device | |
| CN107798672B (en) | Method and system for measuring width of cut tobacco or cut stem and server with system | |
| CN113344134B (en) | Low-voltage distribution monitoring terminal data acquisition abnormality detection method and system | |
| CN109115257B (en) | Method, device, equipment and storage medium for correcting sensor characteristic curve | |
| CN104027100A (en) | Abnormal blood pressure data processing method based on latest historical values | |
| CN109359138A (en) | A kind of method for detecting abnormality and device based on Density Estimator | |
| CN111090685A (en) | Method and device for detecting data abnormal characteristics | |
| CN112990372B (en) | Data processing method, model training device and electronic equipment | |
| CN112465910B (en) | Target shooting distance obtaining method and device, storage medium and electronic equipment | |
| CN114037673A (en) | Hardware connection interface monitoring method and system based on machine vision | |
| CN113342610A (en) | Time sequence data anomaly detection method and device, electronic equipment and storage medium | |
| CN113723467A (en) | Sample collection method, device and equipment for defect detection | |
| CN116304963A (en) | Data processing system suitable for geological disaster early warning | |
| CN108109675B (en) | Laboratory quality control data management system | |
| CN115601564A (en) | Colloid contour detection method and system based on image recognition | |
| CN114092542A (en) | Bolt measuring method and system based on two-dimensional vision | |
| CN113865634A (en) | Detection equipment precision determination method and system based on environment detection | |
| CN114265840A (en) | Abnormality score calculation device, abnormality score calculation method, and storage medium | |
| CN113641848B (en) | Online assembly connection guiding method and system for electronic product | |
| CN112765011B (en) | Quality control state judging method and device and electronic equipment | |
| CN117093947B (en) | Power generation diesel engine operation abnormity monitoring method and system | |
| CN112085053B (en) | Data drift discrimination method and device based on nearest neighbor method | |
| CN112199418B (en) | State identification method, device and equipment for industrial object | |
| CN116452587B (en) | Environment-friendly building structure steel plate defect identification method | |
| Kaminskyi et al. | Calculating the constant in the Hurst index for the time series |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |