CN113917263B - Method and system for secondary monitoring of abnormal energy consumption based on prediction data - Google Patents
Method and system for secondary monitoring of abnormal energy consumption based on prediction data Download PDFInfo
- Publication number
- CN113917263B CN113917263B CN202111176936.6A CN202111176936A CN113917263B CN 113917263 B CN113917263 B CN 113917263B CN 202111176936 A CN202111176936 A CN 202111176936A CN 113917263 B CN113917263 B CN 113917263B
- Authority
- CN
- China
- Prior art keywords
- point
- parameter
- calculation
- monitoring
- calculation result
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 105
- 238000005265 energy consumption Methods 0.000 title claims abstract description 69
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004364 calculation method Methods 0.000 claims abstract description 142
- 238000001746 injection moulding Methods 0.000 claims abstract description 19
- 230000005856 abnormality Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 11
- 238000001125 extrusion Methods 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 abstract description 31
- 230000000694 effects Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 239000003550 marker Substances 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Injection Moulding Of Plastics Or The Like (AREA)
Abstract
The invention discloses a method and a system for monitoring abnormal energy consumption secondarily based on prediction data, which comprises the following steps: obtaining a relevant point of the first monitoring point according to the output data of the injection molding machine; calculating a first preset calculation rule according to the relevant point to obtain a first calculation result; when the first calculation result meets the first preset condition, point abnormity marking is carried out on the first monitoring point; calculating a second preset calculation rule according to the relevant point; when the calculation result meets the second preset condition, performing mode abnormity marking on the first monitoring point; and performing discrete monitoring on the point set marked by the point abnormity and the point set marked by the mode abnormity by using an energy consumption curve as a standard to obtain a first monitoring result. The method solves the technical problems that in the prior art, a large number of error detection points exist, more interference data are captured and detection omission is abnormal when a detection mode is abnormal, and the precision is low.
Description
Technical Field
The invention relates to the field of data monitoring, in particular to a method and a system for abnormal energy consumption secondary monitoring based on prediction data.
Background
The injection molding machine is one of the most main energy consumption devices in plastic processing enterprises as a high-energy-consumption production device, the production process of the injection molding machine is complex, the energy flow direction is changeable, and the problem of energy consumption of the injection molding machine is solved, so that the development of the injection molding industry is concerned. The abnormal detection is defined as an analysis task for detecting data with a mode deviating from normal data, and the abnormal detection problem of the equipment is always a hot problem to be researched, and the abnormal detection problem about the energy consumption is also important.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
the prior art has a large number of error detection points, and has the technical problems of capturing more interference data, missing detection abnormality and low precision when a detection mode is abnormal.
Disclosure of Invention
The embodiment of the application provides a method and a system for monitoring abnormal energy consumption secondarily based on prediction data, and solves the technical problems that in the prior art, the number of error detection points is large, when a mode is detected to be abnormal, more interference data are captured, the detection omission abnormality exists, and the precision is low, so that the purposes of passing through a quick and effective intelligent algorithm, independent detection is carried out on point abnormality and mode abnormality of extrusion equipment, the detection omission rate and the error detection rate can be effectively reduced, high precision is achieved, and the technical effects of saving operation resources and having advantages in quick detection are achieved.
In view of the above, the present invention has been developed to provide a method that overcomes, or at least partially solves, the above-mentioned problems.
In a first aspect, an embodiment of the present application provides a method for monitoring abnormal energy consumption secondarily based on prediction data, where the method includes: acquiring output data of an injection molding machine, and acquiring a first monitoring point according to the output data; obtaining a relevant point of the first monitoring point according to the output data; calculating a first preset calculation rule according to the relevant point to obtain a first calculation result; judging whether the first calculation result meets a first preset condition or not, and when the first calculation result meets the first preset condition, performing point abnormity marking on the first monitoring point; calculating a second preset calculation rule according to the relevant point to obtain a second calculation result; judging whether the second calculation result meets a second preset condition or not, and when the calculation result meets the second preset condition, performing mode abnormity marking on the first monitoring point; obtaining a point set of point anomaly markers and a point set of mode anomaly markers in the output data; and performing discrete monitoring on the point set marked by the point abnormity and the point set marked by the mode abnormity by using an energy consumption curve as a standard to obtain a first monitoring result.
On the other hand, the application also provides a system for monitoring abnormal energy consumption secondarily based on the prediction data, and the system comprises: the first obtaining unit is used for obtaining output data of the injection molding machine and obtaining a first monitoring point according to the output data; the second obtaining unit is used for obtaining the relevant point of the first monitoring point according to the output data; a third obtaining unit, configured to perform calculation according to the correlation point according to a first preset calculation rule, so as to obtain a first calculation result; the first judgment unit is used for judging whether the first calculation result meets a first preset condition or not, and when the first calculation result meets the first preset condition, point abnormity marking is carried out on the first monitoring point; a fourth obtaining unit, configured to perform calculation of a second preset calculation rule according to the correlation point to obtain a second calculation result; the second judging unit is used for judging whether the second calculation result meets a second preset condition or not, and when the calculation result meets the second preset condition, the first monitoring point is marked with a mode abnormity; a fifth obtaining unit configured to obtain a point set of a point abnormality flag and a point set of a pattern abnormality flag in the output data; and the sixth obtaining unit is used for performing discrete monitoring on the point set of the point abnormal marks and the point set of the mode abnormal marks by taking an energy consumption curve as a standard to obtain a first monitoring result.
In a third aspect, an embodiment of the present invention provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor, where the transceiver, the memory, and the processor are connected via the bus, and when the computer program is executed by the processor, the method for controlling output data includes any one of the steps described above.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps in the method for controlling output data according to any one of the above.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the related points of the first monitoring point are obtained according to the output data of the injection molding machine; calculating a first preset calculation rule according to the relevant point to obtain a first calculation result; when the first calculation result meets the first preset condition, point abnormity marking is carried out on the first monitoring point; calculating a second preset calculation rule according to the relevant point to obtain a second calculation result; when the calculation result meets the second preset condition, performing mode abnormity marking on the first monitoring point; obtaining a point set of point anomaly markers and a point set of mode anomaly markers in the output data; and performing discrete monitoring on the point set marked by the point abnormity and the point set marked by the mode abnormity by using an energy consumption curve as a standard to obtain a first monitoring result. And then reach through quick effectual intelligent algorithm, to the unusual and mode anomaly of extrusion equipment go on detecting alone, can effectual reduction miss detection rate and false retrieval rate, have higher precision to have the technological effect of advantage on saving the operation resource and detecting fast.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
Fig. 1 is a schematic flowchart of a method for performing secondary abnormal energy consumption monitoring based on prediction data according to an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating a monitoring result obtained by an energy consumption curve in a method for monitoring abnormal energy consumption twice based on prediction data according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a system for performing secondary abnormal energy consumption monitoring based on predicted data according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device for executing a method of controlling output data according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a first determining unit 14, a fourth obtaining unit 15, a second determining unit 16, a fifth obtaining unit 17, a sixth obtaining unit 18, a bus 1110, a processor 1120, a transceiver 1130, a bus interface 1140, a memory 1150, an operating system 1151, an application 1152 and a user interface 1160.
Detailed Description
In the description of the embodiments of the present invention, it should be apparent to those skilled in the art that the embodiments of the present invention can be embodied as methods, apparatuses, electronic devices, and computer-readable storage media. Thus, embodiments of the invention may be embodied in the form of: entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), a combination of hardware and software. Furthermore, in some embodiments, embodiments of the invention may also be embodied in the form of a computer program product in one or more computer-readable storage media having computer program code embodied in the medium.
The computer-readable storage media described above may take any combination of one or more computer-readable storage media. The computer-readable storage medium includes: an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium include: a portable computer diskette, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, a flash memory, an optical fiber, a compact disc read-only memory, an optical storage device, a magnetic storage device, or any combination thereof. In embodiments of the invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, device, or apparatus.
Summary of the application
The method, the device and the electronic equipment are described through the flow chart and/or the block diagram.
It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner. Thus, the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
The embodiments of the present invention will be described below with reference to the drawings.
Example one
As shown in fig. 1, an embodiment of the present application provides a method for monitoring abnormal energy consumption secondarily based on prediction data, where the method includes:
step S100: acquiring output data of an injection molding machine, and acquiring a first monitoring point according to the output data;
step S200: obtaining a relevant point of the first monitoring point according to the output data;
specifically, the output data of the injection molding machine is energy consumption data output by the injection molding machine through real-time detection, and relevant points of a first monitoring point and the first monitoring point, namely a data check point and relevant points before and after the check point, are obtained according to the output data. And taking the variance between the check point and the points before and after the check point as a judgment standard, and taking the latest third point as the check point and taking the two points before and after the check point as a reference when the energy consumption data of the injection molding machine equipment is output.
Step S300: calculating a first preset calculation rule according to the relevant point to obtain a first calculation result;
specifically, after the mean and the variance of the two points before and after the correlation point are calculated to obtain the mean and the variance of the four points before and after the correlation point, the calculation and judgment of a preset calculation rule may be performed, specifically, the calculation and judgment rule is g (x)i) The parameters are used for judging whether the check point climbs or descends; f (x)i) The parameters are used for judging whether the check point and the front and rear points have large dislocation or not; and u (x)i) And (4) parameters, namely judging whether the standard deviation of each two points before and after the check point is abnormal, and calculating through each judgment parameter to obtain a final calculation result.
Step S400: judging whether the first calculation result meets a first preset condition or not, and when the first calculation result meets the first preset condition, performing point abnormity marking on the first monitoring point;
further, in the determining whether the first calculation result satisfies a first preset condition, step S400 in this embodiment of the present application further includes:
step S410: and when the conditions that the first parameter is greater than zero, the second parameter is greater than zero and any one of the third parameters is less than zero are met simultaneously, the first calculation result meets the first preset condition.
Specifically, whether the first calculation result satisfies a first preset condition is determined,the first preset condition is when the first parameter g (x)i) Greater than zero, the second parameter f (x)i) Greater than zero, the third parameter u (x)i) When any one of the parameters is less than zero and the condition is satisfied simultaneously, namely g (x)i)>0,f(xi)>0,u1(xi) < 0 or u2(xi) If the value is less than 0, the first calculation result meets the first preset condition. When the first calculation result meets the first preset condition, it can be judged that the check point is suspected to be abnormal, and the first monitoring point is marked with point abnormality, namely, the first monitoring point is marked in the extrusion period to be used as data for secondary detection. The abnormity marking algorithm only aims at point abnormity, is not influenced by mode abnormity, and has the technical effect of real-time performance.
Step S500: calculating a second preset calculation rule according to the relevant point to obtain a second calculation result;
specifically, the initial detection of the pattern abnormality is to perform calculation judgment of a second preset calculation rule according to the correlation point, specifically, the calculation judgment rule is f (x)i) The parameters are used for judging whether the interval between the check point and the next point is within a normal fluctuation range; g (x)i) The parameters are used for judging whether the check point and the previous point have the characteristic cliff with abnormal mode; and p (x)i) And (4) parameters, judging whether platforms after cliff break exist on two sides of the check point, and calculating through all judgment parameters to obtain a final second calculation result.
Step S600: judging whether the second calculation result meets a second preset condition or not, and when the calculation result meets the second preset condition, performing mode abnormity marking on the first monitoring point;
further, in the determining whether the second calculation result satisfies a second preset condition, step S600 in this embodiment of the present application further includes:
step S610: and when the conditions that the fourth parameter is less than zero, the fifth parameter is greater than zero and the sixth parameter is greater than zero are simultaneously met, the second calculation result meets the second preset condition.
Specifically, it judgesJudging whether the second calculation result meets a second preset condition, wherein the second preset condition is that the fourth parameter f (x) is obtainedi) Greater than zero, the fifth parameter g (x)i) Greater than zero, the sixth parameter p (x)i) Greater than zero conditions being satisfied simultaneously, i.e. f (x)i)<0,g(xi)>0,p(xi)>And when 0, the second calculation result meets the second preset condition. When the second calculation result meets the second preset condition, it can be preliminarily determined whether the mode is abnormal in a period from the check point to a next check point (or no next check point), and once the above conditions are met, a point between the check point and the next check point is marked as data to be detected, that is, the first monitoring point is marked with the mode abnormality. The above-mentioned abnormal marking algorithm is directed at the pattern abnormality, and will be affected by the point abnormality detection, but can be combined with the data given by the point abnormality detection to perform repeated detection and erasing, and has the technical effect of real-time performance.
Step S700: obtaining a point set of point abnormity marks and a point set of mode abnormity marks in the output data;
step S800: and performing discrete monitoring on the point set marked by the point abnormity and the point set marked by the mode abnormity by using an energy consumption curve as a standard to obtain a first monitoring result.
Specifically, the processing result of the primary detection positioning of the energy consumption data of the injection molding machine is two columns of data, one column is a point abnormal set, the other column is a mode abnormal set, and the two columns of data are subjected to secondary detection. And performing discrete monitoring on the point set of the point abnormal marker and the point set of the mode abnormal marker by using an energy consumption curve as a standard and using an energy consumption curve predicted by a traditional BP neural network as a base standard to obtain a first monitoring result. If the marked point is beyond the normal energy consumption range, namely the point abnormality or the pattern abnormality, the marked point is captured and displayed on the last abnormality capture image. .
As shown in fig. 2, further, in which the point set of the point anomaly flag and the point set of the pattern anomaly flag are discretely monitored by using an energy consumption curve as a standard to obtain a first monitoring result, step S800 in this embodiment of the present application further includes:
step S810: obtaining the energy consumption curve according to a BP neural network model, wherein the energy consumption curve is an energy consumption prediction curve under a complete extrusion period;
step S820: projecting the energy consumption curve to the point set of point anomaly markers and the point set of pattern anomaly markers;
step S830: obtaining distance information and fluctuation information in the energy consumption curve and the marking point set;
step S840: obtaining a first distance threshold and a first fluctuation threshold;
step S850: and performing discrete monitoring judgment on the distance information and the fluctuation information based on the first distance threshold and the first fluctuation threshold to obtain the first monitoring result.
Specifically, the energy consumption curve is obtained according to a BP neural network model, the BP neural network model is a multilayer feedforward neural network trained according to an error back propagation algorithm, the BP neural network model has any complex mode classification capability and excellent multidimensional function mapping capability, and is the neural network which is most widely applied, and the energy consumption curve is an energy consumption prediction curve of the injection molding machine in a complete extrusion period. And the secondary detection is to project the energy consumption prediction curve of one complete extrusion cycle on the mark data of the point set marked by the point abnormity and the point set marked by the mode abnormity. And detecting the distance and the fluctuation threshold value between the marked data set and the predicted energy consumption curve, determining abnormal energy consumption points when the distance exceeds the fluctuation threshold value and the distance threshold value, determining the optimal parameters by experiments before simulation by the fluctuation threshold value and the distance average value, and performing discrete monitoring judgment on the distance information and the fluctuation information based on the first distance threshold value and the first fluctuation threshold value to obtain the abnormal energy consumption secondary monitoring result of the injection molding machine. The mark sequence is detected by using a prediction model and is captured when the mark sequence exceeds a fluctuation threshold value to form a new capture curve, so that the missing detection rate and the false detection rate can be effectively reduced, the precision is high, and certain advantages are achieved in the aspects of saving operation resources and rapid detection.
Further, step S850 in this embodiment of the present application further includes:
step S851: the correlation points comprise a first correlation point, a second correlation point, a third correlation point and a fourth correlation point;
step S852: obtaining a first variance of the first correlation point and the second correlation point, and obtaining a second variance of the third correlation point and the fourth correlation point;
step S853: the first parameter is obtained through formula calculation, and the calculation formula is as follows:
g(xi)=c-|xi+1-xi-1|
and calculating to obtain a second parameter through a formula, wherein the calculation formula is as follows:
and calculating to obtain a third parameter through a formula, wherein the calculation formula is as follows:
u1(xi)=v1(xi)-b
u2(xi)=v2(xi)-b
wherein c is a constant, b is a constant, xiIs the first monitoring point, xi-1Is a second correlation point, xi+1Is the third point of relation, v1(xi) Is a first variance, v2(xi) Is the second variance;
step S854: and obtaining the first calculation result according to the first parameter, the second parameter and the third parameter.
Specifically, the related points of the first monitoring point are two points before and after the check point, including a first related point, a second related point, a third related point and a fourth related point, a first variance between the first two points before the check point, namely the first related point and the second related point, is obtained through calculation, and the second two points after the check point, namely the first related point and the second related point, are obtained through calculation in the same wayA second variance of the third correlation point and the fourth correlation point. By the formula g (x)i)=c-|xi+1-xi-1I calculating to obtain a first parameter, wherein c is a constant and xi-1Is a second correlation point, xi+1And judging whether the check point climbs or descends as a third relevant point. By the formulaCalculating to obtain a second parameter, wherein xiAnd judging whether the inspection point and the front and rear points have large dislocation or not as a first monitoring point. By the formula u1(xi)=v1(xi) -b and u2(xi)=v2(xi) B calculating a third parameter, where b is a constant, v1(xi) Is a first variance, v2(xi) And judging whether the standard deviation of two points before and after the check point is abnormal or not as a second variance. According to the first parameter, the second parameter and the third parameter, judging whether a preset condition is met, namely g (x)i)>0,f(xi)>0,u1(xi) < 0 or u2(xi) And when the first calculation result meets the first preset condition, point abnormity marking is carried out on the first monitoring point, and the algorithm only aims at point abnormity, is not influenced by mode abnormity and has the technical effect of real-time property.
Further, step S854 in this embodiment further includes:
step S8541: and obtaining a fourth parameter through formula calculation, wherein the formula is as follows:
f(xi)=|xi-xi+1|-b
and calculating to obtain a fifth parameter through a formula, wherein the calculation formula is as follows:
g(xi)=|xi-xi-1|-c
and calculating to obtain a sixth parameter through a formula, wherein the calculation formula is as follows:
p(xi)=|m1(xi)-m2(xi)|-a
wherein a is a constant, b is a constant, c is a constant, m1(xi) Is the mean value of the third correlation point and the fourth correlation point, m2(xi) The average value of the first correlation point and the second correlation point is obtained;
step S8542: and obtaining the second calculation result according to the fourth parameter, the fifth parameter and the sixth parameter.
Specifically, by the formula f (x)i)=|xi-xi+1And b, calculating to obtain a fourth parameter, wherein b is a constant, and judging whether the interval between the check point and the subsequent point is within a normal fluctuation range or not, wherein the fluctuation of the energy consumption point in the period is within the fluctuation range even in the abnormal period. By the formula g (x)i)=|xi-xi-1And c, calculating to obtain a fifth parameter, wherein c is a constant, and judging whether the feature cliff with abnormal mode exists at the check point and the previous point. By the formula p (x)i)=|m1(xi)-m2(xi) The sixth parameter is obtained by calculating the value of | -a, wherein a is a constant and m1(xi) Is the mean of the third correlation point and the fourth correlation point, m2(xi) And judging whether platforms after cliff break exist on two sides of the check point or not according to the mean value of the first relevant point and the second relevant point. According to the fourth parameter, the fifth parameter and the sixth parameter, judging whether a preset condition is met, namely f (x)i)<0,g(xi)>0,p(xi)>And 0, acquiring the second calculation result, and marking the point abnormality of the first monitoring point when the second calculation result meets the second preset condition.
Further, the embodiment of the present application further includes:
step S910: and outputting a first abnormal capture graph according to the first monitoring result.
Specifically, the abnormal capture image after secondary detection is output according to the first monitoring result, the mark sequence is detected by using a prediction model and is captured when the mark sequence exceeds a fluctuation threshold value, a new capture curve is formed, and the method is visual and accurate. The method can effectively reduce the data missing rate and the false detection rate, has higher precision, and has the technical effects of saving operation resources and having certain advantages in rapid detection.
To sum up, the method and the system for monitoring abnormal energy consumption secondarily based on the prediction data provided by the embodiment of the application have the following technical effects:
the related points of the first monitoring point are obtained according to the output data of the injection molding machine; calculating a first preset calculation rule according to the relevant point to obtain a first calculation result; when the first calculation result meets the first preset condition, point abnormity marking is carried out on the first monitoring point; calculating a second preset calculation rule according to the relevant point to obtain a second calculation result; when the calculation result meets the second preset condition, performing mode abnormity marking on the first monitoring point; obtaining a point set of point anomaly markers and a point set of mode anomaly markers in the output data; and performing discrete monitoring on the point set marked by the point abnormity and the point set marked by the mode abnormity by using an energy consumption curve as a standard to obtain a first monitoring result. And then reach through quick effectual intelligent algorithm, to the unusual and mode anomaly of extrusion equipment go on detecting alone, can effectual reduction miss detection rate and false retrieval rate, have higher precision to have the technological effect of advantage on saving the operation resource and detecting fast.
Example two
Based on the same inventive concept as the method for monitoring the abnormal energy consumption secondarily based on the prediction data in the foregoing embodiment, the present invention further provides a system for monitoring the abnormal energy consumption secondarily based on the prediction data, as shown in fig. 3, the system includes:
the first obtaining unit 11 is used for obtaining output data of the injection molding machine and obtaining a first monitoring point according to the output data;
a second obtaining unit 12, wherein the second obtaining unit 12 is configured to obtain a relevant point of the first monitoring point according to the output data;
a third obtaining unit 13, where the third obtaining unit 13 is configured to perform calculation of a first preset calculation rule according to the relevant point, and obtain a first calculation result;
a first judging unit 14, where the first judging unit 14 is configured to judge whether the first calculation result meets a first preset condition, and when the first calculation result meets the first preset condition, perform point anomaly marking on the first monitoring point;
a fourth obtaining unit 15, where the fourth obtaining unit 15 is configured to perform calculation of a second preset calculation rule according to the relevant point, so as to obtain a second calculation result;
a second judging unit 16, where the second judging unit 16 is configured to judge whether the second calculation result meets a second preset condition, and when the calculation result meets the second preset condition, perform a mode abnormality marking on the first monitoring point;
a fifth obtaining unit 17, where the fifth obtaining unit 17 is configured to obtain a point set of a point anomaly flag and a point set of a pattern anomaly flag in the output data;
a sixth obtaining unit 18, where the sixth obtaining unit 18 is configured to perform discrete monitoring on the point set of the point anomaly flag and the point set of the pattern anomaly flag by using an energy consumption curve as a standard, and obtain a first monitoring result.
Further, the system further comprises:
a seventh obtaining unit, configured to obtain the energy consumption curve according to a BP neural network model, where the energy consumption curve is an energy consumption prediction curve in a complete extrusion cycle;
a first projection unit for projecting the energy consumption curve to the set of points of the point anomaly marker and the set of points of the pattern anomaly marker;
an eighth obtaining unit, configured to obtain distance information and fluctuation information in the energy consumption curve and the set of marked points;
a ninth obtaining unit configured to obtain a first distance threshold value and a first fluctuation threshold value;
a tenth obtaining unit, configured to perform discrete monitoring determination on the distance information and the fluctuation information based on the first distance threshold and the first fluctuation threshold, and obtain the first monitoring result.
Further, the system further comprises:
the first correlation unit is used for the correlation points to comprise a first correlation point, a second correlation point, a third correlation point and a fourth correlation point;
an eleventh obtaining unit, configured to obtain a first variance of the first correlation point and the second correlation point, and obtain a second variance of the third correlation point and the fourth correlation point;
a twelfth obtaining unit, configured to obtain the first parameter through formula calculation;
a thirteenth obtaining unit configured to obtain a second parameter by formula calculation;
a fourteenth obtaining unit, configured to obtain a third parameter through formula calculation;
a fifteenth obtaining unit configured to obtain the first calculation result according to the first parameter, the second parameter, and the third parameter.
Further, the system further comprises:
a sixteenth obtaining unit, configured to obtain a fourth parameter through formula calculation;
a seventeenth obtaining unit, configured to obtain a fifth parameter through formula calculation;
an eighteenth obtaining unit, configured to obtain a sixth parameter through formula calculation;
a nineteenth obtaining unit, configured to obtain the second calculation result according to the fourth parameter, the fifth parameter, and the sixth parameter.
Further, the system further comprises:
and the first output unit is used for outputting a first abnormal capture graph according to the first monitoring result.
Various changes and specific examples of the method for secondarily monitoring abnormal energy consumption based on the prediction data in the first embodiment of fig. 1 are also applicable to the system for secondarily monitoring abnormal energy consumption based on the prediction data in the present embodiment, and through the foregoing detailed description of the method for secondarily monitoring abnormal energy consumption based on the prediction data, those skilled in the art can clearly know the implementation method of the system for secondarily monitoring abnormal energy consumption based on the prediction data in the present embodiment, so for the brevity of the description, detailed descriptions are not repeated here.
In addition, an embodiment of the present invention further provides an electronic device, which includes a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the transceiver, the memory, and the processor are connected via the bus, and when the computer program is executed by the processor, the processes of the method for controlling output data are implemented, and the same technical effects can be achieved, and are not described herein again to avoid repetition.
Exemplary electronic device
Specifically, referring to fig. 4, an embodiment of the present invention further provides an electronic device, which includes a bus 1110, a processor 1120, a transceiver 1130, a bus interface 1140, a memory 1150, and a user interface 1160.
In an embodiment of the present invention, the electronic device further includes: a computer program stored on the memory 1150 and executable on the processor 1120, the computer program, when executed by the processor 1120, implementing the various processes of the method embodiments of controlling output data described above.
A transceiver 1130 for receiving and transmitting data under the control of the processor 1120.
In embodiments of the invention in which a bus architecture (represented by bus 1110) is used, bus 1110 may include any number of interconnected buses and bridges, with bus 1110 connecting various circuits including one or more processors, represented by processor 1120, and memory, represented by memory 1150.
The bus 1110 may also connect various other circuits such as peripherals, voltage regulators, or power management circuits to provide an interface between the bus 1110 and the transceiver 1130, as is well known in the art. Therefore, the embodiments of the present invention will not be further described.
The transceiver 1130 may be one element or may be multiple elements, such as multiple receivers and transmitters, providing a means for communicating with various other apparatus over a transmission medium. For example: the transceiver 1130 receives external data from other devices, and the transceiver 1130 transmits data processed by the processor 1120 to other devices. Depending on the nature of the computer device, a user interface 1160 may also be provided, such as: touch screen, physical keyboard, display, mouse, speaker, microphone, trackball, joystick, stylus.
It is to be appreciated that in embodiments of the invention, the memory 1150 may further include memory located remotely with respect to the processor 1120, which may be coupled to a server via a network. One or more portions of the above-described network may be an ad hoc network, an intranet, an extranet, a virtual private network, a local area network, a wireless local area network, a wide area network, a wireless wide area network, a metropolitan area network, the internet, a public switched telephone network, a plain old telephone service network, a cellular telephone network, a wireless fidelity network, and a combination of two or more of the above. For example, the cellular telephone network and the wireless network may be global mobile communications devices, code division multiple access devices, global microwave interconnect access devices, general packet radio service devices, wideband code division multiple access devices, long term evolution devices, LTE frequency division duplex devices, LTE time division duplex devices, long term evolution advanced devices, universal mobile communications devices, enhanced mobile broadband devices, mass machine type communications devices, ultra-reliable low-latency communications devices, and the like.
It is to be understood that the memory 1150 in embodiments of the present invention can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory. Wherein the nonvolatile memory includes: read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, or flash memory.
The volatile memory includes: random access memory, which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as: static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronous link dynamic random access memory, and direct memory bus random access memory. The memory 1150 of the electronic device described in the embodiments of the invention includes, but is not limited to, the above and any other suitable types of memory.
In an embodiment of the present invention, memory 1150 stores the following elements of operating system 1151 and application programs 1152: an executable module, a data structure, or a subset thereof, or an expanded set thereof.
Specifically, the operating system 1151 includes various device programs, such as: a framework layer, a core library layer, a driver layer, etc. for implementing various basic services and processing hardware-based tasks. Applications 1152 include various applications such as: media player, browser, used to realize various application services. A program implementing a method of an embodiment of the invention may be included in application program 1152. The application programs 1152 include: applets, objects, components, logic, data structures, and other computer device-executable instructions that perform particular tasks or implement particular abstract data types.
In addition, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements each process of the above method for controlling output data, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
The above description is only a specific implementation of the embodiments of the present invention, but the scope of the embodiments of the present invention is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the embodiments of the present invention, and all such changes or substitutions should be covered by the scope of the embodiments of the present invention. Therefore, the protection scope of the embodiments of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. A secondary monitoring method for abnormal energy consumption based on prediction data is disclosed, wherein the method comprises the following steps:
acquiring output data of an injection molding machine, and acquiring a first monitoring point according to the output data;
obtaining a relevant point of the first monitoring point according to the output data;
calculating a first preset calculation rule according to the relevant point to obtain a first calculation result, wherein the calculation result comprises the following steps:
the correlation points comprise a first correlation point, a second correlation point, a third correlation point and a fourth correlation point;
obtaining a first variance of the first correlation point and the second correlation point, and obtaining a second variance of the third correlation point and the fourth correlation point;
the first parameter is obtained through formula calculation, and the calculation formula is as follows:
and calculating to obtain a second parameter through a formula, wherein the calculation formula is as follows:
and calculating to obtain a third parameter through a formula, wherein the calculation formula is as follows:
wherein,is a constant number of times, and is,is a constant number of times, and is,is a first monitoring point, and is a second monitoring point,as a second point of relevance,as a third point of relevance,in order to be the first variance, the first variance is,;
obtaining the first calculation result according to the first parameter, the second parameter and the third parameter;
judging whether the first calculation result meets a first preset condition, and when the first calculation result meets the first preset condition, performing point abnormity marking on the first monitoring point, wherein the judging whether the first calculation result meets the first preset condition further comprises:
when the conditions that the first parameter is greater than zero, the second parameter is greater than zero and any one of the third parameters is less than zero are met simultaneously, the first calculation result meets the first preset condition;
calculating a second preset calculation rule according to the relevant point to obtain a second calculation result, wherein the calculation result comprises the following steps:
and obtaining a fourth parameter through formula calculation, wherein the formula is as follows:
f
2
(x
i
)=|x
i
-x
i+1
|-b
2
and calculating to obtain a fifth parameter through a formula, wherein the calculation formula is as follows:
g
2
(x
i
)=|x
i
-x
i-1
|-c
2
and calculating to obtain a sixth parameter through a formula, wherein the calculation formula is as follows:
p(x
i
)=|m
1
(x
i
)-m
2
(x
i
)|-a
wherein a is a constant and b2Is a constant, c2Is a constant number of times, and is,m 1 (x i )is the average of the third correlation point and the fourth correlation point,m 2 (x i )the average value of the first correlation point and the second correlation point is obtained;
obtaining the second calculation result according to the fourth parameter, the fifth parameter and the sixth parameter;
judging whether the second calculation result meets a second preset condition, and when the calculation result meets the second preset condition, performing mode abnormity marking on the first monitoring point, wherein the judging whether the second calculation result meets the second preset condition further comprises:
when the conditions that the fourth parameter is less than zero, the fifth parameter is greater than zero and the sixth parameter is greater than zero are simultaneously met, the second calculation result meets the second preset condition;
obtaining a point set of point anomaly markers and a point set of mode anomaly markers in the output data;
obtaining an energy consumption curve according to a BP neural network model, wherein the energy consumption curve is an energy consumption prediction curve under a complete extrusion cycle;
and performing discrete monitoring on the point set marked by the point abnormity and the point set marked by the mode abnormity by using the energy consumption curve as a standard to obtain a first monitoring result.
2. The method of claim 1, wherein the discretely monitoring the point set of point anomaly markers and the point set of pattern anomaly markers using the energy consumption curve as a criterion to obtain a first monitoring result, further comprises:
projecting the energy consumption curve to the point set of point anomaly markers and the point set of pattern anomaly markers;
obtaining distance information and fluctuation information in the energy consumption curve and the marking point set;
obtaining a first distance threshold and a first fluctuation threshold;
and performing discrete monitoring judgment on the distance information and the fluctuation information based on the first distance threshold and the first fluctuation threshold to obtain the first monitoring result.
3. The method of claim 1, wherein the method further comprises:
and outputting a first abnormal capture graph according to the first monitoring result.
4. A system for abnormal energy consumption secondary monitoring based on predictive data, wherein the system comprises:
the first acquisition unit is used for acquiring output data of the injection molding machine and acquiring a first monitoring point according to the output data;
the second obtaining unit is used for obtaining the relevant point of the first monitoring point according to the output data;
a third obtaining unit, configured to perform calculation of a first preset calculation rule according to the correlation point to obtain a first calculation result;
the first correlation unit is used for the correlation points to comprise a first correlation point, a second correlation point, a third correlation point and a fourth correlation point;
a fourth obtaining unit, configured to obtain a first variance of the first correlation point and the second correlation point, and obtain a second variance of the third correlation point and the fourth correlation point;
a fifth obtaining unit, configured to obtain the first parameter through a formula calculation, where the formula calculation is as follows:
a sixth obtaining unit, configured to obtain the second parameter through a formula calculation, where the formula calculation is as follows:
a seventh obtaining unit, configured to obtain the third parameter through a formula calculation, where the formula calculation is as follows:
wherein,is a constant number of times, and is,is a constant number of times, and is,is a first monitoring point, and is a second monitoring point,as a second point of relevance,as a third point of relevance,in order to be the first variance, the first variance is,;
an eighth obtaining unit, configured to obtain the first calculation result according to the first parameter, the second parameter, and the third parameter;
the first judging unit is used for judging whether the first calculation result meets a first preset condition or not, and when the first calculation result meets the first preset condition, the first monitoring point is marked with point abnormity;
the first processing unit is used for determining that the first calculation result meets the first preset condition when any one of the conditions that the first parameter is greater than zero, the second parameter is greater than zero and the third parameter is less than zero is met simultaneously;
a ninth obtaining unit, configured to perform calculation of a second preset calculation rule according to the correlation point, and obtain a second calculation result;
a tenth obtaining unit, configured to obtain the fourth parameter through a formula calculation, where the formula calculation is as follows:
f 2 (x i )=|x i -x i+1 |-b 2 ;
an eleventh obtaining unit, configured to obtain the fifth parameter through a formula calculation, where the formula calculation is as follows:
g 2 (x i )=|x i -x i-1 |-c 2 ;
a twelfth obtaining unit, configured to obtain the sixth parameter through a formula calculation, where the formula calculation is as follows:
p(x
i
)=|m
1
(x
i
)-m
2
(x
i
)|-a
wherein a is a constant and b2Is a constant number c2Is a constant number of times, and is,m 1 (x i )is the average of the third correlation point and the fourth correlation point,m 2 (x i )the average value of the first correlation point and the second correlation point is obtained;
a thirteenth obtaining unit configured to obtain the second calculation result according to the fourth parameter, the fifth parameter, and the sixth parameter;
the second judging unit is used for judging whether the second calculation result meets a second preset condition or not, and when the calculation result meets the second preset condition, the first monitoring point is marked with a mode abnormity;
the second processing unit is used for determining that the second calculation result meets the second preset condition when the conditions that the fourth parameter is smaller than zero, the fifth parameter is larger than zero and the sixth parameter is larger than zero are met simultaneously;
a fourteenth obtaining unit configured to obtain a point set of a point abnormality flag and a point set of a pattern abnormality flag in the output data;
a fifteenth obtaining unit, configured to obtain an energy consumption curve according to a BP neural network model, where the energy consumption curve is an energy consumption prediction curve in a complete extrusion cycle;
and the sixteenth obtaining unit is used for performing discrete monitoring on the point set of the point abnormal marks and the point set of the pattern abnormal marks by using the energy consumption curve as a standard to obtain a first monitoring result.
5. An electronic device for secondary monitoring of abnormal energy consumption based on predicted data, comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected via the bus, characterized in that the computer program when executed by the processor implements the steps of the method as claimed in any one of claims 1-3.
6. A computer-readable storage medium, on which a computer program is stored, wherein the computer program realizes the steps in the method according to any of claims 1-3 when executed by a processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111176936.6A CN113917263B (en) | 2021-10-09 | 2021-10-09 | Method and system for secondary monitoring of abnormal energy consumption based on prediction data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111176936.6A CN113917263B (en) | 2021-10-09 | 2021-10-09 | Method and system for secondary monitoring of abnormal energy consumption based on prediction data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113917263A CN113917263A (en) | 2022-01-11 |
CN113917263B true CN113917263B (en) | 2022-05-24 |
Family
ID=79238716
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111176936.6A Active CN113917263B (en) | 2021-10-09 | 2021-10-09 | Method and system for secondary monitoring of abnormal energy consumption based on prediction data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113917263B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115689095B (en) * | 2022-12-30 | 2023-04-14 | 广东美的制冷设备有限公司 | Equipment energy consumption analysis method, device, production system and storage medium |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104636999A (en) * | 2015-01-04 | 2015-05-20 | 江苏联宏自动化***工程有限公司 | Detection method for building abnormal energy consumption data |
CN108435819A (en) * | 2018-05-29 | 2018-08-24 | 广东工业大学 | A kind of aluminum section extruder energy consumption method for detecting abnormality |
CN109784042A (en) * | 2018-12-29 | 2019-05-21 | 北京奇安信科技有限公司 | The detection method of abnormal point, device, electronic equipment and storage medium in time series |
CN110362608A (en) * | 2019-06-11 | 2019-10-22 | 广东工业大学 | Energy consumption method for detecting abnormality based on rain flow method and local outlier factor |
WO2020006841A1 (en) * | 2018-07-06 | 2020-01-09 | 平安科技(深圳)有限公司 | Power consumption abnormality detection method, apparatus and terminal, and computer-readable storage medium |
CN110941648A (en) * | 2019-11-19 | 2020-03-31 | 广州市自来水有限公司 | Abnormal data identification method, system and storage medium based on cluster analysis |
CN111161095A (en) * | 2019-12-16 | 2020-05-15 | 南京松数科技有限公司 | Method for detecting abnormal consumption of building energy |
CN111198799A (en) * | 2019-12-31 | 2020-05-26 | 苏州浪潮智能科技有限公司 | Machine room power consumption early warning method, system, terminal and storage medium based on LSTM |
CN111783947A (en) * | 2020-06-24 | 2020-10-16 | 上海凯营新能源技术有限公司 | Energy consumption prediction method based on LSTM neural network |
CN112070109A (en) * | 2020-07-21 | 2020-12-11 | 广东工业大学 | Calla kiln energy consumption abnormity detection method based on improved density peak clustering |
CN112381181A (en) * | 2020-12-11 | 2021-02-19 | 桂林电子科技大学 | Dynamic detection method for building energy consumption abnormity |
CN113239619A (en) * | 2021-05-08 | 2021-08-10 | 国网江西省电力有限公司萍乡供电分公司 | Machine learning hybrid model-based abnormal electricity consumption behavior detection method for special transformer users |
CN113284002A (en) * | 2021-04-09 | 2021-08-20 | 南方电网数字电网研究院有限公司 | Power consumption data anomaly detection method and device, computer equipment and storage medium |
CN113435517A (en) * | 2021-06-29 | 2021-09-24 | 平安科技(深圳)有限公司 | Abnormal data point output method and device, computer equipment and storage medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3376446A1 (en) * | 2017-03-18 | 2018-09-19 | Tata Consultancy Services Limited | Method and system for anomaly detection, missing data imputation and consumption prediction in energy data |
US10896378B2 (en) * | 2018-01-02 | 2021-01-19 | International Business Machines Corporation | Fast detection of energy consumption anomalies in buildings |
US11080620B2 (en) * | 2018-05-10 | 2021-08-03 | International Business Machines Corporation | Localizing energy consumption anomalies in buildings |
-
2021
- 2021-10-09 CN CN202111176936.6A patent/CN113917263B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104636999A (en) * | 2015-01-04 | 2015-05-20 | 江苏联宏自动化***工程有限公司 | Detection method for building abnormal energy consumption data |
CN108435819A (en) * | 2018-05-29 | 2018-08-24 | 广东工业大学 | A kind of aluminum section extruder energy consumption method for detecting abnormality |
WO2020006841A1 (en) * | 2018-07-06 | 2020-01-09 | 平安科技(深圳)有限公司 | Power consumption abnormality detection method, apparatus and terminal, and computer-readable storage medium |
CN109784042A (en) * | 2018-12-29 | 2019-05-21 | 北京奇安信科技有限公司 | The detection method of abnormal point, device, electronic equipment and storage medium in time series |
CN110362608A (en) * | 2019-06-11 | 2019-10-22 | 广东工业大学 | Energy consumption method for detecting abnormality based on rain flow method and local outlier factor |
CN110941648A (en) * | 2019-11-19 | 2020-03-31 | 广州市自来水有限公司 | Abnormal data identification method, system and storage medium based on cluster analysis |
CN111161095A (en) * | 2019-12-16 | 2020-05-15 | 南京松数科技有限公司 | Method for detecting abnormal consumption of building energy |
CN111198799A (en) * | 2019-12-31 | 2020-05-26 | 苏州浪潮智能科技有限公司 | Machine room power consumption early warning method, system, terminal and storage medium based on LSTM |
CN111783947A (en) * | 2020-06-24 | 2020-10-16 | 上海凯营新能源技术有限公司 | Energy consumption prediction method based on LSTM neural network |
CN112070109A (en) * | 2020-07-21 | 2020-12-11 | 广东工业大学 | Calla kiln energy consumption abnormity detection method based on improved density peak clustering |
CN112381181A (en) * | 2020-12-11 | 2021-02-19 | 桂林电子科技大学 | Dynamic detection method for building energy consumption abnormity |
CN113284002A (en) * | 2021-04-09 | 2021-08-20 | 南方电网数字电网研究院有限公司 | Power consumption data anomaly detection method and device, computer equipment and storage medium |
CN113239619A (en) * | 2021-05-08 | 2021-08-10 | 国网江西省电力有限公司萍乡供电分公司 | Machine learning hybrid model-based abnormal electricity consumption behavior detection method for special transformer users |
CN113435517A (en) * | 2021-06-29 | 2021-09-24 | 平安科技(深圳)有限公司 | Abnormal data point output method and device, computer equipment and storage medium |
Non-Patent Citations (3)
Title |
---|
Anomaly Detection in Premise Energy Consumption Data;Yi Zhang等;《2011 IEEE Power and Energy Society General Meeting》;20111231;全文 * |
一种挤压机能耗监测及预测***研究;陀树青等;《电子科技》;20150115(第01期);全文 * |
基于机器学习算法的建筑能耗监测数据;崔治国;《基于机器学习算法的建筑能耗监测数据》;20180228;第34卷(第2期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN113917263A (en) | 2022-01-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111079570B (en) | Human body key point identification method and device and electronic equipment | |
WO2021169473A1 (en) | Model performance optimization method, apparatus and device, and storage medium | |
CN112085056B (en) | Target detection model generation method, device, equipment and storage medium | |
CN113917263B (en) | Method and system for secondary monitoring of abnormal energy consumption based on prediction data | |
CN115662469B (en) | Water pipe leakage detection method, electronic equipment and storage medium | |
CN113706527B (en) | Quality detection method and system for cosmetic package | |
CN110688873A (en) | Multi-target tracking method and face recognition method | |
CN117875719A (en) | Substation safety early warning method based on target three-dimensional ranging | |
CN113988438A (en) | Self-checking method and system based on IC carrier plate production process | |
US11989891B2 (en) | System and method for 3D multi-object tracking in LiDAR point clouds | |
CN114997605A (en) | Intelligent planning method and system for degradable resin production route | |
CN113806350A (en) | Management method and system for improving security of big data transaction platform | |
CN114297665A (en) | Intelligent contract vulnerability detection method and device based on deep learning | |
CN117458699B (en) | Power parameter control method and system for self-adaptive scene | |
CN110162362B (en) | Dynamic control position detection and test method, device, equipment and storage medium | |
CN115524066A (en) | VOCs (volatile organic compounds) non-tissue leakage alarm identification method and device, electronic equipment and medium | |
CN114372723B (en) | Safe production method and system of fish products | |
CN112052861B (en) | Method for calculating effective receptive field of deep convolutional neural network and storage medium | |
CN112259239B (en) | Parameter processing method and device, electronic equipment and storage medium | |
CN109410304B (en) | Projection determination method, device and equipment | |
CN111709955A (en) | Image segmentation inspection method, device, terminal and storage medium | |
CN113680703B (en) | Intelligent material screening method and system for rotary connector | |
CN115619724A (en) | Quality detection method and system for electric wrench | |
CN114186159A (en) | Vue-frame-based bidirectional anchor point positioning method and system | |
CN113642260B (en) | Performance evaluation method and system for heat-seal cover tape |
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 |