CN116520742A - Method for determining threshold value of start-up and stop of data-driven equipment - Google Patents
Method for determining threshold value of start-up and stop of data-driven equipment Download PDFInfo
- Publication number
- CN116520742A CN116520742A CN202310444843.XA CN202310444843A CN116520742A CN 116520742 A CN116520742 A CN 116520742A CN 202310444843 A CN202310444843 A CN 202310444843A CN 116520742 A CN116520742 A CN 116520742A
- Authority
- CN
- China
- Prior art keywords
- value
- data
- threshold
- threshold value
- equipment
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012804 iterative process Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 230000005236 sound signal Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 6
- 238000012423 maintenance Methods 0.000 abstract description 5
- 238000005457 optimization Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0423—Input/output
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/25—Pc structure of the system
- G05B2219/25257—Microcontroller
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a method for determining a threshold value of starting and stopping of data-driven equipment, which belongs to the technical field of signal processing and comprises the following steps: historical data in the set time of the equipment is obtained, iteration is carried out on the minimum value of the historical data in a certain step length, the value of each iteration is a dynamic threshold value, the coincidence times of each dynamic threshold value and the historical data are calculated, the iteration times corresponding to the dividing line are found out through analyzing the distribution change rule of the coincidence times, and the threshold value of start-stop can be accurately obtained according to the iteration times meeting the determination conditions. The method is driven by the data of the equipment, the starting and stopping threshold value of the equipment can be accurately obtained by analyzing the distribution characteristics of the historical data, the participation is not required to be set manually, the applicability is wide, the daily operation and maintenance work can be carried out by the equipment operators, the accuracy and the reliability of the operation and maintenance process are improved, and the safe and continuous operation of the equipment is ensured.
Description
Technical Field
The invention belongs to the technical field of signal processing, and particularly relates to a method for determining a threshold value of starting and stopping of data-driven equipment.
Background
In an automatic factory, the start-up and stop state monitoring of equipment is an important link in the full life cycle management application of the equipment. The method has the advantages that the startup and shutdown states of the equipment are accurately judged, the startup and shutdown states of the equipment are uploaded to the equipment management system, data support can be provided for calculation of key indexes such as the operation time length of the equipment, the service life of the equipment and the time without fault intervals, fine management of enterprises on the equipment is enhanced, the equipment management level is improved, and therefore loss caused by unscheduled shutdown of the equipment is reduced. Taking a rotating device as an example, when the device needs to operate at a lower rotating speed for a long time due to lower load and the like, if the monitoring system always erroneously judges that the device is in a shutdown state, erroneous judgment is caused for a device manager, and errors exist in data acquisition and storage of the monitoring system.
In recent years, many researches on the start-up and stop states of equipment are performed, for example, chinese patent publication No. CN114067297a proposes an equipment switch state identification method based on improved fast RCNN, which includes photographing equipment, constructing an image dataset, constructing an identification model, and training out a switch identification model, so as to identify the switch of the equipment; the Chinese patent publication No. CN112577724B proposes a method for determining a starting and stopping threshold value of a mobile device, a method for monitoring the starting and stopping of the mobile device and a device thereof, wherein the method comprises the steps of acquiring a plurality of historical acceleration effective values of the mobile device, gathering the historical acceleration effective values into two types, and finally taking an average value of class centers of the two types as the starting and stopping threshold value of the mobile device; the chinese patent with publication number CN112446618A proposes a method and apparatus for evaluating the state of a switchgear by combining multiple component indicators, and inputs multiple component measurement indicators of insulating gas inside the switchgear to construct a fault characteristic value vector of the switchgear, so as to output the state of the switchgear.
Existing methods or studies have one or more of the following drawbacks and disadvantages:
1. through the mode of image recognition, need additionally increase the camera to shoot, increase work load, and the image is easily influenced by external factors such as illumination, and the error is great.
2. The model training mode is adopted, a large amount of data is needed as a basis, errors are easy to generate in model identification, and the judging effect is poor.
3. The historical data of the device may have different stages, and the method of cluster analysis may not effectively separate the shutdown data from the startup data, so that an accurate startup and shutdown threshold is not obtained.
4. The manually set threshold value needs to be judged empirically, different equipment has different threshold values, manual calibration workload is large, and subjectivity is high.
5. The running state of the equipment may be in the process of changing, and the state of starting and stopping the equipment is judged by a fixed threshold value, so that misjudgment is easy to generate.
Disclosure of Invention
The invention aims to provide a method for determining a threshold value of starting and stopping of data-driven equipment, so as to solve the problems in the background technology.
The invention realizes the above purpose through the following technical scheme:
a method for determining a threshold value of a device start-up and shutdown driven by data comprises the following steps:
s1: collecting historical index data in the set time of equipment, constructing a historical index array, carrying out fixed-step upward iteration based on the minimum value of the index data in the historical index array, and marking the value obtained by each iteration as a dynamic threshold;
s2: constructing a difference value array based on the dynamic threshold value and the history index array, and constructing a crossing frequency array by using the number of elements, which are negative in the product of the front element and the rear element, in the difference value array;
s3: and screening the crossing times meeting the determined conditions in the crossing times array based on a preset starting and stopping threshold determining condition, and calculating the starting and stopping threshold according to the crossing times.
As a further optimization scheme of the invention, the historical index data of the equipment are vibration signal data, sound signal data, temperature signal data, voltage signal data, current signal data, pressure signal data or rotating speed signal data of the equipment.
As a further optimization scheme of the present invention, the iterative process in step S1 includes:
(1) Calculating the numerical value of the previous set proportion in the history index array, taking the numerical value as an upper limit value, and calculating the value with the minimum numerical value in the history index array, taking the value as a lower limit value;
(2) And (3) performing iterative calculation upwards from the lower limit value with a fixed step length, performing a plurality of iterations to the upper limit value, and sequentially recording the dynamic threshold value obtained during each iteration.
As a further optimization scheme of the invention, the construction of the difference value array in the step S2 comprises the following steps: and subtracting the dynamic threshold value obtained in each iteration from the historical index array to obtain a difference value, and constructing a crossing frequency array based on the number of elements, which are in accordance with the product of the front element and the rear element, in the difference value array and are negative.
As a further optimization scheme of the present invention, the condition for determining the threshold value of startup and shutdown in the step S3 at least includes:
(1) The number of passes around the start-stop threshold should be such that there are a certain number of consecutive elements that remain unchanged in value.
(2) And selecting the iteration times corresponding to the element with the smallest value from all elements meeting the determining condition (1), thereby ensuring that the threshold value is as close to the shutdown value as possible.
As a further optimization scheme of the present invention, the calculating the threshold of startup and shutdown according to the number of times of traversal in step S3 includes:
(1) Finding out the corresponding iteration times according to the distribution rule of the crossing times meeting the determination conditions;
(2) And carrying out iterative computation based on the lower limit value with a fixed step length and corresponding iteration times to obtain a start-stop threshold value.
The invention has the beneficial effects that:
1) The invention provides a method for determining a starting and stopping threshold value of data-driven equipment, which can calculate the starting and stopping threshold value by tracing the historical data sequence of the equipment and completely based on the distribution rule of the data; the operation and maintenance system can assist equipment operators in carrying out daily operation and maintenance work, improve the accuracy and reliability of operation and maintenance processes, and ensure the safe and continuous operation of equipment.
2) The invention firstly proposes an iterative method to calculate the dynamic threshold value and analyze the coincidence times of the dynamic threshold value and the historical data each time, thereby ensuring that the method considers all the historical data and improving the accuracy of calculation;
3) The threshold value provided by the invention is adaptively changed along with the change of data, so that the threshold value can be adapted to equipment in different stages, the threshold value can be dynamically adaptively adjusted under the condition of fluctuation of working conditions, and the start-up and stop states of the equipment can be accurately judged;
4) According to the method provided by the invention, prior knowledge of equipment is not needed, a threshold value or other parameters are not needed to be set manually, calculation and analysis are performed completely according to the distribution characteristics of the data, and the equipment data of unknown parameters can be effectively calculated as the threshold value of starting and stopping.
Drawings
FIG. 1 is a schematic overall flow diagram of the present invention;
FIG. 2 is a diagram of a vibration index history data sequence in accordance with an embodiment of the present invention;
FIG. 3 is a graph showing the variation of the number of passes with the number of iterations in an embodiment of the present invention.
Detailed Description
The invention will now be described in further detail with reference to the accompanying drawings, wherein it is to be understood that the following detailed description is for the purpose of illustration only and is not to be construed as limiting the scope of the invention, as various insubstantial modifications and adaptations of the invention to those skilled in the art may be made in light of the foregoing disclosure.
Example 1
As shown in fig. 1, the present invention provides a method for determining a threshold value of a device start-up and shutdown of a data driver, which includes the following steps:
s1: collecting historical index data in the set time of the equipment, constructing a historical index array, carrying out fixed-step upward iteration based on the minimum value of the index data in the historical index array, and marking the value obtained by each iteration as a dynamic threshold;
s2: constructing a difference value array based on the dynamic threshold value and the historical index array, and constructing a crossing frequency array by using the number of elements which are negative in the difference value array and accord with the product of the front element and the rear element;
s3: and screening the crossing times meeting the determined conditions in the crossing times array based on a preset starting and stopping threshold determining condition, and calculating the starting and stopping threshold according to the crossing times.
In the invention, the historical index data of the equipment is vibration signal data, sound signal data, temperature signal data, voltage signal data, current signal data, pressure signal data or rotating speed signal data of the equipment.
In this embodiment, the device server collects historical index data of the device for a period of time before the device, and constructs an array as L, l= [ L ] 1 ,l 2 ,...,l n ]；
The iterative process in step S1 includes:
(1) Calculating the first 20% of values in the historical index array L and taking the values as an upper limit value, namely L-up, and calculating the minimum value in the historical index array and taking the minimum value as a lower limit value, namely L-down;
(2) Performing iterative calculation from the lower limit value l-down with a fixed step length upwards, performing several iterations to the upper limit value l-up, and sequentially recording the dynamic threshold value T obtained during each iteration i 。
Wherein the total number of iterations is noted as n,at each iteration, a corresponding dynamic threshold T can be obtained i ，T i =l_down+step·i; i is the number of iterations and, i= (1, 2,) n.
The construction process of the crossing times array in the step S2 comprises the following steps:
subtracting the dynamic threshold value T acquired corresponding to each iteration from the historical index array L i And obtaining a difference value, and constructing a difference value array D based on the difference value. At each iteration, a dynamic threshold T is recorded i And the crossing number of the history index array L is recorded as cro i Number of traversals cro i The calculation mode of (2) is as follows:
(1) At each iteration, a dynamic threshold T is constructed i And a difference array D of the history index array L, where d= [ D ] 1 ,d 2 ,...,d n ]；
(2) For each ofArray D in a iterative process i Judging that the array elements meetThe number of elements of the condition is the crossing times cro i 。
(3) When all iterations are completed, recording the pass times cro of each pass i Constructing a crossing frequency array C, wherein C= [ cro ] 1 ,cro 2 ,...,cro i ]。
In the present invention, the condition for determining the threshold of startup and shutdown in step S3 at least includes:
(1) The number of passes around the start-stop threshold should be such that there is a certain number and succession of elements remaining cro i The number is at least greater than i/5, where i is the total number of iterations.
(2) In all cros meeting the determination condition (1) i And selecting the iteration number i_b corresponding to the element with the smallest value from the elements, so as to ensure that the threshold value is as close to the shutdown value as possible.
In step S3, calculating the threshold for startup and shutdown according to the number of times of traversal includes:
(1) Calculating the corresponding iteration times according to a preset starting and stopping threshold value determining condition;
(2) And carrying out iterative computation based on the lower limit value with a fixed step length and corresponding iteration times to obtain a start-stop threshold value.
After finding the iteration times i_b which most meet the above-mentioned determining conditions, calculating the corresponding start-stop threshold value Tag: tag=l_down+step·i_b.
A specific embodiment of the method will be described below in connection with 1 actual processing routine.
1. The equipment server collects historical vibration acceleration index data of the equipment for a period of time before, an array L is constructed, and the distribution situation of the historical data is shown in fig. 2:
2. according to the above step S1, the data set is calculated to have l_up of 0.14, l_down of 0.052, and fixed step size step of 0.003, according to the calculation formula of the iteration number:the corresponding number of iterations n is 300.
3. According to the step S2, the corresponding crossing times are calculated to form an array C. The change of the crossing times with the iteration times is shown in fig. 3:
4. and (3) finding out the iteration times which are relatively stable in the crossing times and as small as possible in the threshold according to the determination conditions required in the step (S3), and finally analyzing that the iteration times i_b meeting the requirements is 30.
5. According to a calculation formula of the start-stop threshold value Tag: tag=l_Down+step.i_b, and the corresponding start-stop threshold Tag is calculated to be 0.074.
From the processing results of the cases, the method can accurately obtain the start-stop threshold of the equipment through the distribution characteristics of the historical data, the calculated 0.074 can accurately divide the stop data and the start-stop data, the processing process does not need to be manually participated, and the method has good adaptability to different types of equipment.
It should be noted that, the method of the present invention may be implemented in an upper computer software in a signal processing manner, or may also be implemented in other manners, such as a digital chip, a hardware circuit, etc.
The above examples merely represent a few embodiments of the present invention, which are described in more detail and are not to be construed as limiting the scope of the present invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention.
Claims (6)
1. A method for determining a threshold value of starting and stopping a device driven by data is characterized by comprising the following steps: the method comprises the following steps:
s1: collecting historical index data in the set time of equipment, constructing a historical index array, carrying out fixed-step upward iteration based on the minimum value of the index data in the historical index array, and marking the value obtained by each iteration as a dynamic threshold;
s2: constructing a difference value array based on the dynamic threshold value and the history index array, and constructing a crossing frequency array by using the number of elements, which are negative in the product of the front element and the rear element, in the difference value array;
s3: and screening the crossing times meeting the determined conditions in the crossing times array based on a preset starting and stopping threshold determining condition, and calculating the starting and stopping threshold according to the crossing times.
2. A method of determining a data-driven device start-stop threshold as defined in claim 1, wherein: the historical index data of the equipment is vibration signal data, sound signal data, temperature signal data, voltage signal data, current signal data, pressure signal data or rotating speed signal data of the equipment.
3. A method of determining a data-driven device start-stop threshold as defined in claim 1, wherein: the iterative process in step S1 includes:
s1.1: calculating the numerical value of the previous set proportion in the history index array, taking the numerical value as an upper limit value, and calculating the value with the minimum numerical value in the history index array, taking the value as a lower limit value;
s1.2: and (3) performing iterative calculation upwards from the lower limit value with a fixed step length, performing a plurality of iterations to the upper limit value, and sequentially recording the dynamic threshold value obtained during each iteration.
4. A method of determining a data-driven device start-stop threshold as defined in claim 1, wherein: the constructing of the difference value array in the step S2 comprises the following steps: and subtracting the dynamic threshold value obtained in each iteration from the historical index array to obtain a difference value, and constructing a difference value array based on the difference value.
5. The method for determining the threshold of a data-driven device on/off as defined in claim 4, wherein: the condition for determining the threshold value of startup and shutdown in the step S3 at least includes:
(1) The number of passes around the start-stop threshold should be such that there are a certain number of consecutive elements that remain unchanged in value.
(2) And selecting the iteration times corresponding to the element with the smallest value from all elements meeting the determining condition (1), thereby ensuring that the threshold value is as close to the shutdown value as possible.
6. A method of determining a data-driven device start-stop threshold as defined in claim 1, wherein: in the step S3, calculating the threshold for startup and shutdown according to the number of times of traversal includes:
(1) Calculating the corresponding iteration times according to a preset starting and stopping threshold value determining condition, and finding out the corresponding iteration times;
(2) And carrying out iterative computation based on the lower limit value with a fixed step length and corresponding iteration times to obtain a start-stop threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310444843.XA CN116520742A (en) | 2023-04-24 | 2023-04-24 | Method for determining threshold value of start-up and stop of data-driven equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310444843.XA CN116520742A (en) | 2023-04-24 | 2023-04-24 | Method for determining threshold value of start-up and stop of data-driven equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116520742A true CN116520742A (en) | 2023-08-01 |
Family
ID=87402370
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310444843.XA Pending CN116520742A (en) | 2023-04-24 | 2023-04-24 | Method for determining threshold value of start-up and stop of data-driven equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116520742A (en) |
-
2023
- 2023-04-24 CN CN202310444843.XA patent/CN116520742A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN110659173A (en) | Operation and maintenance system and method | |
| CN111144435B (en) | Electric energy abnormal data monitoring method based on LOF and verification filtering framework | |
| CN111709465B (en) | Intelligent identification method for rough difference of dam safety monitoring data | |
| CN113344134B (en) | Low-voltage distribution monitoring terminal data acquisition abnormality detection method and system | |
| CN115982602B (en) | Photovoltaic transformer electrical fault detection method | |
| CN116028887B (en) | Analysis method of continuous industrial production data | |
| CN112598539B (en) | Wind power curve optimization calculation and outlier detection method for wind generating set | |
| CN111669123A (en) | Method and device for fault diagnosis of photovoltaic string | |
| CN117406026A (en) | Power distribution network fault detection method suitable for distributed power supply | |
| CN113918642A (en) | Data filtering, monitoring and early warning method based on power Internet of things equipment | |
| CN111367909A (en) | Health management method and system of intelligent manufacturing equipment | |
| CN113098912B (en) | User account abnormity identification method and device, electronic equipment and storage medium | |
| CN116956189A (en) | Current abnormality detection system, method, electronic equipment and medium | |
| CN116520742A (en) | Method for determining threshold value of start-up and stop of data-driven equipment | |
| CN115809805A (en) | Power grid multi-source data processing method based on edge calculation | |
| CN112732773B (en) | Method and system for checking uniqueness of relay protection defect data | |
| CN114330141A (en) | Fan main shaft bearing service life prediction method based on GRU (generalized regression Unit) super-parameter optimization | |
| CN115295016A (en) | Equipment running state monitoring method, device, equipment and storage medium | |
| CN114970311A (en) | Method for establishing remote module life prediction model and life prediction method | |
| CN111625525B (en) | Environment data repairing/filling method and system | |
| CN112699609B (en) | Diesel engine reliability model construction method based on vibration data | |
| CN115511106B (en) | Method, device and readable storage medium for generating training data based on time sequence data | |
| CN117435964B (en) | Equipment state evaluation method and system based on data diagnostic instrument | |
| CN117932501B (en) | Electric energy meter running state management method and 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 |