CN116108331A - Method and device for generating industrial equipment monitoring data prediction curve - Google Patents
Method and device for generating industrial equipment monitoring data prediction curve Download PDFInfo
- Publication number
- CN116108331A CN116108331A CN202310199211.1A CN202310199211A CN116108331A CN 116108331 A CN116108331 A CN 116108331A CN 202310199211 A CN202310199211 A CN 202310199211A CN 116108331 A CN116108331 A CN 116108331A
- Authority
- CN
- China
- Prior art keywords
- prediction curve
- data set
- monitoring data
- time
- clue
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Development Economics (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application discloses a method for generating a prediction curve of industrial equipment monitoring data, which is applied to a prediction curve generating device, and comprises the following steps: acquiring monitoring data of industrial equipment; determining an initial prediction curve data set according to the monitoring data; and carrying out standardized shaping on the initial prediction curve data set to generate a target prediction curve data set. The method improves the generation efficiency of the industrial equipment monitoring data prediction curve, and ensures the uniqueness of the generated result through standardized shaping.
Description
Technical Field
The method relates to the technical field of data acquisition in the intelligent manufacturing industry, in particular to a method and a device for generating a prediction curve of industrial equipment monitoring data.
Background
In the production operation process of industrial equipment, various equipment sensors can continuously generate operation state monitoring data such as temperature, height, humidity, speed, current, voltage and the like, and the operation state of the equipment can be known at any time through collecting, comparing and analyzing the monitoring data, so that the hidden danger of equipment operation faults can be found in time, and the occurrence of safety accidents is reduced.
However, not all of the collected monitoring data need to be compared and analyzed, as in most cases, the condition monitoring data generated during normal operation of the device is conventional data, which is typically generated when the operating condition of the device is unchanged, and remains substantially unchanged in value or changes periodically and regularly. The conventional data is not helpful for people to judge the hidden trouble of the equipment, is data generated when the running state of the equipment changes or the equipment runs abnormally, and is called boundary data, and the boundary data obviously changes back and forth in value or deviates from the conventional data obviously. Only the boundary data are acquired, cut, compared and analyzed in a targeted and accurate mode, so that a great deal of network transmission cost and background service computing power can be saved.
If accurate acquisition and cutting of boundary data are to be realized, a prediction curve of equipment operation is used in a data cutting link, the prediction curve is used as a reference standard of monitoring data, the deviation degree of the actual operation curve of the equipment is judged, and if the deviation degree is obvious, the acquisition of the boundary data is indicated that cutting and subsequent analysis are needed; if the deviation degree is 'not obvious', the collected regular data is indicated to be directly discarded.
For the prediction curve, there are two main expression forms: one is a form of a prediction curve function, such as: y=asin (Bx), wherein: x represents time or time sequence number, y represents predicted value, A, B is constant, and the predicted value y corresponding to time can be obtained by calculating the time x of the input function; the other is in the form of a prediction curve dataset, such as: [3.00, 3.63, 4.24, 4.82, 5.35, 5.83, 6.24, 6.56, 6.80, 6.95, 7.00, … ], and the predicted value of the corresponding moment can be obtained by searching by inputting the time sequence number of the data set. The two expression forms are essentially the same, the predicted value is obtained by calculation or search according to the time value, and the application range of the expression form of the data set is wider from the angle of application range, and the expression form is not limited by the waveform of the monitored data curve, so that the expression form is commonly applied in the industry.
The prediction curve of the industrial equipment monitoring data is generally generated in advance before the equipment is put into production, for the industrial equipment running periodically, the current commonly used prediction curve generation method is "system acquisition manual judgment", and an expert cuts a section of complete period curve from a plurality of sections of curves of the equipment running actually according to professional experience to serve as the prediction curve. However, as the number of devices and the monitoring indexes are increased, the method also gradually reveals the following defects: 1, the prediction curve generation process is not automatically completed by the system, so that the prediction curve generation efficiency is reduced; 2, the generated prediction curve data set is not unique in form, for example: the current output by the same alternator can be considered as a data set shaped like a sine wave or a data set shaped like a cosine wave, which are identical in nature except that they are 90 degrees out of phase, but in manifestation they are two mutually different data sets.
Disclosure of Invention
The application provides a method and a device for generating a prediction curve of industrial equipment monitoring data, which are used for solving at least one technical problem existing in the prior art.
In one aspect, the present application provides a method for generating a prediction curve of industrial equipment monitoring data, including:
acquiring monitoring data of industrial equipment;
determining an initial prediction curve data set according to the monitoring data;
and carrying out standardized shaping on the initial prediction curve data set to generate a target prediction curve data set.
In some embodiments, the acquiring monitoring data of the industrial device comprises:
multiple pieces of monitoring data of an industrial device at multiple times are acquired, the multiple times including a current time and at least one historical time.
In some embodiments, the determining an initial prediction curve data set from the monitoring data comprises:
acquiring monitoring data of industrial equipment at the current moment;
comparing whether the monitoring data at the current moment and the monitoring data at the historical moment are matched data values or not, if so, adding a clue at the current moment in the clue table;
judging whether the current time of the clue at the last time still has a matched data value or not, if so, the clue is an effective clue, and merging the clues at the current time and the last time in a clue table;
for the validity clue, judging whether the validity of the validity clue is maintained for a complete period, and if so, successfully learning the initial prediction curve.
In some embodiments, the normalizing the initial prediction curve data set to generate a target prediction curve data set includes:
acquiring a learned initial prediction curve data set;
searching the minimum value in the initial prediction curve data set;
judging whether the minimum value in the initial prediction curve data set is unique:
if yes, taking the moment corresponding to the unique minimum value as a new starting point of the prediction curve data set;
if not, calculating the time length between the minimum values of adjacent identical values, comparing to obtain the maximum value of the time length, and taking the starting time of the maximum time length as a new starting point of the prediction curve data set;
moving the data subset before the new starting point to the tail of the data set;
and generating a target prediction curve data set after standardized shaping.
On the other hand, the application provides a generating device of industrial equipment monitoring data prediction curve, which comprises the following components:
the monitoring data acquisition unit is used for acquiring monitoring data of the industrial equipment;
a prediction curve learning unit for determining an initial prediction curve data set according to the monitoring data;
and the prediction curve shaping unit is used for carrying out standardized shaping on the initial prediction curve data set to generate a target prediction curve data set.
In some embodiments, the acquiring monitoring data of the industrial device comprises:
multiple pieces of monitoring data of an industrial device at multiple times are acquired, the multiple times including a current time and at least one historical time.
In some embodiments, the determining an initial prediction curve data set from the monitoring data comprises:
acquiring monitoring data of industrial equipment at the current moment;
comparing whether the monitoring data at the current moment and the monitoring data at the historical moment are matched data values or not, if so, adding a clue at the current moment in the clue table;
judging whether the current time of the clue at the last time still has a matched data value or not, if so, the clue is an effective clue, and merging the clues at the current time and the last time in a clue table;
for the validity clue, judging whether the validity of the validity clue is maintained for a complete period, and if so, successfully learning the initial prediction curve.
In some embodiments, the normalizing the initial prediction curve data set to generate a target prediction curve data set includes:
acquiring a learned initial prediction curve data set;
searching the minimum value in the initial prediction curve data set;
judging whether the minimum value in the initial prediction curve data set is unique:
if yes, taking the moment corresponding to the unique minimum value as a new starting point of the prediction curve data set;
if not, calculating the time length between the minimum values of adjacent identical values, comparing to obtain the maximum value of the time length, and taking the starting time of the maximum time length as a new starting point of the prediction curve data set;
moving the data subset before the new starting point to the tail of the data set;
and generating a target prediction curve data set after standardized shaping.
In another aspect, the present application provides an electronic device, comprising:
the system comprises at least one processor and a memory communicatively connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the industrial equipment monitoring data prediction curve generation method described herein.
In another aspect, the present application provides a storage medium having a computer program stored thereon, characterized in that: the program when executed by a processor implements the steps of the method for generating a prediction curve for industrial equipment monitoring data described herein.
The beneficial effects of this application embodiment lie in: after the system collects the monitoring data, a prediction curve is automatically generated, so that the generation efficiency of the prediction curve is improved; by carrying out standardized shaping on the prediction curve, the uniqueness of the generated result is ensured.
Drawings
In order to more clearly illustrate the technical solutions described by the present invention, the drawings that are required for the technical solutions will be briefly described below. It should be noted that the following descriptions with reference to the drawings are only some embodiments of the present invention, and those skilled in the art can obtain other embodiments according to these drawings and the descriptions thereof in different scenarios.
FIG. 1a is a schematic diagram of an embodiment of the present application for simulating direct threshold determination without using a prediction curve as a reference;
FIG. 1b is a schematic diagram of an exemplary embodiment of the present application for threshold determination using a prediction curve as a reference;
FIG. 2a is a schematic diagram of a prediction curve 1 of monitoring data generated at a certain moment in time in an embodiment of the present application;
FIG. 2b is a schematic diagram of a prediction curve 2 of monitoring data that simulates the start of generation at another time in an embodiment of the present application;
FIG. 2c is a schematic diagram of a prediction curve 3 of monitoring data that simulates the start of generation at another time in an embodiment of the present application;
FIG. 3 is a flow chart of a method for generating a prediction curve of monitoring data of an industrial equipment according to an embodiment of the present application;
FIG. 4 is a schematic block diagram of an apparatus for generating a prediction curve of monitoring data of an industrial equipment according to another embodiment of the present application;
FIG. 5 is a flowchart of a method for learning prediction curves of monitoring data of an industrial equipment according to an embodiment of the present application;
FIG. 6 is a flowchart of a method for normalizing and shaping an industrial equipment monitoring data prediction curve according to an embodiment of the present application;
FIG. 7a is a schematic diagram of a prediction curve before modeling normalization shaping in an embodiment of the present application;
FIG. 7b is a schematic diagram of a prediction curve after modeling normalization shaping in accordance with an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Description of the embodiments
Fig. 1a and 1b are schematic diagrams of threshold judgment of industrial equipment monitoring data. The conventional data generated during normal operation of the device, which is generally generated when the operating state of the device is unchanged, remain substantially unchanged in value or change periodically and regularly. For periodic monitoring data, if threshold judgment is directly performed without using a prediction curve as a reference, potential boundary data may not be correctly identified. FIG. 1a simulates a schematic diagram of direct threshold determination without using a prediction curve as a reference, wherein a piece of boundary data is not correctly identified. Fig. 1b is a schematic diagram of performing threshold judgment by using a prediction curve as a reference, firstly calculating the difference between the monitoring data set and the prediction curve data set, and then performing threshold judgment on the difference data set, so that boundary data in the difference data set can be easily and correctly identified.
As shown in fig. 2a, 2b, and 2c, the prediction curves of the monitoring data are respectively generated at a plurality of different moments. For industrial equipment which operates periodically, the values of the monitoring data repeatedly appear after the period T is passed no matter from which time, so that the same piece of monitoring data has different expression forms due to different starting times of generating the prediction curve. Fig. 2a, 2b, 2c simulate the situation where the generation of the monitoring data prediction curve starts at three different moments T0, T10, T20, respectively.
Fig. 3 is a flow chart of a method for generating a prediction curve of detection data of an industrial device according to an embodiment of the present application, which includes:
s1, acquiring monitoring data of industrial equipment;
s2, determining an initial prediction curve data set according to the monitoring data;
and S3, carrying out standardized shaping on the initial prediction curve data set to generate a target prediction curve data set.
The method for generating the industrial equipment detection data prediction curve improves the generation efficiency of the industrial equipment detection data prediction curve, and ensures the uniqueness of a generated result through standardized shaping.
In some embodiments, the present application further provides an industrial equipment monitoring data prediction curve generating device, including:
the monitoring data acquisition unit is used for acquiring monitoring data of the industrial equipment;
a prediction curve learning unit for determining an initial prediction curve data set according to the monitoring data;
and the prediction curve shaping unit is used for carrying out standardized shaping on the initial prediction curve data set to generate a target prediction curve data set.
The device for generating the industrial equipment detection data prediction curve improves the generation efficiency of the industrial equipment detection data prediction curve, and ensures the uniqueness of a generated result through standardized shaping.
Referring to fig. 4, a schematic block diagram of an apparatus for generating a prediction curve of monitoring data of an industrial equipment according to another embodiment of the present application is shown. The present embodiment provides an apparatus 800 for generating a prediction curve of industrial equipment monitoring data, including:
a monitoring data acquisition unit 810 for acquiring monitoring data of the industrial equipment;
a monitoring data storage unit 820 for storing the acquired monitoring data;
a prediction curve learning unit 830 for determining an initial prediction curve data set according to the monitoring data; for example, processing and computing the monitored data, learning an initial prediction curve data set when a condition is satisfied;
a prediction curve shaping unit 840, configured to perform standardized shaping on the initial prediction curve data set, and generate a target prediction curve data set; for example, the learned initial prediction curve data set is normalized and shaped to generate a unique target prediction curve data set;
the result data management unit 850 is configured to store, modify, discard, or the like the prediction curve data set.
Wherein the monitoring data acquired by the monitoring data acquisition unit 810 is a data stream periodically generated by the monitored device. Typically, the monitored data is a set of two-dimensional time series data sets: the first dimension is the acquisition time, the acquisition time of a certain piece of monitoring data can be assumed to be T0, and the acquisition time of the subsequent monitoring data is the relative time based on T0; the second dimension is a monitoring data value, which represents the monitoring data value corresponding to the current acquisition time. In many application scenarios, the monitoring data has a strict periodicity at the time of acquisition, for example, once every 100ms, and the two-dimensional time series data set can be simplified into a single-dimensional data set, that is, only the dimension of the monitoring data value, and the simplification does not affect the correctness and accuracy of the method.
As shown in fig. 5, a flowchart of a method for learning a prediction curve of industrial equipment monitoring data is provided. The corresponding system program of the method circularly processes the monitoring data generated by the industrial equipment and learns a prediction curve data set according to the judgment condition. The method comprises the following steps:
s301, acquiring monitoring data of industrial equipment at the current moment;
s302, comparing whether the monitoring data at the current moment and the monitoring data at the historical moment are matched data values, if so, executing step S303, and if not, executing step S305. For example, comparing whether the difference between the monitored data at the current time and the monitored data at the historical time is within a preset range, if so, the monitored data at the current time and the monitored data at the historical time are matched data values, otherwise, the monitored data at the current time and the monitored data at the historical time are not matched data values;
s303, adding a clue at the current moment in a clue table;
s304, judging whether the matching data value still exists at the current moment of the clue of the previous moment, if so, executing a step S306, and if not, executing a step S305;
s305, invalidating a cable line in the last time, deleting the cable line from the cable line table, and then acquiring monitoring data of industrial equipment at the next time;
s306, the last time line cable is effective, and the cables at the current time and the last time are combined in the cable list;
s307, judging whether the validity of the effective clue is maintained for a complete period, if so, executing step S308, and if not, acquiring monitoring data of the industrial equipment at the next moment;
s308, learning an initial prediction curve is successful, and the period of the curve is the duration of the clue;
in step S302, the data types of the monitoring data at the current time and the monitoring data at the historical time may be integer or boolean, and when comparing whether the difference between the monitoring data at the current time and the monitoring data at the historical time is within the preset range, it may be directly determined whether the two integer data values are equal for the integer data, but generally it is not possible to directly determine the equality relationship between the two data values for the floating point data. We can define: if the relationship between the two floating point numbers a, b satisfies: i a-b < = epsilon (where epsilon is a sufficiently small number, which in the schematic provided in this application may be set to 0.05), then the difference between the two floating point numbers is considered to be within a preset range.
The clues defined in step S303 refer to: if the difference between the monitored data at two different times (e.g., the monitored data at the current time and the monitored data at the historical time) is within the preset range, it is possible that they are at two times of "different periods, the same phase", and if this is the case, the difference between the monitored data at all times subsequent to the two times one-to-one is within the preset range and lasts for one complete period. Our goal is to find both times. However, the difference values of the monitoring data at all the two moments do not meet the requirement of 'different periods and the same phases' within a preset range, in fact, in most cases, the difference values are only accidental, whether the difference values meet the requirement of 'different periods and the same phases', and continuous verification is needed by using the follow-up monitoring data. Therefore, we call a clue that the difference between the monitored data at two times is within a preset range but needs to be further verified at a subsequent time.
The "last time" in step S304 is referred to as "current time". In the application, the sequence of defining the data acquisition time is as follows: "earlier time", "last time", "current time", "next time", "later time". Here, "earlier time" and "last time" are collectively referred to as "history time", and "next time" and "later time" are collectively referred to as "later time". As the monitoring data collection of the industrial equipment is continuously carried out, the next moment of the last moment becomes the current moment as time goes on; the "next time" of the "current time" becomes the "current time" of the "next time".
In step S306, the threads at the current time and the previous time are combined in the thread table, and the reason for combining is: as described above, since the thread generated at a certain time is required to be further verified at a subsequent time (to verify whether there is a matching data value), step S306 needs to determine whether the thread generated at the current time and the thread generated at the previous time and required to be further verified at the current time are the same thread, if so, the threads at the current time and the previous time are combined in the thread table to avoid that the same thread corresponds to a plurality of thread records. The merging method comprises the following steps: and (3) retaining the information of the initial matching time (earliest matching time) of the last time cue, retaining the information of the latest matching time (latest matching time) of the current time cue, and combining two cue records in the cue table into one cue record.
In step S307, the method for judging whether the validity has been maintained for a complete period is: for each thread generated at each time, it is necessary to continuously verify whether there is a matching data value at a subsequent time, if a certain thread satisfies: the earliest matching time of the following period is just equal to the latest matching time of the preceding period, the two periods are adjacent periods, and all monitoring data at corresponding times in the whole period pass the verification of the matching data value, namely the thread continuously keeps validity in a complete period.
The duration of the thread in step S307 is the length from the earliest matching time of the thread to the time experienced by the current time.
As shown in fig. 6, a flow chart of a standardized shaping method of the industrial equipment monitoring data prediction curve is provided. The system program corresponding to the method can perform standardized shaping on the prediction curves generated by the same monitoring data at different moments, convert the prediction curves into the prediction curves with unique expression forms, and ensure the uniqueness of the generated results. The method comprises the following steps:
s401, acquiring a learned initial prediction curve data set;
s402, searching for the minimum value in the initial prediction curve data set;
s403, judging whether the minimum value in the initial prediction curve data set is unique, if yes, executing step S406, and if not, executing step S404;
s404, calculating the time length between the minimum values of adjacent identical values, and comparing to obtain the maximum value of the time length;
s405, taking the starting time of the maximum duration as a new starting point of the prediction curve data set, and then executing step S407;
s406, taking the moment corresponding to the unique minimum value as a new starting point of the prediction curve data set;
s407, moving the data subset before the new starting point to the tail part of the data set;
and S408, generating a target prediction curve data set after standardized shaping.
The minimum value described in S402 refers to a method of shaping the initial prediction curve data set in a complete cycle by using the time corresponding to the minimum value as the starting time of the prediction curve data set. Similarly, if the time corresponding to the maximum value or the average value is used as the starting time of the prediction curve data set, a maximum value shaping method, an average value shaping method, or the like may be defined, which is not limited in this application.
The adjacent same value minimum value in step S404 refers to: under the condition that the minimum values are not unique, a plurality of minimum values with equal values can appear, one moment is selected from the moments corresponding to the minimum values to serve as a new starting point of the prediction curve data set, and the specific method is that the time length between two adjacent minimum values with the same value is calculated respectively, the maximum value of the time length is obtained through comparison among the time lengths, and the starting moment of the maximum time length is used as the new starting point of the prediction curve data set.
As shown in fig. 7a and 7b, the prediction curves before and after the standardized shaping are schematic diagrams. In which fig. 7a simulates a prediction curve diagram before normalization shaping, from time T28 to time T188 shows a complete cycle of the prediction curve data set, with a curve period of 160, having two identical minimum values (minimum 1 and minimum 2) at times T54 and T152, respectively. Fig. 7b simulates a schematic diagram of a prediction curve after normalization shaping, first, the time period 98 from the first minimum value T54 to the second minimum value T152 and the time period 62 from the second minimum value T152 to the first minimum value T54 (i.e. T214 of the next cycle) are calculated respectively, then the magnitudes (98 > 62) of these two time periods are compared, the time T54 corresponding to the first minimum value is selected as a new starting point of the prediction curve data set, and finally the prediction curve data set after normalization shaping is generated: from time T54 to time T214, the curve period is still 160.
Fig. 8 is a schematic structural diagram of an embodiment of the electronic device of the present application. The apparatus includes:
one or more processors 910, and a memory 920, one processor 910 being illustrated in fig. 8.
The apparatus for performing the industrial apparatus monitoring data prediction curve generation method may further include: an input device 930, and an output device 940.
The processor 910, memory 920, input device 930, and output device 940 may be connected by a bus or other means, for example in fig. 8.
The memory 920 is used as a non-volatile computer readable storage medium, and may be used to store a non-volatile software program, a non-volatile computer executable program, and a module, such as a program instruction/module corresponding to the industrial equipment monitoring data prediction curve generating method in the embodiment of the present application. The processor 910 performs various functional applications of the server and data processing by running non-volatile software programs, instructions, and modules stored in the memory 920.
The input device 930 may receive input numeric or character information and generate signals related to user settings and function control of the industrial equipment monitoring data prediction curve generation device. The output device 940 may include a display device such as a display screen.
The one or more modules are stored in the memory 920 that, when executed by the one or more processors 910, perform the industrial equipment monitoring data prediction curve generation method of any of the method embodiments described above.
The product can execute the method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present application.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
From the above description of embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus a general purpose hardware platform, or may be implemented by hardware. Based on such understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the related art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. A method for generating a prediction curve of industrial equipment monitoring data, comprising:
acquiring monitoring data of industrial equipment;
determining an initial prediction curve data set according to the monitoring data;
and carrying out standardized shaping on the initial prediction curve data set to generate a target prediction curve data set.
2. The method of claim 1, wherein the acquiring monitoring data of the industrial device comprises:
multiple pieces of monitoring data of an industrial device at multiple times are acquired, the multiple times including a current time and at least one historical time.
3. The method of claim 2, wherein the determining an initial prediction curve dataset from the monitoring data comprises:
acquiring monitoring data of industrial equipment at the current moment;
comparing whether the monitoring data at the current moment and the monitoring data at the historical moment are matched data values or not, if so, adding a clue at the current moment in the clue table;
judging whether the current time of the clue at the last time still has a matched data value or not, if so, the clue is an effective clue, and merging the clues at the current time and the last time in a clue table;
for the validity clue, judging whether the validity of the validity clue is maintained for a complete period, and if so, successfully learning the initial prediction curve.
4. The method of claim 1, wherein said normalizing the initial prediction curve data set to generate a target prediction curve data set comprises:
acquiring a learned initial prediction curve data set;
searching the minimum value in the initial prediction curve data set;
judging whether the minimum value in the initial prediction curve data set is unique:
if yes, taking the moment corresponding to the unique minimum value as a new starting point of the prediction curve data set;
if not, calculating the time length between the minimum values of adjacent identical values, comparing to obtain the maximum value of the time length, and taking the starting time of the maximum time length as a new starting point of the prediction curve data set;
moving the data subset before the new starting point to the tail of the data set;
and generating a target prediction curve data set after standardized shaping.
5. An apparatus for generating a prediction curve of industrial equipment monitoring data, comprising:
the monitoring data acquisition unit is used for acquiring monitoring data of the industrial equipment;
a prediction curve learning unit for determining an initial prediction curve data set according to the monitoring data;
and the prediction curve shaping unit is used for carrying out standardized shaping on the initial prediction curve data set to generate a target prediction curve data set.
6. The apparatus of claim 5, wherein the acquiring monitoring data of the industrial device comprises:
multiple pieces of monitoring data of an industrial device at multiple times are acquired, the multiple times including a current time and at least one historical time.
7. The apparatus of claim 6, wherein the determining an initial prediction curve data set from the monitoring data comprises:
acquiring monitoring data of industrial equipment at the current moment;
comparing whether the monitoring data at the current moment and the monitoring data at the historical moment are matched data values or not, if so, adding a clue at the current moment in the clue table;
judging whether the current time of the clue at the last time still has a matched data value or not, if so, the clue is an effective clue, and merging the clues at the current time and the last time in a clue table;
for the validity clue, judging whether the validity of the validity clue is maintained for a complete period, and if so, successfully learning the initial prediction curve.
8. The apparatus of claim 5, wherein said normalizing the initial prediction curve data set to generate a target prediction curve data set comprises:
acquiring a learned initial prediction curve data set;
searching the minimum value in the initial prediction curve data set;
judging whether the minimum value in the initial prediction curve data set is unique:
if yes, taking the moment corresponding to the unique minimum value as a new starting point of the prediction curve data set;
if not, calculating the time length between the minimum values of adjacent identical values, comparing to obtain the maximum value of the time length, and taking the starting time of the maximum time length as a new starting point of the prediction curve data set;
moving the data subset before the new starting point to the tail of the data set;
and generating a target prediction curve data set after standardized shaping.
9. An electronic device, comprising:
at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of any one of claims 1-4.
10. A storage medium having a computer program stored thereon, characterized by: which program, when being executed by a processor, carries out the steps of the method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310199211.1A CN116108331A (en) | 2023-03-03 | 2023-03-03 | Method and device for generating industrial equipment monitoring data prediction curve |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310199211.1A CN116108331A (en) | 2023-03-03 | 2023-03-03 | Method and device for generating industrial equipment monitoring data prediction curve |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116108331A true CN116108331A (en) | 2023-05-12 |
Family
ID=86259860
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310199211.1A Pending CN116108331A (en) | 2023-03-03 | 2023-03-03 | Method and device for generating industrial equipment monitoring data prediction curve |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116108331A (en) |
-
2023
- 2023-03-03 CN CN202310199211.1A patent/CN116108331A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109960653A (en) | Regression testing method, device, equipment and storage medium | |
| CN111782460A (en) | Large-scale log data anomaly detection method and device and storage medium | |
| CN111459698A (en) | Database cluster fault self-healing method and device | |
| CN111614491A (en) | Power monitoring system oriented safety situation assessment index selection method and system | |
| CN115048370B (en) | Artificial intelligence processing method for big data cleaning and big data cleaning system | |
| CN108763064B (en) | Code test generation method and device based on black box function and machine learning | |
| CN115309575A (en) | Micro-service fault diagnosis method, device and equipment based on graph convolution neural network | |
| CN115640159A (en) | Micro-service fault diagnosis method and system | |
| JP6190539B2 (en) | Log analysis apparatus, log analysis system, log analysis method, and computer program | |
| CN109815697A (en) | Wrong report behavior processing method and processing device | |
| CN112949711B (en) | Neural network model multiplexing training method and device for software defined satellites | |
| Huang et al. | Dissimilarity‐based test case prioritization through data fusion | |
| CN117632905A (en) | Database management method and system based on cloud use records | |
| CN117033209A (en) | AI model training method, BIOS testing method, device, equipment and storage medium | |
| CN116108331A (en) | Method and device for generating industrial equipment monitoring data prediction curve | |
| CN110968518A (en) | Analysis method and device for automatic test log file | |
| CN115470504A (en) | Data risk analysis method and server combined with artificial intelligence | |
| CN114416417A (en) | System abnormity monitoring method, device, equipment and storage medium | |
| CN111708670B (en) | Method and device for determining task time parameters in real-time operation system and vehicle | |
| CN113688403A (en) | Intelligent contract vulnerability detection method and device based on symbolic execution verification | |
| CN112907055A (en) | Data processing aging test method and device | |
| CN112906914A (en) | Rail transit IT equipment fault analysis method and device and electronic equipment | |
| CN116302762B (en) | Evaluation method and system for fault location application based on red-blue countermeasure | |
| CN112379656A (en) | Processing method, device, equipment and medium for detecting abnormal data of industrial system | |
| CN115237606B (en) | Edge calculation control system |
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 |