CN116990683B - Driving motor locked rotor detection system and detection method based on electric variable - Google Patents
Driving motor locked rotor detection system and detection method based on electric variable Download PDFInfo
- Publication number
- CN116990683B CN116990683B CN202311243584.0A CN202311243584A CN116990683B CN 116990683 B CN116990683 B CN 116990683B CN 202311243584 A CN202311243584 A CN 202311243584A CN 116990683 B CN116990683 B CN 116990683B
- Authority
- CN
- China
- Prior art keywords
- driving motor
- phase current
- phase voltage
- time points
- phase
- 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 43
- 238000000034 method Methods 0.000 claims description 109
- 238000012545 processing Methods 0.000 claims description 10
- 238000004804 winding Methods 0.000 claims description 3
- 230000000712 assembly Effects 0.000 claims description 2
- 238000000429 assembly Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 abstract description 2
- 238000013528 artificial neural network Methods 0.000 description 15
- 238000013527 convolutional neural network Methods 0.000 description 9
- 230000005856 abnormality Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 125000004122 cyclic group Chemical group 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G01R31/34—Testing dynamo-electric machines
- G01R31/343—Testing dynamo-electric machines in operation
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P29/00—Arrangements for regulating or controlling electric motors, appropriate for both AC and DC motors
- H02P29/02—Providing protection against overload without automatic interruption of supply
- H02P29/024—Detecting a fault condition, e.g. short circuit, locked rotor, open circuit or loss of load
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Power Engineering (AREA)
- Control Of Ac Motors In General (AREA)
Abstract
The invention provides a driving motor locked rotor detection system and a detection method based on an electric variable, and relates to the field of electric variable measurement, wherein the detection system comprises: the electric variable prediction module is used for acquiring control parameters of the driving motor from a controller of the driving motor, acquiring related information of a driven load and predicting electric variables through an electric variable prediction model; the electric variable acquisition module is used for acquiring the electric variable of the driving motor; the locked rotor pre-judging module is used for determining a first locked rotor possibility based on the predicted electric variable and the electric variable of the driving motor; the reference information acquisition module is used for acquiring auxiliary judgment information; and the locked rotor detection module is used for determining the second locked rotor possibility based on the auxiliary judgment information, the predicted electric variable and the electric variable of the driving motor when the first locked rotor possibility is larger than a preset locked rotor possibility threshold value, and has the advantage of improving the locked rotor detection accuracy of the driving motor.
Description
Technical Field
The invention relates to the field of electric variable measurement, in particular to a driving motor locked rotor detection system and method based on electric variable.
Background
When the rotation speed of the motor is zero, the torque is still output, namely, the motor is blocked, and the driving motor is blocked, so that the problem of attention is needed in the design of the driving motor. There are many reasons for motor stalling, including mechanical or man-made, such as: the rotor and the stator are blocked by contact, the driven equipment is blocked, the motor cannot be driven due to too large equipment load, and the like, so that the locked rotor is caused. When the driving motor is blocked, the driving motor needs to increase output energy, and as the energy is obtained from current, the current is correspondingly increased, and the driving motor driving device is failed or burnt out due to overlarge current.
Chinese patent publication No. CN114966403a discloses a method and system for detecting a locked rotor fault of a motor of a new energy automobile, the method obtains multiple layers of IMF signals of three-phase current signals of the motor, obtains matching similarity between matching signals of three channels in a target layer after two-by-two matching, and determines whether the matching signal is a noise main layer according to average matching similarity in the target layer. And screening out useful information in the IMF signals of each channel in the noise main guide layer according to the Gaussian distribution model to obtain an adjusted IMF signal, and further obtaining a reconstruction signal by combining the IMF signals of the signal main guide layer. And judging whether the motor has a locked rotor fault or not according to the amplitude difference between each channel of the reconstruction signal.
Chinese patent publication No. CN110927570a discloses a method and apparatus for detecting locked rotor, wherein the method comprises: acquiring phase current and phase voltage of a motor in real time; calculating input power according to the phase current and the phase voltage; setting an initial value of the observation period to 0; acquiring the input power of a motor in real time; calculating a fluctuation value of input power; judging whether the motor is blocked according to the fluctuation value; the step of judging whether the motor is blocked according to the fluctuation value comprises the following steps: judging whether the fluctuation value is smaller than a fluctuation threshold value or not; when the fluctuation value is smaller than the fluctuation threshold value, continuing to time on the basis of the existing observation time length; when the fluctuation value is greater than or equal to the fluctuation threshold value, resetting the observation time length; judging whether the observation time length is greater than or equal to a preset time length; when the observed time length is greater than or equal to the preset time length, judging that the motor is blocked; and when the observed time length is smaller than the preset time length, returning to the step of judging whether the fluctuation value is smaller than the fluctuation threshold value.
However, in the above conventional techniques, the stall determination is performed based on the detected phase current of the motor, and erroneous diagnosis is likely to occur when the phase current fluctuates.
Therefore, it is necessary to provide a system and a method for detecting the stalling of a driving motor based on an electrical variable, which are used for improving the accuracy of the detection of the stalling of the driving motor.
Disclosure of Invention
One of the embodiments of the present specification provides a driving motor stall detection system based on an electrical variable, including: the electric variable prediction module is used for acquiring control parameters of the driving motor from a controller of the driving motor, acquiring related information of a driven load, and predicting electric variables of the driving motor at a plurality of time points in the working process based on the control parameters of the driving motor and the related information of the driven load through an electric variable prediction model; the electric variable acquisition module is used for acquiring electric variables of the driving motor at a plurality of time points in the working process of the driving motor, wherein the electric variables at least comprise phase current and phase voltage; the locked rotor pre-judging module is used for determining a first locked rotor possibility based on the predicted electric variables of the driving motor at a plurality of time points in the working process and the electric variables of the driving motor acquired at a plurality of time points in the working process; the reference information acquisition module is used for acquiring auxiliary judgment information at a plurality of time points in the working process of the driving motor; and the locked rotor detection module is used for determining a second locked rotor possibility based on auxiliary judgment information acquired at a plurality of time points of the driving motor in the working process, predicted electric variables at a plurality of time points of the driving motor in the working process and electric variables of the driving motor acquired at a plurality of time points of the driving motor in the working process when the first locked rotor possibility is larger than a preset locked rotor possibility threshold.
Further, the electrical variables of the plurality of time points in the working process of the driving motor predicted by the electrical variable prediction model at least comprise predicted A-phase currents of the plurality of time points in the working process of the driving motor, predicted B-phase currents of the plurality of time points in the working process of the driving motor, predicted C-phase currents of the plurality of time points in the working process of the driving motor, predicted A-phase voltages of the plurality of time points in the working process of the driving motor, predicted B-phase voltages of the plurality of time points in the working process of the driving motor and predicted C-phase voltages of the plurality of time points in the working process of the driving motor; the stall pre-judging module determines the first stall likelihood based on predicted electrical variables of the driving motor at a plurality of time points in the working process and electrical variables of the driving motor acquired at a plurality of time points in the working process, and the stall pre-judging module comprises: based on the predicted A-phase current of the driving motor at a plurality of time points in the working process, the predicted B-phase current of the driving motor at a plurality of time points in the working process, the predicted C-phase current of the driving motor at a plurality of time points in the working process, the predicted A-phase voltage of the driving motor at a plurality of time points in the working process, the predicted B-phase voltage of the driving motor at a plurality of time points in the working process and the predicted C-phase voltage of the driving motor at a plurality of time points in the working process respectively, generating an A-phase current prediction curve, a B-phase current prediction curve, a C-phase current prediction curve, an A-phase voltage prediction curve, a B-phase voltage prediction curve and a C-phase voltage prediction curve; denoising the A-phase current, the B-phase current, the C-phase current, the A-phase voltage, the B-phase voltage and the C-phase voltage which are acquired at a plurality of historical time points to generate an A-phase current history curve, a B-phase current history curve, a C-phase current history curve, an A-phase voltage history curve, a B-phase voltage history curve and a C-phase voltage history curve; intercepting an A-phase current prediction curve segment, a B-phase current prediction curve segment, a C-phase current prediction curve segment, an A-phase voltage prediction curve segment, a B-phase voltage prediction curve segment and a C-phase voltage prediction curve segment which correspond to the plurality of history points from the A-phase current prediction curve, the B-phase current prediction curve, the C-phase current prediction curve, the A-phase voltage prediction curve, the B-phase voltage prediction curve and the C-phase voltage prediction curve; and determining the first locked-rotor possibility based on the A-phase current similarity of the A-phase current history curve and the A-phase current prediction curve segment, the B-phase current similarity of the B-phase current history curve and the B-phase current prediction curve segment, the C-phase current similarity of the C-phase current history curve and the C-phase current prediction curve segment, the A-phase voltage similarity of the A-phase voltage history curve and the A-phase voltage prediction curve segment, the B-phase voltage similarity of the B-phase voltage history curve and the B-phase voltage prediction curve segment, and the C-phase voltage similarity of the C-phase voltage history curve and the C-phase voltage prediction curve segment.
Further, the electrical variable prediction model performs denoising processing on an a-phase current, a B-phase current, a C-phase current, an a-phase voltage, a B-phase voltage, and a C-phase voltage acquired at a plurality of historical time points, and generates an a-phase current history curve, a B-phase current history curve, a C-phase current history curve, an a-phase voltage history curve, a B-phase voltage history curve, and a C-phase voltage history curve, including: generating an initial a-phase current history curve, an initial B-phase current history curve, an initial C-phase current history curve, an initial a-phase voltage history curve, an initial B-phase voltage history curve, and an initial C-phase voltage history curve based on the a-phase current, the B-phase current, the C-phase current, the a-phase voltage, the B-phase voltage, and the C-phase voltage acquired at a plurality of history time points, respectively; decomposing the initial A-phase current history curve into at least one A-phase current connotation modal component and one A-phase current residual; decomposing the initial B-phase current history curve into at least one B-phase current connotation modal component and one B-phase current residual; decomposing the initial C-phase current history curve into at least one C-phase current connotation modal component and one C-phase current residual; decomposing the initial A-phase voltage history curve into at least one A-phase voltage connotation modal component and one A-phase voltage residual; decomposing the initial B-phase voltage history curve into at least one B-phase voltage connotation modal component and one B-phase voltage residual; decomposing the initial C-phase voltage history curve into at least one C-phase current connotation modal component and one C-phase voltage residual; and denoising based on the at least one A-phase current connotation mode component and one A-phase current residual error, the at least one B-phase current connotation mode component and one B-phase current residual error, the at least one C-phase current connotation mode component and one C-phase current residual error, the A-phase voltage connotation mode component and one A-phase voltage residual error, the B-phase voltage connotation mode component and one B-phase voltage residual error and the at least one C-phase current connotation mode component and one C-phase voltage residual error by a denoising model to generate an A-phase current history curve, a B-phase current history curve, a C-phase current history curve, an A-phase voltage history curve, a B-phase voltage history curve and a C-phase voltage history curve.
Further, the reference information acquisition module comprises a sound acquisition unit, a vibration sensing unit and a temperature sensing unit, wherein the vibration sensing unit comprises a plurality of vibration sensing components which are respectively arranged at different positions of the connection part of the driven load and the driving motor; the sound acquisition unit is arranged at the joint of the driven load and the driving motor: the temperature sensing unit comprises a plurality of groups of temperature sensing components, and the temperature sensing components are respectively arranged at different positions of the winding of the driving motor.
Further, the reference information acquisition module determining the locations of the plurality of vibration sensing components includes: establishing a three-dimensional model of the joint of the driven load and the driving motor; based on the three-dimensional model, the locations of the plurality of vibration sensing components are determined.
Further, the position of the sound acquisition unit is determined based on the positions of the plurality of vibration sensing components.
Further, the stall detection module determines a second stall likelihood based on auxiliary judgment information acquired at a plurality of time points of the driving motor during operation, predicted electrical variables of the driving motor at a plurality of time points of the driving motor during operation, and electrical variables of the driving motor acquired at a plurality of time points of the driving motor during operation, including: performing data processing on vibration data acquired by the plurality of vibration sensing components at the plurality of historical time points based on the sound data acquired by the sound acquisition unit at the plurality of historical time points, and generating a vibration history curve; performing data processing on temperature data acquired by the plurality of groups of temperature sensing components at the plurality of historical time points to generate a temperature historical curve; and determining the second locked-rotor possibility based on the vibration history curve, the temperature history curve, the predicted electrical variables of the driving motor at a plurality of time points in the working process and the electrical variables of the driving motor acquired at a plurality of time points in the working process of the driving motor.
Further, the locked rotor detection module corrects vibration data acquired by the plurality of vibration sensing components at the plurality of history time points based on the sound data acquired by the sound acquisition unit at the plurality of history time points, and generates a vibration history curve, including: generating a plurality of initial vibration history curves based on vibration data acquired by the plurality of vibration sensing components at the plurality of history time points; correcting the plurality of vibration history curves based on the sound data acquired by the sound acquisition unit at the plurality of history time points, and generating corrected plurality of initial vibration history curves; fitting the corrected multiple initial vibration history curves to generate the vibration history curves.
Further, the stall detection module determines the second stall likelihood based on the vibration history curve, the temperature history curve, the predicted electrical variables of the driving motor at a plurality of time points in the working process, and the electrical variables of the driving motor acquired at a plurality of time points in the working process, including: and determining the second possibility of locked rotor through a locked rotor detection model based on the vibration history curve, the temperature history curve, the predicted electric variables of the driving motor at a plurality of time points in the working process and the electric variables of the driving motor acquired at a plurality of time points in the working process of the driving motor.
One of the embodiments of the present specification provides a method for detecting a locked rotor of a driving motor based on an electrical variable, including: acquiring control parameters of a driving motor from a controller of the driving motor; acquiring related information of a driven load; predicting electric variables of the driving motor at a plurality of time points in the working process based on control parameters of the driving motor and related information of the driven load through an electric variable prediction model; acquiring electric variables of the driving motor at a plurality of time points in the working process of the driving motor, wherein the electric variables at least comprise phase current and phase voltage; acquiring auxiliary judgment information at a plurality of time points of the driving motor in the working process; determining a first possibility of stalling based on predicted electrical variables of the driving motor at a plurality of time points in the working process and electrical variables of the driving motor acquired at a plurality of time points in the working process; and when the first stall possibility is larger than a preset stall possibility threshold, determining a second stall possibility based on auxiliary judgment information acquired at a plurality of time points of the driving motor in the working process, predicted electric variables of the driving motor at a plurality of time points of the driving motor in the working process and electric variables of the driving motor acquired at a plurality of time points of the driving motor in the working process.
Compared with the prior art, the driving motor locked rotor detection system and the detection method based on the electric variable provided by the specification have the following beneficial effects:
1. the occurrence of the stall condition is directly judged based on the predicted electric variables of the driving motor at a plurality of time points in the working process and the electric variables of the driving motor obtained at a plurality of time points in the working process, the stall judgment is inaccurate, bus overcurrent or phase current abnormality can be caused by reasons such as voltage abnormality, damage to control panel components, over-power and the like, the cause logic is not unique, and when the stall occurs, the fault causing the bus overcurrent or the phase current abnormality can not be determined possibly, so that false detection is generated, therefore, secondary judgment is needed, and the second stall possibility is determined based on the auxiliary judgment information obtained at a plurality of time points in the working process of the driving motor, the predicted electric variables of the driving motor at a plurality of time points in the working process of the driving motor and the electric variables of the driving motor obtained at a plurality of time points in the working process of the driving motor, and the accuracy of the stall detection of the driving motor based on the electric variables is improved.
2. The denoising process is performed on the basis of at least one A-phase current inclusion modal component and one A-phase current residual error, at least one B-phase current inclusion modal component and one B-phase current residual error, at least one C-phase current inclusion modal component and one C-phase current residual error, an A-phase voltage inclusion modal component and one A-phase voltage residual error, a B-phase voltage inclusion modal component and one B-phase voltage residual error and at least one C-phase current inclusion modal component and one C-phase voltage residual error by a denoising model, so that a relatively accurate A-phase current history curve, B-phase current history curve, C-phase current history curve, A-phase voltage history curve, B-phase voltage history curve and C-phase voltage history curve can be generated more rapidly.
Drawings
The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:
FIG. 1 is a block diagram of a drive motor stall detection system based on electrical variables according to some embodiments of the present disclosure;
FIG. 2 is a schematic flow diagram illustrating a determination of a first possibility of stall according to some embodiments of the present description;
FIG. 3 is a schematic flow diagram of generating an A-phase current history curve, a B-phase current history curve, a C-phase current history curve, an A-phase voltage history curve, a B-phase voltage history curve, and a C-phase voltage history curve according to some embodiments of the present disclosure;
fig. 4 is a flow chart of a method for detecting a locked rotor of a drive motor based on an electrical variable according to some embodiments of the present disclosure.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.
Fig. 1 is a schematic block diagram of a driving motor stall detection system based on electric variables according to some embodiments of the present disclosure, and as shown in fig. 1, a driving motor stall detection system based on electric variables may include an electric variable prediction module, an electric variable acquisition module, a stall pre-determination module, a reference information acquisition module, and a stall detection module. The respective modules are described in order below.
The electrical variable prediction module may be configured to obtain control parameters of the drive motor (e.g., torque, rotational speed, etc. of the drive motor at various points in time during operation) from a controller of the drive motor, and obtain information about the driven load (e.g., weight of the driven load).
The electric variable prediction module can also predict electric variables of the driving motor at a plurality of time points in the working process through an electric variable prediction model based on control parameters of the driving motor and related information of the driven load. The electrical variable prediction model may include, but is not limited to, a Neural Network (NN), a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a cyclic neural network (RNN), etc., or any combination thereof, for example, the electrical variable prediction model may be a model formed by combining the convolutional neural network and the deep neural network.
Further, the electrical variables of the plurality of time points of the driving motor in the working process predicted by the electrical variable prediction model at least comprise A-phase currents of the plurality of time points of the driving motor in the working process, B-phase currents of the plurality of time points of the driving motor in the working process, C-phase currents of the plurality of time points of the driving motor in the working process, A-phase voltages of the plurality of time points of the driving motor in the working process, B-phase voltages of the plurality of time points of the driving motor in the working process and C-phase voltages of the plurality of time points of the driving motor in the working process.
The electrical variable acquisition module may be configured to acquire electrical variables of the drive motor at a plurality of points in time during operation of the drive motor.
The electrical variables include at least phase current and phase voltage, such as a-phase current, B-phase current, C-phase current, a-phase voltage, B-phase voltage, and C-phase voltage.
The stall pre-determination module may be configured to determine a first stall likelihood based on the predicted electrical variables of the drive motor at a plurality of points in time during operation and the electrical variables of the drive motor obtained at the plurality of points in time during operation.
Fig. 2 is a schematic flow chart of determining a first possibility of stalling, as shown in fig. 2, according to some embodiments of the present disclosure, further including:
generating an A-phase current prediction curve, a B-phase current prediction curve, a C-phase current prediction curve, an A-phase voltage prediction curve, a B-phase voltage prediction curve and a C-phase voltage prediction curve based on the A-phase current of the predicted driving motor at a plurality of time points in the working process, the B-phase current of the predicted driving motor at a plurality of time points in the working process and the C-phase voltage of the predicted driving motor at a plurality of time points in the working process respectively;
denoising the A-phase current, the B-phase current, the C-phase current, the A-phase voltage, the B-phase voltage and the C-phase voltage which are acquired at a plurality of historical time points to generate an A-phase current history curve, a B-phase current history curve, a C-phase current history curve, an A-phase voltage history curve, a B-phase voltage history curve and a C-phase voltage history curve;
Intercepting an A-phase current prediction curve segment, a B-phase current prediction curve segment, a C-phase current prediction curve segment, an A-phase voltage prediction curve segment, a B-phase voltage prediction curve segment and a C-phase voltage prediction curve segment which correspond to a plurality of history points from an A-phase current prediction curve, a B-phase current prediction curve, a C-phase current prediction curve, a B-phase voltage prediction curve and a C-phase voltage prediction curve;
the first stall likelihood is determined based on a phase A current similarity of the phase A current history curve and the phase A current prediction curve segment, a phase B current similarity of the phase B current history curve and the phase B current prediction curve segment, a phase C current similarity of the phase C current history curve and the phase C current prediction curve segment, a phase A voltage similarity of the phase A voltage history curve and the phase A voltage prediction curve segment, a phase B voltage similarity of the phase B voltage history curve and the phase B voltage prediction curve segment, and a phase C voltage similarity of the phase C voltage history curve and the phase C voltage prediction curve segment.
For example only, the first stall likelihood may be determined by the following formula:
；
wherein,for the first locked rotor possibility, +.>For the A phase current similarity of the A phase current history curve and the A phase current prediction curve segment,/I >B-phase current similarity of B-phase current history curve and B-phase current prediction curve segment,/-phase current similarity of B-phase current history curve and B-phase current prediction curve segment>C-phase current similarity of C-phase current history curve and C-phase current prediction curve segment,/-phase current similarity of C-phase current history curve and C-phase current prediction curve segment>A phase voltage similarity of the A phase voltage history curve and the A phase voltage prediction curve segment is +.>B-phase voltage similarity of B-phase voltage history curve and B-phase voltage prediction curve segment, < >>C-phase voltage similarity of C-phase voltage history curve and C-phase voltage prediction curve segment,/>For preset parameters, < >>、/>、/>、/>、/>AndAll are preset weights.
FIG. 3 is a schematic flow chart of generating an A-phase current history curve, a B-phase current history curve, a C-phase current history curve, an A-phase voltage history curve, a B-phase voltage history curve, and a C-phase voltage history curve according to some embodiments of the present disclosure, further, as shown in FIG. 3, an electrical variable prediction model performs denoising processing on an A-phase current, a B-phase current, a C-phase current, an A-phase voltage, a B-phase voltage, and a C-phase voltage acquired at a plurality of history time points, to generate an A-phase current history curve, a B-phase current history curve, a C-phase current history curve, an A-phase voltage history curve, a B-phase voltage history curve, and a C-phase voltage history curve, including:
Generating an initial a-phase current history curve, an initial B-phase current history curve, an initial C-phase current history curve, an initial a-phase voltage history curve, an initial B-phase voltage history curve, and an initial C-phase voltage history curve based on the a-phase current, the B-phase current, the C-phase current, the a-phase voltage, the B-phase voltage, and the C-phase voltage acquired at a plurality of history time points, respectively;
decomposing the initial A-phase current history curve into at least one A-phase current connotation modal component and one A-phase current residual;
decomposing the initial B-phase current history curve into at least one B-phase current connotation modal component and one B-phase current residual;
decomposing the initial C-phase current history curve into at least one C-phase current connotation modal component and one C-phase current residual;
decomposing the initial A-phase voltage history curve into at least one A-phase voltage connotation modal component and one A-phase voltage residual;
decomposing the initial B-phase voltage history curve into at least one B-phase voltage connotation modal component and one B-phase voltage residual;
decomposing the initial C-phase voltage history curve into at least one C-phase current connotation modal component and one C-phase voltage residual;
denoising is performed by a denoising model based on at least one a-phase current inclusion modal component and one a-phase current residual, at least one B-phase current inclusion modal component and one B-phase current residual, at least one C-phase current inclusion modal component and one C-phase current residual, an a-phase voltage inclusion modal component and one a-phase voltage residual, a B-phase voltage inclusion modal component and one B-phase voltage residual and at least one C-phase current inclusion modal component and one C-phase voltage residual, and an a-phase current history curve, a B-phase current history curve, a C-phase current history curve, an a-phase voltage history curve, a B-phase voltage history curve, and a C-phase voltage history curve, wherein the denoising model may include, but is not limited to, a Neural Network (NN), a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a cyclic neural network (RNN), and the like, or any combination thereof, and the denoising model may be a model formed by combining a convolutional neural network and a deep neural network, for example.
The reference information acquisition module may be configured to acquire the auxiliary judgment information at a plurality of time points during operation of the driving motor.
Further, the reference information acquisition module comprises a sound acquisition unit, a vibration sensing unit and a temperature sensing unit, wherein the vibration sensing unit comprises a plurality of vibration sensing components, and the plurality of vibration sensing components are respectively arranged at different positions of the connection part of the driven load and the driving motor; the sound acquisition unit is arranged at the joint of the driven load and the driving motor: the temperature sensing unit comprises a plurality of groups of temperature sensing components, and the temperature sensing components are respectively arranged at different positions of the winding of the driving motor.
Further, the reference information acquisition module determines the locations of the plurality of vibration sensing components, including:
establishing a three-dimensional model of the joint of the driven load and the driving motor;
based on the three-dimensional model, the locations of the plurality of vibration sensing components are determined.
Specifically, the reference information acquisition module may perform mechanical analysis based on the three-dimensional model to determine the positions of the plurality of vibration sensing components.
Further, the position of the sound acquisition unit is determined based on the positions of the plurality of vibration sensing components.
For example, the reference information acquisition module may generate candidate positions of at least one sound acquisition unit based on a constraint condition set, where the constraint condition set may include a shortest distance constraint of the sound acquisition unit and the vibration sensing assembly, a longest distance constraint of the sound acquisition unit and the vibration sensing assembly, and the like, and for each candidate position, determine a position priority value of the candidate position, and take a candidate position with the largest position priority value as an installation position of the sound acquisition unit.
For example only, the reference information acquisition module may determine the position priority value for the candidate position based on the following formula:
；
wherein,position priority value for candidate position, +.>For preset parameters, < >>For the distance between the candidate position and the ith vibration sensing element, +.>For the average distance between the candidate location and the plurality of vibration sensing components,the weight corresponding to the ith vibration sensing component is given, and I is the total number of the vibration sensing components.
The stall detection module may be configured to determine, when the first stall likelihood is greater than a preset stall likelihood threshold, a second stall likelihood based on auxiliary determination information acquired at a plurality of time points of the driving motor during operation, predicted electrical variables of the driving motor at a plurality of time points of the driving motor during operation, and electrical variables of the driving motor acquired at a plurality of time points of the driving motor during operation.
It can be understood that the occurrence of the stall condition is directly determined based on the predicted electric variables of the driving motor at a plurality of time points in the working process and the electric variables of the driving motor obtained at a plurality of time points in the working process, the stall determination is inaccurate, bus overcurrent or phase current abnormality may be caused by reasons such as voltage abnormality, damage to control panel components, overpower and the like, and cause logic is not unique, and when stall occurs, the fault causing the bus overcurrent or phase current abnormality may not be determined at probability, so that false detection is generated, and therefore, secondary determination needs to be performed, and the second stall possibility is determined based on the auxiliary determination information obtained at a plurality of time points in the working process of the driving motor, the predicted electric variables of the driving motor at a plurality of time points in the working process and the electric variables of the driving motor obtained at a plurality of time points in the working process of the driving motor, thereby improving the accuracy of the stall detection of the driving motor.
Further, the stall detection module determines a second stall likelihood based on auxiliary determination information acquired at a plurality of time points of the driving motor during operation, predicted electrical variables of the driving motor at a plurality of time points of the driving motor during operation, and electrical variables of the driving motor acquired at a plurality of time points of the driving motor during operation, including:
Performing data processing (e.g., denoising, fitting, etc.) on vibration data acquired by the plurality of vibration sensing components at a plurality of historical time points based on sound data acquired by the sound acquisition unit at the plurality of historical time points, and generating a vibration history curve;
performing data processing (such as denoising, fitting and the like) on temperature data acquired by a plurality of groups of temperature sensing components at a plurality of historical time points to generate a temperature history curve;
the second possibility of stalling is determined based on the vibration history curve, the temperature history curve, the predicted electrical variables of the drive motor at a plurality of points in time during operation, and the electrical variables of the drive motor obtained at a plurality of points in time during operation.
Further, the locked rotor detection module corrects vibration data acquired by the plurality of vibration sensing components at a plurality of history time points based on sound data acquired by the sound acquisition unit at the plurality of history time points, and generates a vibration history curve, including:
generating a plurality of initial vibration history curves based on vibration data acquired by the plurality of vibration sensing assemblies at a plurality of history time points;
correcting the plurality of vibration history curves based on the sound data acquired by the sound acquisition unit at a plurality of history time points, and generating a plurality of corrected initial vibration history curves;
Fitting the corrected multiple initial vibration history curves to generate a vibration history curve.
For example, the locked rotor detection module may modify the plurality of vibration history curves based on the sound data acquired by the sound acquisition unit at a plurality of history time points through a modification model, and generate a plurality of modified initial vibration history curves, where the modification model may include, but is not limited to, a Neural Network (NN), a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a cyclic neural network (RNN), or any combination thereof, and for example, the modification model may be a model formed by combining the convolutional neural network and the deep neural network.
Further, the locked rotor detection module may determine the second locked rotor likelihood based on the vibration history curve, the temperature history curve, the predicted electrical variables of the driving motor at a plurality of time points in the working process, and the electrical variables of the driving motor acquired at a plurality of time points in the working process.
Fig. 4 is a schematic flow chart of a method for detecting a locked-rotor of a driving motor based on an electrical variable according to some embodiments of the present disclosure, as shown in fig. 4, the method for detecting a locked-rotor of a driving motor based on an electrical variable may include the following steps:
Step 410, obtaining control parameters of the drive motor from a controller of the drive motor.
Step 420, obtaining information about the driven load.
Step 430, predicting the electric variables of the driving motor at a plurality of time points in the working process by using the electric variable prediction model based on the control parameters of the driving motor and the related information of the driven load.
Step 440, obtaining an electrical variable of the drive motor at a plurality of time points during operation of the drive motor.
Step 450, obtaining auxiliary judgment information at a plurality of time points in the working process of the driving motor.
Step 460 of determining a first possibility of stalling based on the predicted electrical variables of the drive motor at a plurality of points in time during operation and the electrical variables of the drive motor obtained at the plurality of points in time during operation.
Step 470, determining a second stall likelihood based on the auxiliary judgment information acquired at a plurality of time points of the driving motor during operation, the predicted electric variables of the driving motor at a plurality of time points of the driving motor during operation, and the electric variables of the driving motor acquired at a plurality of time points of the driving motor during operation when the first stall likelihood is greater than the preset stall likelihood threshold.
Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.
Claims (8)
1. A drive motor stall detection system based on electrical variables, comprising:
the electric variable prediction module is used for acquiring control parameters of the driving motor from a controller of the driving motor, acquiring related information of a driven load, and predicting electric variables of the driving motor at a plurality of time points in the working process based on the control parameters of the driving motor and the related information of the driven load through an electric variable prediction model;
the electric variable acquisition module is used for acquiring electric variables of the driving motor at a plurality of time points in the working process of the driving motor, wherein the electric variables at least comprise phase current and phase voltage;
the locked rotor pre-judging module is used for determining a first locked rotor possibility based on the predicted electric variables of the driving motor at a plurality of time points in the working process and the electric variables of the driving motor acquired at a plurality of time points in the working process;
The reference information acquisition module is used for acquiring auxiliary judgment information at a plurality of time points in the working process of the driving motor;
the locked rotor detection module is used for determining a second locked rotor possibility based on auxiliary judgment information acquired at a plurality of time points of the driving motor in the working process, based on predicted electric variables of the driving motor at a plurality of time points of the driving motor in the working process and based on electric variables of the driving motor acquired at a plurality of time points of the driving motor in the working process when the first locked rotor possibility is larger than a preset locked rotor possibility threshold;
the electric variables of the plurality of time points in the working process of the driving motor predicted by the electric variable prediction model at least comprise predicted A-phase currents of the plurality of time points in the working process of the driving motor, predicted B-phase currents of the plurality of time points in the working process of the driving motor, predicted C-phase currents of the plurality of time points in the working process of the driving motor, predicted A-phase voltages of the plurality of time points in the working process of the driving motor, predicted B-phase voltages of the plurality of time points in the working process of the driving motor and predicted C-phase voltages of the plurality of time points in the working process of the driving motor;
The stall pre-judging module determines the first stall likelihood based on predicted electrical variables of the driving motor at a plurality of time points in the working process and electrical variables of the driving motor acquired at a plurality of time points in the working process, and the stall pre-judging module comprises:
based on the predicted A-phase current of the driving motor at a plurality of time points in the working process, the predicted B-phase current of the driving motor at a plurality of time points in the working process, the predicted C-phase current of the driving motor at a plurality of time points in the working process, the predicted A-phase voltage of the driving motor at a plurality of time points in the working process, the predicted B-phase voltage of the driving motor at a plurality of time points in the working process and the predicted C-phase voltage of the driving motor at a plurality of time points in the working process respectively, generating an A-phase current prediction curve, a B-phase current prediction curve, a C-phase current prediction curve, an A-phase voltage prediction curve, a B-phase voltage prediction curve and a C-phase voltage prediction curve;
denoising the A-phase current, the B-phase current, the C-phase current, the A-phase voltage, the B-phase voltage and the C-phase voltage which are acquired at a plurality of historical time points to generate an A-phase current history curve, a B-phase current history curve, a C-phase current history curve, an A-phase voltage history curve, a B-phase voltage history curve and a C-phase voltage history curve;
Intercepting an A-phase current prediction curve segment, a B-phase current prediction curve segment, a C-phase current prediction curve segment, an A-phase voltage prediction curve segment, a B-phase voltage prediction curve segment and a C-phase voltage prediction curve segment which correspond to the historical time points from the A-phase current prediction curve, the B-phase current prediction curve, the C-phase current prediction curve, the A-phase voltage prediction curve, the B-phase voltage prediction curve and the C-phase voltage prediction curve;
determining the first stall likelihood based on a phase current similarity of the a phase current history curve and the a phase current prediction curve segment, a phase current similarity of the B phase current history curve and the B phase current prediction curve segment, a phase current similarity of the C phase current history curve and the C phase current prediction curve segment, a phase voltage similarity of the a phase voltage history curve and the a phase voltage prediction curve segment, a phase voltage similarity of the B phase voltage history curve and the B phase voltage prediction curve segment, and a phase voltage similarity of the C phase voltage history curve and the C phase voltage prediction curve segment;
the locked rotor pre-judging module performs denoising processing on an A-phase current, a B-phase current, a C-phase current, an A-phase voltage, a B-phase voltage and a C-phase voltage acquired at a plurality of historical time points to generate an A-phase current history curve, a B-phase current history curve, a C-phase current history curve, an A-phase voltage history curve, a B-phase voltage history curve and a C-phase voltage history curve, and comprises the following steps:
Generating an initial a-phase current history curve, an initial B-phase current history curve, an initial C-phase current history curve, an initial a-phase voltage history curve, an initial B-phase voltage history curve, and an initial C-phase voltage history curve based on the a-phase current, the B-phase current, the C-phase current, the a-phase voltage, the B-phase voltage, and the C-phase voltage acquired at a plurality of history time points, respectively;
decomposing the initial A-phase current history curve into at least one A-phase current connotation modal component and one A-phase current residual;
decomposing the initial B-phase current history curve into at least one B-phase current connotation modal component and one B-phase current residual;
decomposing the initial C-phase current history curve into at least one C-phase current connotation modal component and one C-phase current residual;
decomposing the initial A-phase voltage history curve into at least one A-phase voltage connotation modal component and one A-phase voltage residual;
decomposing the initial B-phase voltage history curve into at least one B-phase voltage connotation modal component and one B-phase voltage residual;
decomposing the initial C-phase voltage history curve into at least one C-phase voltage connotation modal component and one C-phase voltage residual;
and denoising based on the at least one A-phase current connotation mode component and one A-phase current residual error, the at least one B-phase current connotation mode component and one B-phase current residual error, the at least one C-phase current connotation mode component and one C-phase current residual error, the A-phase voltage connotation mode component and one A-phase voltage residual error, the B-phase voltage connotation mode component and one B-phase voltage connotation mode component and the at least one C-phase voltage connotation mode component and one C-phase voltage residual error by a denoising model to generate an A-phase current history curve, a B-phase current history curve, a C-phase current history curve, an A-phase voltage history curve, a B-phase voltage history curve and a C-phase voltage history curve.
2. The system of claim 1, wherein the reference information acquisition module comprises a sound acquisition unit, a vibration sensing unit and a temperature sensing unit, wherein the vibration sensing unit comprises a plurality of vibration sensing components, and the plurality of vibration sensing components are respectively arranged at different positions of the connection part of the driven load and the driving motor;
the sound acquisition unit is arranged at the joint of the driven load and the driving motor:
the temperature sensing unit comprises a plurality of groups of temperature sensing components, and the temperature sensing components are respectively arranged at different positions of the winding of the driving motor.
3. The electrical variable based drive motor stall detection system of claim 2, wherein the reference information acquisition module determines the position of the plurality of vibration sensing components comprising:
establishing a three-dimensional model of the joint of the driven load and the driving motor;
based on the three-dimensional model, the locations of the plurality of vibration sensing components are determined.
4. A drive motor lock detection system based on an electrical variable as recited in claim 3, wherein the position of the sound acquisition unit is determined based on the positions of the plurality of vibration sensing assemblies.
5. The electrical variable based drive motor stall detection system of claim 4, wherein the stall detection module determines a second stall likelihood based on the auxiliary determination information obtained at a plurality of points in time during operation of the drive motor, the predicted electrical variable at a plurality of points in time during operation of the drive motor, and the electrical variable of the drive motor obtained at a plurality of points in time during operation of the drive motor, comprising:
performing data processing on vibration data acquired by the plurality of vibration sensing components at the plurality of historical time points based on the sound data acquired by the sound acquisition unit at the plurality of historical time points, and generating a vibration history curve;
performing data processing on temperature data acquired by the plurality of groups of temperature sensing components at the plurality of historical time points to generate a temperature historical curve;
and determining the second locked-rotor possibility based on the vibration history curve, the temperature history curve, the predicted electrical variables of the driving motor at a plurality of time points in the working process and the electrical variables of the driving motor acquired at a plurality of time points in the working process of the driving motor.
6. The system of claim 5, wherein the stall detection module performs data processing on vibration data acquired by the plurality of vibration sensing components at the plurality of historical time points based on sound data acquired by the sound acquisition unit at the plurality of historical time points, and generates a vibration history curve, comprising:
generating a plurality of initial vibration history curves based on vibration data acquired by the plurality of vibration sensing components at the plurality of history time points;
correcting the plurality of initial vibration history curves based on the sound data acquired by the sound acquisition unit at the plurality of history time points, and generating corrected plurality of initial vibration history curves;
fitting the corrected multiple initial vibration history curves to generate the vibration history curves.
7. The electrical variable based drive motor stall detection system of claim 6, wherein the stall detection module determines the second stall likelihood based on the vibration history curve, the temperature history curve, predicted electrical variables for a plurality of points in time of the drive motor during operation, and electrical variables for the drive motor obtained at a plurality of points in time of the drive motor during operation, comprising:
And determining the second possibility of locked rotor through a locked rotor detection model based on the vibration history curve, the temperature history curve, the predicted electric variables of the driving motor at a plurality of time points in the working process and the electric variables of the driving motor acquired at a plurality of time points in the working process of the driving motor.
8. A method for detecting the stalling of a drive motor based on an electric variable by using the detection system as claimed in any one of claims 1 to 7, comprising:
acquiring control parameters of a driving motor from a controller of the driving motor;
acquiring related information of a driven load;
predicting electric variables of the driving motor at a plurality of time points in the working process based on control parameters of the driving motor and related information of the driven load through an electric variable prediction model;
acquiring electric variables of the driving motor at a plurality of time points in the working process of the driving motor, wherein the electric variables at least comprise phase current and phase voltage;
acquiring auxiliary judgment information at a plurality of time points of the driving motor in the working process;
determining a first possibility of stalling based on predicted electrical variables of the driving motor at a plurality of time points in the working process and electrical variables of the driving motor acquired at a plurality of time points in the working process;
And when the first stall possibility is larger than a preset stall possibility threshold, determining a second stall possibility based on auxiliary judgment information acquired at a plurality of time points of the driving motor in the working process, predicted electric variables of the driving motor at a plurality of time points of the driving motor in the working process and electric variables of the driving motor acquired at a plurality of time points of the driving motor in the working process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311243584.0A CN116990683B (en) | 2023-09-26 | 2023-09-26 | Driving motor locked rotor detection system and detection method based on electric variable |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311243584.0A CN116990683B (en) | 2023-09-26 | 2023-09-26 | Driving motor locked rotor detection system and detection method based on electric variable |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116990683A CN116990683A (en) | 2023-11-03 |
| CN116990683B true CN116990683B (en) | 2023-12-29 |
Family
ID=88532427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311243584.0A Active CN116990683B (en) | 2023-09-26 | 2023-09-26 | Driving motor locked rotor detection system and detection method based on electric variable |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116990683B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118112417B (en) * | 2024-04-30 | 2024-06-21 | 普诚创智（成都）科技有限公司 | Motor locked rotor detection method and system and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100810979B1 (en) * | 2006-12-08 | 2008-03-12 | 대림대학 산학협력단 | A method for detecting defects of induction motors |
| CN111397666A (en) * | 2020-04-28 | 2020-07-10 | 上海艾临科智能科技有限公司 | Generator test equipment |
| WO2021095142A1 (en) * | 2019-11-12 | 2021-05-20 | 三菱電機株式会社 | Failure prediction device, learning device, and learning method |
| CN114066274A (en) * | 2021-11-22 | 2022-02-18 | 通用电气（武汉）自动化有限公司 | Equipment performance early warning method and device |
| CN114184955A (en) * | 2021-11-22 | 2022-03-15 | 无锡新泰克电机有限公司 | Motor fault detection method, system and storage medium |
| CN115559928A (en) * | 2022-11-18 | 2023-01-03 | 淄博博睿机电科技有限公司 | Direct current brushless fan controller fault monitoring system based on big data |
| CN115940744A (en) * | 2022-10-28 | 2023-04-07 | 重庆青山工业有限责任公司 | Motor locked-rotor detection method based on vector control |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10984154B2 (en) * | 2018-12-27 | 2021-04-20 | Utopus Insights, Inc. | System and method for evaluating models for predictive failure of renewable energy assets |
-
2023
- 2023-09-26 CN CN202311243584.0A patent/CN116990683B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100810979B1 (en) * | 2006-12-08 | 2008-03-12 | 대림대학 산학협력단 | A method for detecting defects of induction motors |
| WO2021095142A1 (en) * | 2019-11-12 | 2021-05-20 | 三菱電機株式会社 | Failure prediction device, learning device, and learning method |
| CN111397666A (en) * | 2020-04-28 | 2020-07-10 | 上海艾临科智能科技有限公司 | Generator test equipment |
| CN114066274A (en) * | 2021-11-22 | 2022-02-18 | 通用电气（武汉）自动化有限公司 | Equipment performance early warning method and device |
| CN114184955A (en) * | 2021-11-22 | 2022-03-15 | 无锡新泰克电机有限公司 | Motor fault detection method, system and storage medium |
| CN115940744A (en) * | 2022-10-28 | 2023-04-07 | 重庆青山工业有限责任公司 | Motor locked-rotor detection method based on vector control |
| CN115559928A (en) * | 2022-11-18 | 2023-01-03 | 淄博博睿机电科技有限公司 | Direct current brushless fan controller fault monitoring system based on big data |
Non-Patent Citations (1)
| Title |
|---|
| EEMD模糊熵和变量预测模型的转子故障诊断新方法;崔心瀚;内燃机工程;第37卷(第4期);84-90 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116990683A (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116990683B (en) | Driving motor locked rotor detection system and detection method based on electric variable | |
| Odgaard et al. | Results of a wind turbine FDI competition | |
| CN111458666B (en) | Permanent magnet synchronous motor winding open-circuit fault diagnosis method | |
| JP6238928B2 (en) | Diagnostic equipment for electric motors | |
| CN104422918B (en) | Method for detecting current sensor fault in electronic drive system by using voltage command error | |
| CN109477869B (en) | Diagnostic device for motor | |
| CN112910375B (en) | Integrated Fault Isolation and Prognosis System for Electric Drive Systems | |
| CN112041819B (en) | Method for monitoring and identifying sensor faults in an electric drive system | |
| Bourogaoui et al. | An effective encoder fault detection in PMSM drives at different speed ranges | |
| KR101808461B1 (en) | Method and apparatus for predicting remaining life of a machine | |
| CN111693867A (en) | Electric drive system winding open-circuit fault diagnosis method based on grey prediction theory | |
| CN111624433A (en) | State evaluation method and system for pure electric vehicle and computer readable storage medium | |
| Strangas et al. | Improving the reliability of electrical drives through failure prognosis | |
| CN114070146A (en) | Fault detection method, device, equipment and storage medium | |
| EP3712430A1 (en) | Detecting wind turbine performance change | |
| CN114720870A (en) | Multi-phase motor winding fault diagnosis method based on phase current integral processing | |
| Shen et al. | A data based diagnostic method for current sensor fault in permanent magnet synchronous motors (pmsm) | |
| JP2017070127A (en) | Motor control device | |
| RU2381605C1 (en) | Method to detect power system asynchronous conditions | |
| CN114636880A (en) | Driver power tube fault diagnosis method based on motor phase-to-phase voltage signal processing | |
| Kilic | Predictive diagnosis with artificial neural network for automated electric vehicle | |
| EP4311934A1 (en) | Computer-implemented method for optimizing the operation of a drivetrain of a wind turbine | |
| EP4273557A1 (en) | Wind turbine rotor speed estimation | |
| Hamoudi et al. | Stator fault detection in induction machines by parameter estimation using trust region algorithms | |
| Svensson et al. | Unsupervised deviation detection by GMM—a simulation study |
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 |