CN116223937B - Abnormality detection method, abnormality detection device, abnormality detection equipment and computer-readable storage medium - Google Patents
Abnormality detection method, abnormality detection device, abnormality detection equipment and computer-readable storage medium Download PDFInfo
- Publication number
- CN116223937B CN116223937B CN202211575336.1A CN202211575336A CN116223937B CN 116223937 B CN116223937 B CN 116223937B CN 202211575336 A CN202211575336 A CN 202211575336A CN 116223937 B CN116223937 B CN 116223937B
- Authority
- CN
- China
- Prior art keywords
- wolf
- line
- detection circuit
- data
- performance detection
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 184
- 230000005856 abnormality Effects 0.000 title claims abstract description 39
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 241000282461 Canis lupus Species 0.000 claims description 63
- 241000257303 Hymenoptera Species 0.000 claims description 30
- 241000282421 Canidae Species 0.000 claims description 26
- 230000002159 abnormal effect Effects 0.000 claims description 24
- 238000000034 method Methods 0.000 claims description 19
- 239000003016 pheromone Substances 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 4
- 238000005265 energy consumption Methods 0.000 claims description 4
- 238000012804 iterative process Methods 0.000 claims description 4
- 238000013178 mathematical model Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 2
- 239000006185 dispersion Substances 0.000 claims description 2
- 230000006870 function Effects 0.000 claims description 2
- 235000012907 honey Nutrition 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 230000000717 retained effect Effects 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 17
- 230000008439 repair process Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010977 unit operation Methods 0.000 description 1
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
- 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
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an anomaly detection method, an anomaly detection device, anomaly detection equipment and a computer-readable storage medium, wherein the anomaly detection method comprises the following steps: under the condition that the unit is electrically connected with each performance detection circuit, a signal feedback module is additionally arranged at the interface of the circuit meter, and on-off signals are fed back to the acquisition board. Acquiring line feedback signals of the performance detection circuits and performance data of passing units; under the condition that the line feedback signals represent line abnormality, the signal problems of a power supply, an acquisition instrument, a line and an instrument board are directionally checked through an improved hunting algorithm, and the problem guidance is arranged item by item. Locating a line portion in the corresponding performance detection circuit based on the line feedback signal; the signals of the line part are monitored through an ant colony algorithm, the feedback signals are carried out through a bee colony simulation algorithm, and the position and fault characteristic information of the meter are positioned. By means of the bee colony algorithm, data observation is not required to be maintained in real time, only alarm events are required to be processed, and site work efficiency is greatly improved.
Description
Technical Field
The present invention relates to the field of data testing, and in particular, to an anomaly detection method, apparatus, device, and computer readable storage medium.
Background
For the performance test of the unit, a plurality of meters, circuits, wiring boards and other instruments are required to be installed, the unit is connected to a computer through wiring instruments, various parameters are monitored through software, a few tens of measuring point meters are often required for the conventional unit checking test, when bad points are displayed in the system, the bad points are often required to be continuously checked along the circuits to the meters or the monitoring modules, the positions of the bad points in the system cannot be immediately judged, and the field working efficiency is affected.
Disclosure of Invention
The present invention provides an anomaly detection method, apparatus, device, and computer-readable storage medium to solve at least the above technical problems.
The invention provides an abnormality detection method, which comprises the following steps:
under the condition that the unit is electrically connected with each performance detection circuit, acquiring a line feedback signal of each performance detection circuit and unit performance data acquired by the performance detection circuit;
the improved hunting search algorithm related to this patent is as follows:
step1: and (3) according to the input measuring point information, delineating a test point line range through a hunting algorithm, and determining the problem and parameter range to be examined. The hunting group considers three parts of E [ A, B and C ], wherein A represents a data acquisition board module, B represents a line module and C represents a meter module. A, B, C is set up in turn for fault capture inspection of hunting targets. And performing fault capturing according to the step 2-step 4 feedback results. The hunting procedure is captured as a conventional procedure.
Step2: the system algorithm is initialized, and the power supply signal, the acquisition board signal and the meter signal are sequentially checked along the line through the ant colony algorithm. According to the number of lines, the algorithm sets the number of ant colony groups to be 2 times of the number of all lines, checks the on-off information quantity of the line paths of the system sequentially through line sequencing set in the acquisition system, and searches the on-off through signal feedback set in a program. And sends a signal to the step1 module. Moving to the target group in turn, and checking each line in turn.
And (3) all the measuring points are used for sending the ant colony initially, and in the test process, the low-frequency inspection is set according to the number of lines after the complete and sustainable operation of the system is confirmed, so that the safety and reliability in the operation of the system are ensured.
Step3: and feeding back the meter on-off signal through an improved bee colony algorithm, setting the acquired meter signal as a new food source, sending a bee colony, evaluating the food source, conforming to a signal constraint rule (according to a rule set by step4 or checking with DCS data in a factory), and sending abnormal data to a test interface for alarming and reminding. And the method is convenient to adjust or correct in time so as to obtain correct data.
Step4: and setting a specific operation data boundary according to the unit operation load condition, and carrying out trend tracking feedback on the test data operation range to ensure that the monitoring data range is in an effective range during operation. The parallel setting parameters are: 1. the pressure fluctuation of the main steam is less than 3 percent or 40kPa, and the temperature fluctuation range is less than 40 ℃; the fluctuation of the pumping pressure is not more than 15%; the fluctuation of the exhaust pressure is not more than 6 percent or 2kPa; 2. the isentropic enthalpy drop fluctuation range of the unit is less than 12%. 3. And under the same working condition, the load fluctuation is less than 12%. 4. The deviation range of the rotating speed range is less than 8%; the generator voltage fluctuation is less than 10%.
Step5: and repeating Step 2-4 until the test is ended.
Positioning a line portion in the corresponding performance detection circuit based on the line feedback signal in the case where the line feedback signal characterizes a line anomaly;
and under the condition that the unit performance data representation data is abnormal, positioning a meter part corresponding to the performance detection circuit based on the unit performance data.
In one embodiment, the line feedback signal characterizes a specific form of line anomaly, and includes at least one of:
the signal value of the line feedback signal is lower than a first specified threshold;
the signal value of the line feedback signal is above a second specified threshold.
In one embodiment, the unit performance data characterizes a manifestation of data anomalies, including:
the unit performance data is not within the normal range of measurement corresponding to the meter.
In one embodiment, the normal range of the meter is obtained by:
and matching the normal range of the corresponding meter from a preset database according to the model of the unit and the keyword information corresponding to the performance detection circuit.
In an embodiment, the positioning a line portion corresponding to the performance detection circuit based on the line feedback signal includes: determining a keyword name corresponding to the model or performance detection circuit of the unit based on the line feedback signal;
Determining position information of a circuit part in the performance detection circuit from a preset database based on the model of the unit or the keyword name of the performance detection circuit;
correspondingly, the positioning of the meter part corresponding to the performance detection circuit based on the unit performance data comprises the following steps:
determining a keyword name corresponding to the model or performance detection circuit of the unit based on the line feedback signal;
and determining the position information of the meter part in the performance detection circuit from a preset database based on the model of the unit or the keyword name of the performance detection circuit.
In another aspect, the invention provides an anomaly detection device, a data processing module and a plurality of groups of performance detection circuits;
the data processing module is electrically connected with a plurality of groups of performance detection circuits and is used for acquiring line feedback signals sent by the performance detection circuits;
each group of performance detection circuits comprises a meter, an acquisition instrument and an installation circuit;
the meter is used for being installed on a unit to acquire relevant unit performance data;
the acquisition instrument is respectively and electrically connected with the meter and the data processing module so as to acquire the unit performance data and send the unit performance data to the data processing module;
In the case that the line feedback signal characterizes a line abnormality, the data processing module locates a line portion corresponding to the performance detection circuit based on the line feedback signal;
and under the condition that the unit performance data represents data abnormality, the data processing module positions a meter part corresponding to the performance detection circuit based on the unit performance data.
In an embodiment, the data processing module is specifically one of a PLC and an MCU.
Another aspect of the present invention provides an abnormality detection apparatus including:
the acquisition module is used for acquiring line feedback signals of the performance detection circuits and unit performance data acquired by the performance detection circuits under the condition that the unit is electrically connected with the performance detection circuits;
the circuit positioning module is used for positioning a circuit part corresponding to the performance detection circuit based on the circuit feedback signal under the condition that the circuit feedback signal represents the circuit abnormality;
and the meter positioning module is used for positioning a meter part corresponding to the performance detection circuit based on the unit performance data under the condition that the unit performance data representation data are abnormal.
Another aspect of the present invention provides an abnormality detection apparatus including a memory and a processor; the memory is used for storing instructions for controlling the processor to operate to implement the anomaly detection method when executed.
Another aspect of the invention provides a readable storage medium comprising a set of computer executable instructions for performing the anomaly detection method when the instructions are executed.
The embodiment of the invention provides an anomaly detection method, an anomaly detection device, anomaly detection equipment and a computer readable storage medium, wherein the anomaly detection method, the anomaly detection device and the anomaly detection equipment are used for acquiring line feedback signals of all performance detection circuits and unit performance data acquired by the performance detection circuits; under the condition that the line feedback signal represents the abnormality of the line, locating a line part in the corresponding performance detection circuit based on the line feedback signal; under the condition that the unit performance data represent data are abnormal, the meter part in the corresponding performance detection circuit is positioned based on the unit performance data, so that a worker can directly go to the site to check and repair based on the position of the line part or the meter position, and all lines do not need to be checked, thereby greatly improving the site work efficiency.
It should be understood that the teachings of the present invention need not achieve all of the benefits set forth above, but rather that certain technical solutions may achieve certain technical effects, and that other embodiments of the present invention may also achieve benefits not set forth above.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
FIG. 1 is a flowchart of an embodiment of an anomaly detection method according to the present invention;
FIG. 2 is a diagram showing an actual circuit connection of an abnormality detection apparatus according to an embodiment of the present invention;
fig. 3 is a schematic diagram of virtual module connection of an abnormality detection apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more comprehensible, the technical solutions according to the embodiments of the present invention will be clearly described in the following with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, an embodiment of the present invention provides an anomaly detection method, including:
step 101, under the condition that a unit is electrically connected with each performance detection circuit, acquiring a line feedback signal of each performance detection circuit and unit performance data acquired by the performance detection circuit, firstly adopting a hunting algorithm, and directionally setting a hunting algorithm fault module retrieval sequence to screen matching tracking conditions of line power on-off, signal on-off and data accuracy in sequence;
102, detecting a line through an improved ant colony algorithm based on the line feedback signal under the condition that the line feedback signal represents line abnormality, positioning signal monitoring corresponding to a line part of the performance detection circuit, sequentially feeding back abnormality of a line path according to a set route, and carrying out line abnormality alarm when the information of the path feedback signal is incomplete;
wherein, the ant colony algorithm: setting the total number of ants as M, distributing ants to n measuring points according to the number of access measuring points in turn, wherein the number of ants is X i I=1, 2..n, dividing ants into groups identical to the measuring points in sequence, and after the line is determined, setting the path, so that the on-off of the line can be judged through the feedback information intensity;
1. Carry-over formula；
2. Li represents the length of the ith ant path which circulates through three nodes of the acquisition instrument, the line and the meter;
3. the calculation formula of the line L is；
4. Calculating according to the line L to obtain each node information signal update;
5、N(i+1)=Ni+∆i；
6. let ni=1 initially and i=0, then the pheromone is updated locally after each ant moves one step at a time:
the variables are expressed as follows:the pheromone concentration after one step of movement; />The pheromone concentration of the current node; />Locally updating the volatility coefficient for the pheromone, wherein 0</><1；/>For each ant in the current circulationThe concentration of the retained pheromone; />A change value for the pheromone;Qa constant empirically set;LSis antkThe total path track integrated value walked in the current circulation;
7. updating a tabu table; continuing to calculate the probability, selecting the nodes and updating the tabu list until all the nodes are traversed for 1 time: and carrying out pheromone global update on the optimal path obtained after all ants complete one iteration, and updating a tabu table at the same time:
wherein:the volatilization coefficient is globally updated for the pheromone;Qis an empirical constant; OP is the optimal path obtained in the native cycle; />The optimal solution obtained at present;
After node information collected in the program is complete, confirming that the content detection of the part is normal;
step 103, positioning data corresponding to a meter part in the performance detection circuit through a bee colony simulation algorithm based on the unit performance data under the condition that the unit performance data representation data are abnormal, and screening and checking;
step 104, dividing the bee colony into patrol bees, collection bees and search bees according to the bee colony algorithm setting; the data are collected by the collecting bees and then sent to the patrol bees, and the patrol bees send the data to the collecting instrument; when the signal is normal, the searching bees search the data of each measuring point in the whole course during the test operation, and when the data exceeds the specified range, the alarm is given;
setting the number of measuring points, namely the number of honey sources as n, and collecting bees X at an initial position i =X 0 +X i-1 Wherein i=1, 2,3 … n;
comparing the acquired data with information under corresponding load working conditions in a thermodynamic system diagram of the unit, and judging that the Xi number A is adaptively compared with a given design number B in the system diagram; when the change of (A-B)/B is not more than the set proportion, the acquired data is transmitted to an acquisition system, and when the change is more than the set proportion and the fluctuation is larger, an alarm signal is transmitted to an acquisition instrument;
When all the measuring points of the system run normally and no alarm exists, the collecting bees in the system run normally according to the set reading frequency, the searching bees start to search all the parameters, and the areas are sequentially selected from the parameters set by the collecting instrument for carrying out;
setting 5 measuring points as search units, wherein each search unit is provided with a range area S, dividing S into S1, S2..Sn, searching the S1, S2 … Sn by a search bee in sequence, and sorting the search units in a grading manner according to the importance of the measuring points, and timely transmitting the search units to a hunting area;
step 105, classifying importance levels of the measuring points according to the hunting algorithm, wherein the importance levels correspond to the classification in the hunting algorithm;
the hunting wolf group is set to 4 grades, and the grade importance corresponds to the alarm data of the bee colony algorithm, the energy consumption calculation of the two kinds of correction covered measuring point parameters, the energy consumption calculation of the one kind of correction covered measuring point parameters and other measuring point parameters respectively; the wolf group of the previous grade can be called and managed for the wolf group of the next grade; setting and carrying the hunting wolves in sequence;
in the gray wolf optimization algorithm, a social level system model of the gray wolves is firstly constructed; the solutions with optimal fitness value, suboptimal and third optimal in the population are respectively corresponding to Wolf (wolf) and (Ten) of (Ten) feet>Wolf and->Wolf, the remainder is called +.>Wolves; by->Wolf (wolf) and (Ten) of (Ten) feet>Wolf and Chinese wolfWolf takes charge of guiding, is->Wolf is followed by->Wolf (wolf) and (Ten) of (Ten) feet>Wolf and->Wolves complete hunting by searching for, surrounding and attacking the prey;
(1) Surrounding the prey: the mathematical model of the wolf surrounding the hunting object is that
Formula (1) defines the distance between the wolf and the prey, while formula (2) defines the final position of the wolf; wherein t represents the current iteration number, X p Representing the position of a prey, X representing the position of a wolf, A and C being parameter vectors, the calculation formula of which is
Wherein: a is a linearly decreasing parameter from 2 to 0 in the whole iterative process, r 1 And r 2 Is [0,1]Random vectors between;
(2) And (3) a pig is guided: to simulate collective hunting behavior of wolves, we always assume thatWolf (wolf) and (Ten) of (Ten) feet>Wolf and->Wolves have a better understanding of the potential location of the prey; in each iteration process, the currently obtained fitness value is saved to be optimal +.>Wolf, suboptimal->Wolf and third you->The position information of 3 wolves of wolves, the wolves comprehensively judge the moving direction of the individual to the prey according to the position information of the 3 optimal solutions and update the position of the individual, and the update formula is as follows
(3) Attack prey: to construct a mathematical model of a wolf attacking a prey, a is a random vector over the interval [ -2a,2a ] according to equation (3), where a is a linearly decreasing parameter from 2 to 0 in an iterative process, when the value of |a| is within [ -1,1], the next position of the wolf will be anywhere between its present position and the prey position, indicating that an attack is being initiated to the prey;
(4) Searching for hunting: the gray wolf is mainly based onWolf (wolf) and (Ten) of (Ten) feet>Wolf and->The position information of the wolves is used for searching the hunting, the wolves are scattered to search the hunting and then gathered together to attack the hunting; to construct a dispersion model, a random value of greater than 1 or less than-1 is used to force the wolf away from the prey to explore more promising search space to achieve a global search of the algorithm; another exploration vector in the gray wolf optimization algorithm is C, which is [0,21 ] from equation (4)]The random value can randomly increase the difficulty level of |C| > 1 or lighten the difficulty level of the gray wolves of |C| < 1 when approaching to a prey, so that the gray wolves optimization algorithm shows more random behaviors in the whole optimization process, and the global exploration capacity of the algorithm is improved;
and 106, finishing the functions of data exploration, searching and alarming through hunting of the wolf group.
In this embodiment, in step 101, the performance detecting circuits may include a plurality of groups, such as a temperature detecting circuit, a pressure detecting circuit, a vibration detecting circuit, and so on, and the plurality of groups of performance detecting circuits are all installed on the unit to detect the performance of the pressure, the temperature, the vibration, and so on the unit.
And under the condition that the unit is electrically connected with each performance detection circuit, respectively receiving a line feedback signal sent by each performance detection circuit and the detected unit performance data, wherein the line feedback signal is used for judging whether the line of the performance detection circuit is abnormal or not.
In step 102, in the case where the line feedback signal characterizes the line abnormality, the line portion in the performance detection circuit is located according to the acquired line feedback signal, and at this time, the worker may go to the site directly to inspect and repair the line, the interface, and the like based on the position of the line portion.
In step 103, in the case that the unit performance data represents that the data is abnormal, the meter part in the corresponding performance detection circuit is located according to the acquired unit performance data, and at this time, the staff can directly go to the meter installed on site to check based on the position of the meter part.
Therefore, the circuit feedback signals of the performance detection circuits and the unit performance data acquired by the performance detection circuits are obtained; under the condition that the line feedback signal represents the abnormality of the line, locating a line part in the corresponding performance detection circuit based on the line feedback signal; under the condition that the unit performance data represent data are abnormal, the meter part in the corresponding performance detection circuit is positioned based on the unit performance data, so that a worker can directly go to the site to check and repair based on the position of the line part or the meter position, and all lines do not need to be checked, thereby greatly improving the site work efficiency.
In one embodiment, the line feedback signal characterizes a specific form of line anomaly, including at least one of:
the signal value of the line feedback signal is lower than a first specified threshold;
the signal value of the line feedback signal is above a second specified threshold.
In this embodiment, the circuit abnormality includes two types of circuit breaking and short circuit, so after the circuit feedback signal is obtained, whether the circuit is abnormal or not can be judged according to the following two ways;
the first way is that the signal value of the line feedback signal is lower than a first specified threshold, wherein the first specified threshold is specifically a low level signal or a very small signal value, and the line part is in an open state.
In a second way, the signal value of the line feedback signal is higher than a second specified threshold, where the second specified threshold is specifically a high level signal or a maximum signal value, and the line portion is in a short circuit state.
In one embodiment, the unit performance data characterizes a manifestation of data anomalies, including:
the unit performance data is not within the normal range of the corresponding meter.
In this embodiment, the mode for judging whether the unit performance data is abnormal specifically:
The normal measuring range of the meter is obtained in advance;
judging whether the fluctuation range of the obtained unit performance data is within a normal range;
if the fluctuation range of the unit performance data is judged to be within the normal range, the unit performance data is normal, and the meter is normal.
If the fluctuation range of the unit performance data is judged to be outside the normal range, the unit performance data is abnormal, and the table is abnormal.
In one embodiment, the normal range of the meter is obtained by:
and matching the normal range of the corresponding meter from a preset database according to the model of the unit and the keyword information corresponding to the performance detection circuit.
In this embodiment, before the normal range of the gauge is obtained, the model number of the unit corresponding to the performance detection circuit and the name of the performance detection circuit may be stored in a preset database in advance, and are associated with each other in the preset database. In addition, the position of the meter and the position of the performance detection circuit are stored in a preset database.
Thus, the normal range of the meter is obtained by the following steps:
the names of the performance detection circuits can be correspondingly acquired through the sources of the performance data of the unit, and then the model of the unit is positioned through a preset database;
And taking the model of the unit or the keyword name of the performance detection circuit as a search field, and inquiring the normal range of the meter in the performance detection circuit in a preset database.
In one embodiment, locating a line portion in a corresponding performance detection circuit based on a line feedback signal includes:
determining the model of the corresponding unit or the keyword name of the performance detection circuit based on the line feedback signal;
determining position information of a circuit part in the performance detection circuit from a preset database based on the model of the unit or the keyword name of the performance detection circuit;
correspondingly, based on the unit performance data, locating the meter portion of the corresponding performance detection circuit includes:
determining the model of the corresponding unit or the keyword name of the performance detection circuit based on the line feedback signal;
and determining position information of the meter part in the performance detection circuit from a preset database based on the model number of the unit or the keyword name of the performance detection circuit.
In this embodiment, based on the line feedback signal, the specific process of locating the line portion in the corresponding performance detection circuit is:
according to the line feedback signals, the names of the models or the performance detection circuits or the keyword names of the units are correspondingly obtained;
And taking the model or the keyword name as a search field, and determining the position information of the circuit part in the performance detection circuit from a preset database.
Correspondingly, based on unit performance data, the specific process of positioning the meter part in the corresponding performance detection circuit is as follows:
according to the line feedback signals, the names of the models or the performance detection circuits or the keyword names of the units are correspondingly obtained;
and taking the model or the keyword name as a search field, and determining the position information of the meter in the performance detection circuit from a preset database.
As shown in fig. 2, another aspect of the present invention provides an anomaly detection device, a data processing module and a plurality of sets of performance detection circuits;
the data processing module is electrically connected with a plurality of groups of performance detection circuits and is used for acquiring line feedback signals sent by the performance detection circuits;
each group of performance detection circuits comprises a meter, an acquisition instrument and an installation circuit;
the meter is used for being installed on the unit to acquire relevant unit performance data;
the acquisition instrument is respectively and electrically connected with the meter and the data processing module so as to acquire unit performance data and send the unit performance data to the data processing module;
under the condition that the line feedback signal represents the abnormality of the line, the data processing module positions a line part in the corresponding performance detection circuit based on the line feedback signal;
In the case of the unit performance data characterizing data anomalies, the data processing module locates a meter portion in the corresponding performance detection circuit based on the unit performance data.
In this embodiment, the data processing module is specifically one of a PLC and an MCU.
When the system is used, a detection signal can be sent to each group of performance detection circuits through the data processing module, a corresponding line feedback signal is received through a loop of each performance detection circuit, if the line feedback signal is lower than a first specified threshold value or higher than a second specified threshold value, the abnormality of the line, namely the short circuit or open circuit of the line is indicated, and at the moment, the data processing module is positioned at the position of the line and can inform the position of the line in a data transmission mode or a display mode;
under the condition that the line is normal, the data processing module also receives the unit performance data detected by the performance detection circuit for the unit, judges whether the unit performance data is in the normal range of the corresponding meter, and if the unit performance data is not met, acquires the position of the line part in the performance detection circuit, and can be informed in a data transmission mode or a display mode.
Another aspect of the present invention provides an abnormality detection apparatus, as shown in fig. 3, the apparatus including:
The acquiring module 201 is configured to acquire a line feedback signal of each performance detection circuit and unit performance data acquired by the performance detection circuit when the unit is electrically connected to each performance detection circuit;
a line locating module 202, configured to locate a line portion in the corresponding performance detection circuit based on the line feedback signal in a case where the line feedback signal characterizes the line abnormality;
the meter positioning module 203 is configured to, in a case where the unit performance data represents an abnormality, position a meter portion in the corresponding performance detection circuit based on the unit performance data.
In this embodiment, in the obtaining module 201, the performance detecting circuits may include a plurality of groups, such as a temperature detecting circuit, a pressure detecting circuit, a vibration detecting circuit, and the like, and the plurality of groups of performance detecting circuits are all installed on the unit to detect the performance of the pressure, the temperature, the vibration, and the like on the unit, respectively.
And under the condition that the unit is electrically connected with each performance detection circuit, respectively receiving a line feedback signal sent by each performance detection circuit and the detected unit performance data, wherein the line feedback signal is used for judging whether the line of the performance detection circuit is abnormal or not.
In the line locating module 202, in the case where the line feedback signal characterizes the line abnormality, the line portion in the performance detection circuit is located according to the acquired line feedback signal, and at this time, a worker may directly go to the site to inspect and repair the line, the interface, and the like based on the position of the line portion.
In the meter positioning module 203, in the case that the unit performance data representing data is abnormal, the meter portion in the corresponding performance detection circuit is positioned according to the acquired unit performance data, and at this time, the staff can directly go to the meter installed on site to check based on the position of the meter portion.
Therefore, the circuit feedback signals of the performance detection circuits and the unit performance data acquired by the performance detection circuits are obtained; under the condition that the line feedback signal represents the abnormality of the line, locating a line part in the corresponding performance detection circuit based on the line feedback signal; under the condition that the unit performance data represent data are abnormal, the meter part in the corresponding performance detection circuit is positioned based on the unit performance data, so that a worker can directly go to the site to check and repair based on the position of the line part or the meter position, and all lines do not need to be checked, thereby greatly improving the site work efficiency.
In one embodiment, the line locating module 202 determines that the line feedback signal characterizes a particular form of line anomaly, including at least one of:
the signal value of the line feedback signal is lower than a first specified threshold;
the signal value of the line feedback signal is above a second specified threshold.
In this embodiment, the line abnormality includes two types of circuit breaking and short circuit, so after the line feedback signal is obtained, the line positioning module 202 may determine whether the line is abnormal according to the following two ways;
the first way is that the signal value of the line feedback signal is lower than a first specified threshold, wherein the first specified threshold is specifically a low level signal or a very small signal value, and the line part is in an open state.
In a second way, the signal value of the line feedback signal is higher than a second specified threshold, where the second specified threshold is specifically a high level signal or a maximum signal value, and the line portion is in a short circuit state.
In one embodiment, the meter locating module 203 determines the performance form of the unit performance data characterization data anomaly, including:
the unit performance data is not within the normal range of the corresponding meter.
In this embodiment, the mode for judging whether the unit performance data is abnormal specifically:
the normal measuring range of the meter is obtained in advance;
judging whether the fluctuation range of the obtained unit performance data is within a normal range;
if the fluctuation range of the unit performance data is judged to be within the normal range, the unit performance data is normal, and the meter is normal.
If the fluctuation range of the unit performance data is judged to be outside the normal range, the unit performance data is abnormal, and the table is abnormal.
In one embodiment, the gauge positioning module 203 obtains the normal range of the gauge by:
and matching the normal range of the corresponding meter from a preset database according to the model of the unit and the keyword information corresponding to the performance detection circuit.
In this embodiment, before the normal range of the gauge is obtained, the model number of the unit corresponding to the performance detection circuit and the name of the performance detection circuit may be stored in a preset database in advance, and are associated with each other in the preset database. In addition, the position of the meter and the position of the performance detection circuit are stored in a preset database.
Thus, the normal range of the meter is obtained by the following steps:
the names of the performance detection circuits can be correspondingly acquired through the sources of the performance data of the unit, and then the model of the unit is positioned through a preset database;
and taking the model of the unit or the keyword name of the performance detection circuit as a search field, and inquiring the normal range of the meter in the performance detection circuit in a preset database.
In one embodiment, the specific process of the line location module 202 in locating the line portion in the corresponding performance detection circuit is:
determining the model of the corresponding unit or the keyword name of the performance detection circuit based on the line feedback signal;
determining position information of a circuit part in the performance detection circuit from a preset database based on the model of the unit or the keyword name of the performance detection circuit;
correspondingly, the specific process of the meter positioning module 203 in positioning the meter part in the corresponding performance detection circuit is as follows:
determining the model of the corresponding unit or the keyword name of the performance detection circuit based on the line feedback signal;
and determining position information of the meter part in the performance detection circuit from a preset database based on the model number of the unit or the keyword name of the performance detection circuit.
In this embodiment, based on the line feedback signal, the specific process of locating the line portion in the corresponding performance detection circuit is:
the line positioning module 202 correspondingly acquires the names of the models or the names of the performance detection circuits or the keyword names of the units according to the line feedback signals;
and taking the model or the keyword name as a search field, and determining the position information of the circuit part in the performance detection circuit from a preset database.
Correspondingly, based on unit performance data, the specific process of positioning the meter part in the corresponding performance detection circuit is as follows:
the meter positioning module 203 correspondingly acquires the names of the models or the performance detection circuits of the units or the names of the keywords according to the line feedback signals;
and taking the model or the keyword name as a search field, and determining the position information of the meter in the performance detection circuit from a preset database.
Another aspect of the present invention provides an abnormality detection apparatus including a memory and a processor; the memory is used for storing instructions for controlling the processor to operate to implement the anomaly detection method when executed.
In this embodiment, when the instruction is executed, the instruction is configured to obtain, when the unit is electrically connected to each performance detection circuit, a line feedback signal of each performance detection circuit and unit performance data acquired by the performance detection circuit; under the condition that the line feedback signal represents the abnormality of the line, locating a line part in the corresponding performance detection circuit based on the line feedback signal; and under the condition that the unit performance data representation data is abnormal, positioning a meter part in the corresponding performance detection circuit based on the unit performance data.
Therefore, the circuit feedback signals of the performance detection circuits and the unit performance data acquired by the performance detection circuits are obtained; under the condition that the line feedback signal represents the abnormality of the line, locating a line part in the corresponding performance detection circuit based on the line feedback signal; under the condition that the unit performance data represent data are abnormal, the meter part in the corresponding performance detection circuit is positioned based on the unit performance data, so that a worker can directly go to the site to check and repair based on the position of the line part or the meter position, and all lines do not need to be checked, thereby greatly improving the site work efficiency.
Another aspect of the present invention provides a readable storage medium comprising a set of computer executable instructions for performing the above-described anomaly detection method when the instructions are executed.
In this embodiment, when the instruction is executed, the instruction is configured to obtain, when the unit is electrically connected to each performance detection circuit, a line feedback signal of each performance detection circuit and unit performance data acquired by the performance detection circuit; under the condition that the line feedback signal represents the abnormality of the line, locating a line part in the corresponding performance detection circuit based on the line feedback signal; and under the condition that the unit performance data representation data is abnormal, positioning a meter part in the corresponding performance detection circuit based on the unit performance data.
Therefore, the circuit feedback signals of the performance detection circuits and the unit performance data acquired by the performance detection circuits are obtained; under the condition that the line feedback signal represents the abnormality of the line, locating a line part in the corresponding performance detection circuit based on the line feedback signal; under the condition that the unit performance data represent data are abnormal, the meter part in the corresponding performance detection circuit is positioned based on the unit performance data, so that a worker can directly go to the site to check and repair based on the position of the line part or the meter position, and all lines do not need to be checked, thereby greatly improving the site work efficiency.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. An anomaly detection method, the method comprising:
under the condition that a machine set is electrically connected with each performance detection circuit, acquiring line feedback signals of each performance detection circuit and machine set performance data acquired by the performance detection circuits, firstly adopting a hunting algorithm, and directionally setting a hunting algorithm fault module retrieval sequence to screen matching tracking conditions of line power on-off, signal on-off and data accuracy in sequence;
Under the condition that the line feedback signal represents line abnormality, detecting the line through an improved ant colony algorithm based on the line feedback signal, positioning signal monitoring corresponding to a line part of the performance detection circuit, sequentially feeding back abnormality of a line path according to a set route, and carrying out line abnormality alarm when the path feedback signal information is incomplete;
wherein, the ant colony algorithm: setting the total number of ants as M, distributing ants to n measuring points according to the number of access measuring points in turn, wherein the number of ants is X i I=1, 2..n, dividing ants into groups identical to the measuring points in sequence, and after the line is determined, setting the path, so that the on-off of the line can be judged through the feedback information intensity;
(1) Carry-over formula；
(2) Li represents the length of the ith ant path which circulates through three nodes of the acquisition instrument, the circuit and the meter;
(3) The calculation formula of the line L is；
(4) Calculating according to the line L to obtain each node information signal update;
（5）、N(i+1)=Ni+∆i；
(6) Let ni=1 initially and i=0, then the pheromone is updated locally after each ant moves one step at a time:
the variables are expressed as follows: The pheromone concentration after one step of movement; />Information for current nodeConcentration of the element; />Locally updating the volatility coefficient for the pheromone, wherein 0</><1；/>For each ant in the current circulation in the way +.>The concentration of the retained pheromone; />A change value for the pheromone;Qa constant empirically set;LSis antkThe total path track integrated value walked in the current circulation;
(7) Updating the tabu list; continuing to calculate the probability, selecting the nodes and updating the tabu list until all the nodes are traversed for 1 time: and carrying out pheromone global update on the optimal path obtained after all ants complete one iteration, and updating a tabu table at the same time:
wherein:the volatilization coefficient is globally updated for the pheromone;Qis an empirical constant; OP is the optimal path obtained in the native cycle; />The optimal solution obtained at present;
after node information collected in the program is complete, confirming that the content detection of the part is normal;
under the condition that the unit performance data representing data are abnormal, positioning data corresponding to a meter part in the performance detection circuit through a bee colony simulation algorithm based on the unit performance data to carry out screening and checking;
dividing the bee colony into patrol bees, collection bees and search bees according to the bee colony algorithm setting; the data are collected by the collecting bees and then sent to the patrol bees, and the patrol bees send the data to the collecting instrument; when the signal is normal, the searching bees search the data of each measuring point in the whole course during the test operation, and when the data exceeds the specified range, the alarm is given;
Setting the number of measuring points, namely the number of honey sources as n, and collecting bees X at an initial position i =X 0 +X i-1 Wherein i=1, 2,3 … n;
comparing the acquired data with information under corresponding load working conditions in a thermodynamic system diagram of the unit, and judging that the Xi number A is adaptively compared with a given design number B in the system diagram; when the change of (A-B)/B is not more than the set proportion, the acquired data is transmitted to an acquisition system, and when the change is more than the set proportion and the fluctuation is larger, an alarm signal is transmitted to an acquisition instrument;
when all the measuring points of the system run normally and no alarm exists, the collecting bees in the system run normally according to the set reading frequency, the searching bees start to search all the parameters, and the areas are sequentially selected from the parameters set by the collecting instrument for carrying out;
setting 5 measuring points as search units, wherein each search unit is provided with a range area S, dividing S into S1, S2..Sn, searching the S1, S2 … Sn by a search bee in sequence, and sorting the search units in a grading manner according to the importance of the measuring points, and timely transmitting the search units to a hunting area;
classifying importance levels of the measuring points according to a hunting algorithm, wherein the importance levels correspond to the classification in the hunting algorithm;
the hunting wolf group is set to 4 grades, and the grade importance corresponds to the alarm data of the bee colony algorithm, the energy consumption calculation of the two kinds of correction covered measuring point parameters, the energy consumption calculation of the one kind of correction covered measuring point parameters and other measuring point parameters respectively; the wolf group of the previous grade can be called and managed for the wolf group of the next grade; setting and carrying the hunting wolves in sequence;
In the gray wolf optimization algorithm, a social level system model of the gray wolves is firstly constructed; the solutions with optimal fitness value, suboptimal and third optimal in the population are respectively corresponding toWolf (wolf) and (Ten) of (Ten) feet>Wolf and->Wolf, the remainder is called +.>Wolves; by->Wolf (wolf) and (Ten) of (Ten) feet>Wolf and->Wolf takes charge of guiding, is->Wolf is followed by->Wolf (wolf) and (Ten) of (Ten) feet>Wolf and->Wolves complete hunting by searching for, surrounding and attacking the prey;
(1) Surrounding the prey: the mathematical model of the wolf surrounding the hunting object is that
Formula (1) defines the distance between the wolf and the prey, while formula (2) defines the final position of the wolf; wherein t represents the current iteration number, X p Representing the position of a prey, X representing the position of a wolf, A and C being parameter vectors, and the calculation formula being:
wherein: a is a linearly decreasing parameter from 2 to 0 in the whole iterative process, r 1 And r 2 Is [0,1]Random vectors between;
(2) Hunting: to simulate the collective hunting behavior of a wolf group, alpha wolves are always assumed,wolf and->Wolves have a better understanding of the potential location of the prey; in each iteration process, the optimal alpha wolf and suboptimal alpha wolf of the currently obtained fitness value are stored>Wolf and third you->The position information of 3 wolves of wolves, the wolves comprehensively judge the moving direction of the individual to the prey according to the position information of the 3 optimal solutions and update the position of the individual, and the update formula is as follows
(3) Attack prey: to construct a mathematical model of a wolf attacking a prey, a is a random vector over the interval [ -2a,2a ] according to equation (3), where a is a linearly decreasing parameter from 2 to 0 in an iterative process, when the value of |a| is within [ -1,1], the next position of the wolf will be anywhere between its present position and the prey position, indicating that an attack is being initiated to the prey;
(4) Searching for hunting: the gray wolf is mainly based onWolf (wolf) and (Ten) of (Ten) feet>Wolf and->The position information of the wolves is used for searching the hunting, the wolves are scattered to search the hunting and then gathered together to attack the hunting; to construct a dispersion model, a random value of greater than 1 or less than-1 is used to force the wolf away from the prey to explore more promising search space to achieve a global search of the algorithm; another exploration vector in the gray wolf optimization algorithm is C, which is [0,21 ] from equation (4)]The random value can randomly increase the difficulty level of |C| > 1 or lighten the difficulty level of the gray wolves of |C| < 1 when approaching to a prey, so that the gray wolves optimization algorithm shows more random behaviors in the whole optimization process, and the global exploration capacity of the algorithm is improved;
and the hunting of the wolf group is used for completing the functions of data exploration, searching and alarming.
2. The method of claim 1, wherein the line feedback signal characterizes a particular form of line anomaly, including at least one of:
the signal value of the line feedback signal is lower than a first specified threshold;
the signal value of the line feedback signal is above a second specified threshold.
3. The method of claim 1, wherein the crew performance data characterizes a manifestation of data anomalies, comprising:
the unit performance data is not within the normal range of measurement corresponding to the meter.
4. A method according to claim 3, wherein the normal range of the meter is obtained by:
and matching the normal range of the corresponding meter from a preset database according to the model of the unit and the keyword information corresponding to the performance detection circuit.
5. The method of claim 1, wherein locating a line portion in the corresponding performance detection circuit based on the line feedback signal comprises:
determining a keyword name corresponding to the model or performance detection circuit of the unit based on the line feedback signal;
determining position information of a circuit part in the performance detection circuit from a preset database based on the model of the unit or the keyword name of the performance detection circuit;
Correspondingly, the positioning of the meter part corresponding to the performance detection circuit based on the unit performance data comprises the following steps:
determining a keyword name corresponding to the model or performance detection circuit of the unit based on the line feedback signal;
and determining the position information of the meter part in the performance detection circuit from a preset database based on the model of the unit or the keyword name of the performance detection circuit.
6. An abnormality detection apparatus, characterized in that the apparatus includes a memory and a processor; the memory is configured to store instructions that, when executed, control the processor to perform the anomaly detection method of any one of claims 1-5.
7. A readable storage medium comprising a set of computer executable instructions which when executed are adapted to perform the anomaly detection method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211575336.1A CN116223937B (en) | 2022-12-08 | 2022-12-08 | Abnormality detection method, abnormality detection device, abnormality detection equipment and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211575336.1A CN116223937B (en) | 2022-12-08 | 2022-12-08 | Abnormality detection method, abnormality detection device, abnormality detection equipment and computer-readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116223937A CN116223937A (en) | 2023-06-06 |
| CN116223937B true CN116223937B (en) | 2024-02-06 |
Family
ID=86575694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211575336.1A Active CN116223937B (en) | 2022-12-08 | 2022-12-08 | Abnormality detection method, abnormality detection device, abnormality detection equipment and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116223937B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117250480B (en) * | 2023-11-08 | 2024-02-23 | 英诺达(成都)电子科技有限公司 | Loop detection method, device, equipment and storage medium of combinational logic circuit |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20010077602A (en) * | 2000-02-03 | 2001-08-20 | 이종훈 | The Preventive Diagnostic System for the Electric Power Substation Equipments |
| CN105676126A (en) * | 2016-01-18 | 2016-06-15 | 常州工学院 | Electric power system main transformer cooling motor group monitoring device |
| CN112379211A (en) * | 2020-09-24 | 2021-02-19 | 国网吉林省电力有限公司电力科学研究院 | Detection method of power transmission line fault area positioning device |
| CN113359030A (en) * | 2021-06-09 | 2021-09-07 | 西安热工研究院有限公司 | Wind driven generator short circuit fault simulation platform based on external magnetic flux leakage detection |
| CN113670609A (en) * | 2021-07-21 | 2021-11-19 | 广州大学 | Fault detection method, system, device and medium based on wolf optimization algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210148996A1 (en) * | 2019-11-14 | 2021-05-20 | Vigyanlabs Innovations Private Limited | System and method of monitoring electrical devices to detect anomaly in the electrical devices |
-
2022
- 2022-12-08 CN CN202211575336.1A patent/CN116223937B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20010077602A (en) * | 2000-02-03 | 2001-08-20 | 이종훈 | The Preventive Diagnostic System for the Electric Power Substation Equipments |
| CN105676126A (en) * | 2016-01-18 | 2016-06-15 | 常州工学院 | Electric power system main transformer cooling motor group monitoring device |
| CN112379211A (en) * | 2020-09-24 | 2021-02-19 | 国网吉林省电力有限公司电力科学研究院 | Detection method of power transmission line fault area positioning device |
| CN113359030A (en) * | 2021-06-09 | 2021-09-07 | 西安热工研究院有限公司 | Wind driven generator short circuit fault simulation platform based on external magnetic flux leakage detection |
| CN113670609A (en) * | 2021-07-21 | 2021-11-19 | 广州大学 | Fault detection method, system, device and medium based on wolf optimization algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 基于最优个体蚁群算法的配电网故障定位研究;邹琦 等;电气传动自动化(01);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116223937A (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116223937B (en) | Abnormality detection method, abnormality detection device, abnormality detection equipment and computer-readable storage medium | |
| CN112528519A (en) | Method, system, readable medium and electronic device for engine quality early warning service | |
| CN109839915A (en) | Diagnostic device, diagnostic method and storage medium | |
| CN108956111B (en) | Abnormal state detection method and detection system for mechanical part | |
| CN107391335B (en) | Method and equipment for checking health state of cluster | |
| CN109738014A (en) | The intelligent diagnosing method and system of city integrated piping lane equipment fault | |
| Zhang et al. | Few-shot bearing anomaly detection via model-agnostic meta-learning | |
| Al-Haddad et al. | Improved UAV blade unbalance prediction based on machine learning and ReliefF supreme feature ranking method | |
| US20050144537A1 (en) | Method to use a receiver operator characteristics curve for model comparison in machine condition monitoring | |
| Liu et al. | Validation of strain gauges for structural health monitoring with Bayesian belief networks | |
| CN117590159A (en) | Tunnel cable power supply state monitoring method and system based on deep learning | |
| CN103926494A (en) | Interference source determining method and device | |
| Kinaneva et al. | Application of artificial intelligence in UAV platforms for early forest fire detection | |
| Sands et al. | Output-only structural damage detection via enhanced random vibration analysis using LSTM/GRU model | |
| CN116953395B (en) | Method, device, equipment and storage medium for detecting electricity stealing of charging pile | |
| CN111555899B (en) | Alarm rule configuration method, equipment state monitoring method, device and storage medium | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| KR20210071438A (en) | Method of data analysis for detection of facility status | |
| CN116205885A (en) | Abnormal state detection method, system, electronic device and readable storage medium | |
| US11886831B2 (en) | Data sorting device and method, and monitoring and diagnosis device | |
| CN113204280A (en) | Method, system, equipment and medium for diagnosing power failure | |
| Gad et al. | A wind turbine fault identification using machine learning approach based on pigeon inspired optimizer | |
| CN110824293A (en) | Power grid fault diagnosis method based on multi-feature fusion parameters of wolf pack algorithm | |
| KR102515081B1 (en) | Apparatus and method for learning object detection software | |
| CN111090037A (en) | Reliability detection method for instrument control card |
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 |