CN113033605A - Motor fault judgment method and device, terminal equipment and computer storage medium - Google Patents
Motor fault judgment method and device, terminal equipment and computer storage medium Download PDFInfo
- Publication number
- CN113033605A CN113033605A CN202110180726.8A CN202110180726A CN113033605A CN 113033605 A CN113033605 A CN 113033605A CN 202110180726 A CN202110180726 A CN 202110180726A CN 113033605 A CN113033605 A CN 113033605A
- Authority
- CN
- China
- Prior art keywords
- motor
- model
- state data
- motors
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000012549 training Methods 0.000 claims abstract description 115
- 238000004364 calculation method Methods 0.000 claims abstract description 83
- 238000010801 machine learning Methods 0.000 claims abstract description 44
- 238000012360 testing method Methods 0.000 claims description 107
- 238000012821 model calculation Methods 0.000 claims description 32
- 230000015654 memory Effects 0.000 claims description 25
- 230000007613 environmental effect Effects 0.000 claims description 19
- 238000003745 diagnosis Methods 0.000 claims description 14
- 238000013473 artificial intelligence Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 10
- 238000013145 classification model Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000012935 Averaging Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- 208000033748 Device issues Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Control Of Electric Motors In General (AREA)
Abstract
The invention relates to the technical field of motors and artificial intelligence, and provides a motor fault judgment method, a motor fault judgment device, terminal equipment and a computer readable storage medium, wherein the method comprises the following steps: the method comprises the steps of obtaining real-time state data of a motor to be detected, and inputting the real-time state data into a preset motor fault judgment model, wherein the motor fault judgment model is obtained by carrying out federal learning training based on sample state data of a plurality of motors; receiving a calculation result output by the motor fault judgment model after training calculation based on the real-time state data; and determining whether the motor to be detected fails according to the calculation result. In addition, the invention also relates to a block chain technology, and the motor fault judgment model can be stored in the block chain. According to the motor fault identification method and device, the federal machine learning training can be carried out on the basis of the state data of the collected samples of the motors to obtain the model for carrying out motor fault identification and judgment, the operation of fault judgment on the motors is simplified, and the accuracy of fault judgment is improved.
Description
Technical Field
The invention relates to the technical field of motors and artificial intelligence, in particular to a motor fault judgment method and device, terminal equipment and a computer readable storage medium.
Background
Artificial Intelligence (AI) is a theory, method and technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.
The existing fault identification and judgment for motors is to perform state detection of various dimensions on the motor to be detected in real time, perform complex professional calculation for a large amount of state data after the large amount of state data of the motor to be detected is obtained through detection, and further output a fault judgment result. Therefore, complex calculation is required when the judgment is carried out every time, and the running state of the motor is inevitably influenced by external noise, so that even if time is consumed for carrying out complicated calculation, the finally obtained judgment result still cannot ensure the accuracy.
Disclosure of Invention
The embodiment of the invention provides a motor fault judgment method, a motor fault judgment device, terminal equipment and a computer readable storage medium, and aims to realize fault identification and judgment of a motor based on machine learning, achieve the purposes of simplifying calculation operation and improving judgment accuracy and improve the efficiency of motor fault judgment.
In order to achieve the above technical object, an embodiment of the present invention provides a method for determining a fault of a motor, where the method for determining a fault of a motor is applied to a terminal device connected to a plurality of motors, and the method for determining a fault of a motor includes:
the method comprises the steps of obtaining real-time state data of a motor to be detected, and inputting the real-time state data into a preset motor fault judgment model, wherein the motor fault judgment model is obtained by carrying out federal learning training based on sample state data of a plurality of motors;
receiving a calculation result output by the motor fault judgment model after training calculation based on the real-time state data;
and determining whether the motor to be detected fails according to the calculation result.
Further, in the foregoing solution, the method for determining a fault of a motor further includes:
and controlling the plurality of motors to carry out federal learning training based on respective sample state data to obtain a motor fault judgment model.
Further, in the foregoing solution, the step of controlling the plurality of motors to perform federal learning training based on respective sample state data to obtain a motor fault determination model includes:
controlling the motors to locally acquire sample state data and performing machine learning training of a local model based on the sample state data;
receiving model parameters of respective local models uploaded by the motors, and integrating the model parameters to generate a model to be confirmed;
distributing the model to be confirmed to the motors for testing and receiving test results returned by the motors respectively;
and determining the model to be confirmed as a motor fault judgment model according to the test result.
Further, in the above scheme, the step of determining that the model to be confirmed is the motor fault determination model according to the test result includes:
if the received test result is that the model calculation is accurate, determining that the model to be confirmed is the motor fault judgment model;
if the received test result is that the model calculation is inaccurate, controlling a corresponding motor to train the model to be confirmed again locally based on the sample state data and uploading new model parameters;
integrating the new model parameters to generate a new model to be confirmed and testing the new model to be confirmed to obtain a new test result;
and if the new test result is that the model calculation is accurate, determining the new model to be confirmed as the motor fault judgment model.
Further, in the foregoing solution, the step of controlling each of the plurality of motors to locally acquire sample state data and perform machine learning training of a local model based on the sample state data includes:
distributing model training instructions to the motors so that the motors can locally acquire the motor real-time operation parameters and the environmental noise data according to the model training instructions and locally perform machine learning training on local models based on the motor real-time operation parameters and the environmental noise data.
Further, in the foregoing solution, the step of storing the motor fault determination model in a block chain, and inputting the real-time status data into a preset motor fault determination model includes:
and extracting the motor fault judgment model from the block chain, and inputting the real-time state data into the motor fault judgment model.
In addition, to achieve the above technical object, an embodiment of the present invention further provides another method for determining a fault of a motor, where the method for determining a fault of a motor is applied to the motor itself, and the method for determining a fault of a motor includes:
carrying out federal learning training with other motors based on local sample state data to obtain a motor fault judgment model;
acquiring real-time state data of a motor, and inputting the real-time state data into the motor fault judgment model;
receiving a calculation result output by the motor fault judgment model after training calculation based on the real-time state data;
and determining whether the motor to be detected fails according to the calculation result.
In addition, to achieve the above technical object, an embodiment of the present invention further provides a failure determination device for a motor, where the failure determination device for a motor is applied to a terminal device connected to a plurality of motors, and the failure determination device for a motor includes:
the motor fault diagnosis system comprises an acquisition module, a fault diagnosis module and a fault diagnosis module, wherein the acquisition module is used for acquiring real-time state data of a motor to be detected and inputting the real-time state data into a preset motor fault diagnosis model, and the motor fault diagnosis model is obtained by carrying out federal learning training based on sample state data of a plurality of motors;
the receiving module is used for receiving a calculation result output after the motor fault judgment model carries out training calculation based on the real-time state data;
the determining module is used for determining whether the motor to be detected fails according to the calculation result;
wherein, the fault diagnosis device of motor still is applied to motor itself, the fault diagnosis device of motor still includes:
and the model training module is used for carrying out federal learning training with other motors based on local sample state data to obtain a motor fault judgment model.
In addition, to achieve the above technical object, an embodiment of the present invention provides a terminal device, where the terminal device includes:
a memory for storing executable instructions;
and the processor is used for realizing the fault judgment method of the motor provided by the embodiment of the invention when the executable instruction stored in the memory is executed.
In addition, to achieve the above technical object, an embodiment of the present invention further provides a computer-readable storage medium, where executable instructions are stored, and the executable instructions are used for causing a processor to execute the method for determining a fault of a motor according to the embodiment of the present invention.
The embodiment of the invention provides a computer program product, which comprises a computer program, wherein when the computer program is executed by a processor, the fault judgment method of the motor provided by the embodiment of the invention is realized.
The embodiment of the invention has the following beneficial technical effects:
according to the motor fault judgment method, the motor fault judgment device, the terminal equipment and the computer readable storage medium, real-time state data of a motor to be detected are obtained and input into a preset motor fault judgment model, wherein the motor fault judgment model is obtained by carrying out federal learning training based on sample state data of a plurality of motors; receiving a calculation result output by the motor fault judgment model after training calculation based on the real-time state data; and determining whether the motor to be detected fails according to the calculation result.
Compared with the mode that the state of various dimensions of a motor to be detected is detected in real time to obtain a large amount of state data and then complex calculation is carried out on the large amount of state data to obtain a fault judgment result in the related technology, the embodiment of the invention carries out federal learning training on the basis of the sample state data of a plurality of motors to obtain a motor fault judgment model, then directly obtains the real-time state data of the motor to be detected when fault judgment is carried out on the motor to be detected, inputs the real-time state data into the motor fault judgment model, thus the motor fault judgment model trains and calculates the real-time state data to output a calculation result, and finally determines whether the motor to be detected has a fault or not on the basis of the calculation result.
The motor fault identification method and the motor fault identification system realize that the motor fault identification and judgment are carried out by carrying out federal machine learning training on the basis of the state data of the collected samples of the motors to obtain the model, so that complex professional calculation is not required to be carried out on a large amount of real-time state data of the motors, the operation of fault judgment on the motors is simplified, the fault judgment accuracy is effectively improved, and the motor fault judgment efficiency is greatly improved.
Drawings
Fig. 1 is a schematic view of an implementation scenario of a method for determining a fault of a motor according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a terminal device according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a method for determining a fault of a motor according to an embodiment of the present invention;
fig. 4 is another schematic flow chart of a method for determining a fault of a motor according to an embodiment of the present invention;
fig. 5 is a schematic view of another implementation scenario of the method for determining a fault of a motor according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in some embodiments with reference to the attached drawings, the described embodiments should not be construed as limiting the present invention, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
In the following description, if the term "first \ second \ third" is referred to, the "first \ second \ third" merely distinguishes similar objects and does not represent a specific ordering for the objects, it is to be understood that "first \ second \ third" may be interchanged under certain circumstances or in a sequence order so that embodiments of the present invention described herein may be performed in an order other than that shown or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to be limiting of the invention.
Before further detailed description of the embodiments of the present invention, terms and expressions mentioned in the embodiments of the present invention are explained, and the terms and expressions mentioned in the embodiments of the present invention are applied to the following explanations.
1) And (3) federal learning training, namely, combining respective sample data of a plurality of examples (namely motors in the scheme) to perform machine learning together so as to complete the training and optimization of the model under the multi-party cooperative condition.
Based on the above explanations of terms and terms involved in the embodiments of the present invention, an implementation scenario of the training method of the classification model provided in the embodiments of the present invention is described below, referring to fig. 1, fig. 1 is a schematic diagram of an implementation scenario of the method for determining a fault of a motor provided in the embodiments of the present invention, and in order to support an exemplary application, a terminal device 200-1 connects a plurality of motors, that is, a motor 200-1 to a motor 200-n (n is a positive integer greater than 1) through a network 300.
The terminal device (including the terminal device 200-1) is used for receiving real-time state data uploaded by each of a plurality of motors (including the motor 200-1 and/or the motor 200-2.. the motor 200-n), inputting the real-time state data into a motor fault judgment model, receiving a calculation result output by the motor fault judgment model, and judging whether the motor corresponding to the real-time state data has a fault according to the calculation result;
the motor (including the motor 200-1 and/or the motor 200-2.. the motor 200-n) is used for uploading respective real-time state data and receiving a motor fault judgment result fed back by the terminal equipment (including the terminal equipment 200-1).
In practical application, the terminal device 200-1 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, middleware service, a domain name service, a security service, a CDN, and a big data and artificial intelligence platform. The terminal device 200-1 may also be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, etc. The terminal device 200-1 and the motor 200-2 may be directly or indirectly connected through wired or wireless communication, and the present invention is not limited thereto.
The following describes in detail a hardware structure of a terminal device implementing the method for determining a fault of a motor according to an embodiment of the present invention, where the terminal device includes, but is not limited to, a server or a terminal. Referring to fig. 2, fig. 2 is a schematic structural diagram of a terminal device according to an embodiment of the present invention, and the terminal device 200 shown in fig. 2 includes: at least one processor 210, memory 250, at least one network interface 220, and a user interface 230. The various components in terminal device 200 are coupled together by a bus system 240. It will be appreciated that the bus system 240 is used to enable communications among the components of the connection. The bus system 240 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 240 in fig. 2.
The Processor 210 may be an integrated circuit chip having Signal processing capabilities, such as a general purpose Processor, a Digital Signal Processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like, wherein the general purpose Processor may be a microprocessor or any conventional Processor, or the like.
The user interface 230 includes one or more output devices 231, including one or more speakers and/or one or more visual display screens, that enable the presentation of media content. The user interface 230 also includes one or more input devices 232, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.
The memory 250 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid state memory, hard disk drives, optical disk drives, and the like. Memory 250 optionally includes one or more storage devices physically located remotely from processor 210.
The memory 250 includes volatile memory or nonvolatile memory, and may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read Only Memory (ROM), and the volatile Memory may be a Random Access Memory (RAM). The memory 250 described in embodiments of the invention is intended to comprise any suitable type of memory.
In some embodiments, memory 250 is capable of storing data, examples of which include programs, modules, and data structures, or a subset or superset thereof, to support various operations, as exemplified below.
An operating system 251 including system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;
a network communication module 252 for communicating to other computing devices via one or more (wired or wireless) network interfaces 220, exemplary network interfaces 220 including: bluetooth, wireless compatibility authentication (WiFi), and Universal Serial Bus (USB), etc.;
an input processing module 253 for detecting one or more user inputs or interactions from one of the one or more input devices 232 and translating the detected inputs or interactions.
In some embodiments, the failure determination device for a motor provided by the embodiments of the present invention may be implemented in software, and fig. 2 shows the failure determination device 254 for a motor, which may be software in the form of programs and plug-ins, stored in the memory 250, and includes the following software modules:
the acquisition module 2541 is used for acquiring real-time state data of a motor to be detected and inputting the real-time state data into a preset motor fault judgment model, wherein the motor fault judgment model is obtained by carrying out federal learning training based on sample state data of a plurality of motors;
a receiving module 2542, configured to receive a calculation result output after the motor fault determination model performs training calculation based on the real-time state data;
and the determining module 2543 is configured to determine whether the motor to be detected fails according to the calculation result.
Optionally, the failure determination device 254 for a motor further includes:
and the model training module 2544 is used for controlling the plurality of motors to perform federal learning training based on respective sample state data to obtain a motor fault judgment model.
Optionally, model training module 2544, comprising:
the control unit is used for controlling the motors to respectively collect sample state data locally and carry out machine learning training of a local model based on the sample state data;
the model generation unit is used for receiving model parameters of respective local models uploaded by the motors and integrating the model parameters to generate a model to be confirmed;
the test unit is used for distributing the model to be confirmed to the motors to be tested and receiving test results returned by the motors respectively;
and the determining unit is used for determining the model to be confirmed as the motor fault judgment model according to the test result.
Optionally, the test result includes model calculation accuracy and model calculation inaccuracy, and the determining unit includes:
the first determining subunit is configured to determine that the model to be confirmed is the motor fault determination model if the received test result indicates that the model calculation is accurate;
the control subunit is used for controlling the corresponding motor to retrain the model to be confirmed locally based on the sample state data and upload new model parameters if the received test result indicates that the model is inaccurate in calculation;
the model generation subunit is used for integrating the new model parameters to generate a new model to be confirmed and testing the new model to be confirmed to obtain a new test result;
and the second determining subunit is used for determining the new model to be determined as the motor fault judgment model if the new test result indicates that the model calculation is accurate.
Optionally, the sample state data includes motor real-time operation parameters and environmental noise data, and the control unit is further configured to distribute model training instructions to the motors, so that the motors locally acquire the motor real-time operation parameters and the environmental noise data according to the model training instructions, and locally perform machine learning training on a local model based on the motor real-time operation parameters and the environmental noise data.
Optionally, the motor fault determination model is stored in a block chain, and the obtaining module 2541 is further configured to extract the motor fault determination model from the block chain, and input the real-time state data into the motor fault determination model.
In other possible embodiments, the motor failure determination device 254 stored in the memory 250 may be applied to the motor itself, and when the motor failure determination device 254 is applied to the motor itself,
a model training module 2544, configured to perform federal learning training with multiple other motors based on local sample state data to obtain a motor fault determination model
An obtaining module 2541, configured to obtain real-time state data of a motor, and input the real-time state data into the motor fault determination model;
a receiving module 2542, configured to receive a calculation result output after the motor fault determination model performs training calculation based on the real-time state data;
and the determining module 2543 is configured to determine whether the motor to be detected fails according to the calculation result.
The above modules are logical, and thus may be arbitrarily combined or further divided according to the implemented functions, and the functions of the respective modules will be described below.
In other embodiments, the failure determination Device of the motor provided in the embodiments of the present invention may be implemented by a combination of hardware and software, and as an example, the failure determination Device of the motor provided in the embodiments of the present invention may be a processor in the form of a hardware decoding processor, which is programmed to execute the failure determination method of the motor provided in the embodiments of the present invention, for example, the processor in the form of the hardware decoding processor may be one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field Programmable Gate Arrays (FPGAs), or other electronic components.
Based on the above description of the implementation scenario of the motor fault determination method and the electronic device according to the embodiments of the present invention, the following description describes the motor fault determination method according to the embodiments of the present invention. Referring to fig. 3, fig. 3 is a schematic flow chart of a method for determining a fault of a motor according to an embodiment of the present invention, where the method for determining a fault of a motor according to an embodiment of the present invention is applied to a terminal device connected to a plurality of motors in a wired or wireless manner, and the method for determining a fault of a motor includes:
step 301: the method comprises the steps of obtaining real-time state data of a motor to be detected, inputting the real-time state data into a preset motor fault judgment model, wherein the motor fault judgment model is obtained by carrying out federal learning training based on sample state data of a plurality of motors.
The terminal equipment continuously monitors the real-time state data of the motor to be detected in the whole operation process of the connected motor to be detected, directly acquires the real-time state data of the motor to be detected when fault judgment is needed to be carried out on the motor to be detected, and inputs the real-time state data into a motor fault judgment model obtained by carrying out federal machine learning training in advance.
In this embodiment, the motor failure determination model is obtained by performing federal machine learning training on a plurality of motors connected to the terminal device under control in advance based on local sample state data of the motors.
Specifically, in the actual implementation of this embodiment, the terminal device establishes communication connection with various sensors installed on the motor to be detected, and the sensors are used for detecting the operating state of the motor, so that in the whole process of starting and operating the motor to be detected, real-time state data of the motor to be detected, which are detected by the various sensors in real time, are continuously monitored, and then the terminal device obtains the real-time state data of the motor to be detected, which are detected by the various sensors, to the local area by receiving an instruction for performing fault judgment on the motor to be detected, and then the terminal device can directly input the real-time state data into a motor fault judgment model which is trained in advance.
Further, in some possible embodiments, the method for determining a fault of a motor according to an embodiment of the present invention may further include:
step A: and controlling the plurality of motors to carry out federal learning training based on respective sample state data to obtain a motor fault judgment model.
The method comprises the steps that before terminal equipment obtains real-time state data of a motor to be detected and inputs the real-time state data into a motor fault judgment model, a plurality of connected motors are controlled to serve as a federation to conduct federated learning training based on respective sample state data of the plurality of motors, and therefore the motor fault judgment model capable of conducting fault judgment on the motor to be detected is obtained.
Further, in a possible embodiment, step a may include:
step A1: controlling the motors to locally acquire sample state data and performing machine learning training of a local model based on the sample state data;
in the process of controlling the connected motors to carry out the federal learning training, the terminal equipment firstly controls the motors to respectively collect sample state data locally, and then utilizes the sample state data to carry out the machine learning training on the local model locally until the local model converges, or the number of times of carrying out the machine learning training on the local model reaches the maximum iteration number.
It should be noted that, in this embodiment, the sample state data may specifically be real-time operating parameters such as motor rotation speed, current, voltage, and vibration amplitude, which are monitored in real time by various sensors locally and collected in real time by each motor, and environmental noise data, or, the sample state data may also be real-time operating parameters such as motor speed, current, voltage, and vibration amplitude, manually entered by the operator, as well as ambient noise data, it being understood that, depending on the design needs of the actual application, in different possible embodiments, each motor may, of course, locally collect various real-time operation parameters and environmental noise data of the environment as sample state data, and the method for determining a fault of a motor according to the embodiment of the present invention is not limited to a specific type of the sample state data.
In addition, in this embodiment, the local model may specifically be any machine learning model such as a neural network model, a convolutional neural network model, a binary model, or a multi-class model, and it should be understood that, based on different design requirements of practical applications, in different feasible embodiments, each motor may perform machine learning training on a certain model in any machine learning model locally and jointly, and the fault determination method for a motor provided in the embodiment of the present invention is also not limited to a specific type of the local model.
Further, in a possible embodiment, the sample state data includes real-time motor operating parameters and ambient noise data, and the step a1 may include:
step A101: distributing model training instructions to the motors so that the motors can locally acquire the motor real-time operation parameters and the environmental noise data according to the model training instructions and locally perform machine learning training on local models based on the motor real-time operation parameters and the environmental noise data.
After the connected motors are combined into the federation, the terminal equipment uniformly distributes model training instructions to the motors, the motors start to collect motor real-time operation parameters and environmental noise data monitored by various sensors locally after receiving the model training instructions, and then the motors perform machine learning training aiming at the same type of machine learning model locally based on the motor real-time operation parameters and the environmental noise data.
Specifically, in practical implementation, the terminal device selects one binary model in advance as a local model for each motor to perform machine learning training locally, then packages the binary model into a model training instruction for controlling each motor to perform machine learning training locally, and distributes the model training instruction to each motor, so that each motor, after receiving the model training instruction, respectively collects real-time motor operating parameters (such as motor rotation speed, current, voltage and/or vibration amplitude) monitored by a respective preset sensor in real time, and collects environmental noise data of respective environment, and locally performs iterative training on two classification models issued together with the model training instruction based on the respective collected real-time motor operating parameters and environmental noise data until the binary model converges, or until the number of times of iterative training of the two-classification model reaches the set maximum iteration number.
Step A2: receiving model parameters of respective local models uploaded by the motors, and integrating the model parameters to generate a model to be confirmed;
the terminal equipment combines a plurality of connected motors into a federation, uniformly distributes model training instructions to the motors so that the motors collect sample state data locally according to the model training instructions to perform machine learning training aiming at a machine learning model of the same type, receives model parameters of the machine learning model after the plurality of motors converge the machine learning model training or the training times reach the maximum iteration times, and integrates the model parameters uploaded by the motors to generate a complete machine learning model as a model to be confirmed.
In particular, in practical implementation, each motor locally performs iterative training on a binary model based on the collected real-time motor operating parameters and environmental noise data until the binary model converges, or, after the iterative training times of the binary model reach the set maximum iterative times, each motor respectively packages and uploads model parameters of categories such as intermediate gradient, coefficient, weight and the like of the two-category model to the terminal equipment, the terminal equipment classifies the model parameters after receiving the model parameters uploaded by each motor, and the model parameters of the same category are weighted and averaged to obtain the unique model parameters of the category, and finally, and the terminal equipment integrates the model parameters of different classes after weighted averaging into a new two-classification model serving as the model to be confirmed.
Step A3: distributing the model to be confirmed to the motors for testing and receiving test results returned by the motors respectively;
after integrating the model parameters uploaded by the motors respectively to generate a model to be confirmed, the terminal equipment distributes the model to be confirmed to the motors again to enable the motors to test the model to be confirmed locally respectively, and feeds back test results of the model to be confirmed respectively after the test is finished.
It should be noted that, in this embodiment, when the multiple motors are each tested locally for the model to be confirmed, the multiple motors may use locally collected test sample data specially used for testing, where the test sample data may specifically be locally collected real-time motor operating parameters and environmental noise data when each motor is determined to have a fault, or the test sample data may also be motor operating parameters and environmental noise data that are manually input by a worker and that indicate whether the motor has a fault.
Specifically, in the embodiment, during actual implementation, the terminal device classifies and weights model parameters of two classification models uploaded by each motor, integrates model parameters of different classes after weighted averaging to obtain a model to be confirmed, packages the model to be confirmed again into a model test instruction, distributes the model test instruction to each motor to enable each motor to extract the model to be confirmed in the model test instruction, obtains test sample data, inputs the test sample data into the model to be confirmed to perform model training calculation, generates corresponding test results according to calculation results output by the model to be confirmed, and feeds the test results back to the terminal device respectively.
It should be noted that, in this embodiment, when each motor is tested locally with the test sample data for the model to be confirmed, if the motor currently inputs test sample data identifying the motor as faulty into the model to be validated, and the model to be confirmed performs model training calculation on the test sample data to output a calculation result that the motor is in fault, the motor then generates a test result with accurate model calculation and feeds the test result back to the terminal equipment, or the motor inputs test sample data for identifying the motor fault into the model to be confirmed currently, but the model to be confirmed carries out model training calculation on the test sample data and outputs a calculation result that the motor has no fault, the motor then generates a test result with inaccurate model calculation and feeds the test result back to the terminal equipment.
Step A4: and determining the model to be confirmed as a motor fault judgment model according to the test result.
After receiving the test results respectively uploaded by the motors, the terminal equipment directly determines the model to be confirmed as a motor fault judgment model capable of accurately judging whether the motor to be detected has a fault or not based on the test results, or controls the motor to perform local machine learning training for the model to be confirmed again based on the test results, and then regenerates a new model to be confirmed for testing, so that the new model to be confirmed is determined as the motor fault judgment model based on the test results.
Further, in a possible embodiment, the test result includes model calculation accuracy and model calculation inaccuracy, and step a4 may include:
step A401: if the received test result is that the model calculation is accurate, determining that the model to be confirmed is the motor fault judgment model;
after the terminal equipment receives the test results respectively uploaded by the motors, if the test results are model calculation accuracy, the terminal equipment directly determines the model to be confirmed as a motor fault judgment model capable of accurately judging whether the motor to be detected has a fault.
Specifically, referring to the application scenario shown in fig. 5, in actual implementation of this embodiment, if, in each motor, the motor 1 locally uses test sample data to test the model to be determined, and then generates a test result that is "model calculation accurate", so that after the motor 1 uploads the test result that is "model calculation accurate" to the terminal device, the terminal device can directly determine that the model to be determined, which is transferred to the motor 1 for testing, is the motor fault determination model that can accurately determine whether the motor to be detected has a fault.
Step A402: if the received test result is that the model calculation is inaccurate, controlling a corresponding motor to train the model to be confirmed again locally based on the sample state data and uploading new model parameters;
after the terminal equipment receives the test results respectively uploaded by the motors, if the test results are inaccurate in model calculation, the terminal equipment controls the motors which upload the test results again to conduct machine learning training on the model to be confirmed locally based on the sample state data again and uploads new model parameters.
Specifically, referring to the application scenario shown in fig. 5, in an actual implementation of this embodiment, if, in each motor, a test result generated after the motor 2 tests the model to be confirmed locally by using test sample data is "model calculation inaccurate", so that after the motor 2 uploads the test result of "model calculation inaccurate" to the terminal device, the terminal device immediately issues a new model training instruction to the motor 2 again, so that the motor 2 locally performs iterative training on the model to be confirmed again by using the pre-collected real-time motor operating parameters (such as motor rotation speed, current, voltage and/or vibration amplitude) and environmental noise data based on the new model training instruction until the model to be confirmed converges, or until the number of iterative training on the model to be confirmed reaches a set maximum number of iterations, and packaging and uploading new model parameters of the intermediate gradient, the coefficient, the weight and the like of the model to be confirmed to the terminal equipment.
Step A403: integrating the new model parameters to generate a new model to be confirmed and testing the new model to be confirmed to obtain a new test result;
after receiving the new model parameters, the terminal device integrates the new model parameters to generate a complete machine learning model as a new model to be confirmed, then the terminal device issues the new model to be confirmed to the corresponding motor again, and the motor tests the new model to be confirmed and feeds back a new test result.
Specifically, referring to the application scenario shown in fig. 5, in the actual implementation of this embodiment, after receiving new model parameters uploaded by the motor 2, the terminal device classifies the new model parameters, performs weighted averaging on the model parameters of the same class to obtain model parameters unique to the class, and finally integrates the model parameters of different classes after weighted averaging into a new model to be confirmed, and then the terminal device packages the new model to be confirmed again as a model test instruction and distributes the model test instruction to the motor 2 so that the motor 2 extracts the new model to be confirmed in the model test instruction, obtains test sample data, inputs the new model to be confirmed to perform model training calculation, and generates a corresponding new test result according to a calculation result output by the new model to be confirmed, namely, the model calculation is accurate or the model calculation is inaccurate, and the new test result is fed back to the terminal equipment.
It should be noted that, in this embodiment, the process of testing the motor 2 for the new model to be confirmed and generating the new test result is the same as the process of testing each motor for the model to be confirmed locally by using the test sample data and then generating the corresponding test result, and details are not repeated here.
Step A404: and if the new test result is that the model calculation is accurate, determining the new model to be confirmed as the motor fault judgment model.
After the terminal equipment receives a new test result uploaded by the motor again, if the new test result is that model calculation is accurate, the terminal equipment directly determines a new model to be confirmed as a motor fault judgment model capable of accurately judging whether the motor to be detected has a fault.
Specifically, referring to the application scenario shown in fig. 5, in actual implementation of this embodiment, if a new test result generated after the motor 2 locally utilizes the test sample data again to test a new model to be determined is "model calculation accurate", the motor 2 uploads the new test result of "model calculation accurate" to the terminal device, and then the terminal device can directly determine that the new model to be determined, which is transferred to the motor 2 for testing, is a motor fault determination model capable of accurately determining whether the motor to be detected has a fault.
Further, in another possible embodiment, if the new test result received again by the terminal device is still "model calculation inaccurate", the terminal device repeatedly executes the processes from step a401 to step a403 again until the new test result is "model calculation accurate" and determines the new model to be confirmed as the motor fault determination model.
Further, in some possible embodiments, the motor fault determination model is stored in a block chain, and the step of inputting the real-time status data into a preset motor fault determination model in step 301 may include:
step 3011: and extracting the motor fault judgment model from the block chain, and inputting the real-time state data into the motor fault judgment model.
After the terminal device performs federated learning training on a plurality of motors to obtain a motor fault judgment model, the terminal device can store the motor fault judgment model in block chain link points developed in advance, so that in the process of fault judgment on the motor to be detected, the terminal device extracts the motor fault judgment model from the block chain link points after acquiring real-time state data of the motor to be detected, and inputs the real-time state data into the motor fault judgment model.
It should be noted that, in this embodiment, in order to ensure that the terminal device performs federal learning training in combination with multiple motors to obtain that the motor fault determination model is not erroneously modified or removed, the motor fault determination model is selected to be stored in a node of a block chain, so that not only the stability of the motor fault determination model can be ensured, but also the response enthusiasm of subsequent terminal devices when extracting the motor fault determination model to perform motor fault determination and the accuracy of the read motor fault determination model can be ensured, and the overall efficiency of motor fault determination is further improved.
Step 302: and receiving a calculation result output by the motor fault judgment model after training calculation based on the real-time state data.
After the terminal equipment obtains the real-time state data of the motor to be detected and inputs the real-time state data into the motor fault judgment model, the motor fault judgment model carries out model training calculation on the real-time state data and outputs a calculation result, and the terminal equipment receives the calculation result and is used for determining whether the motor to be detected breaks down or not.
Step 303: and determining whether the motor to be detected fails according to the calculation result.
It should be noted that, in this embodiment, the calculation result includes a motor failure and a motor non-failure.
After the terminal equipment receives the calculation result output by the motor fault model, if the calculation result indicates that the motor is not in fault, the terminal equipment determines that the motor to be detected is not in fault, or if the calculation result indicates that the motor is in fault, the terminal equipment determines that the motor to be detected is in fault, and therefore a corresponding prompt message is output.
By applying the embodiment of the invention, before the real-time state data of the motor to be detected is acquired through the terminal equipment and is input into the motor fault judgment model, the connected motors are controlled to serve as the federal to carry out the federal learning training based on the respective sample state data of the motors, so that the motor fault judgment model capable of carrying out fault judgment on the motor to be detected is obtained; the terminal equipment continuously monitors the real-time state data of the motor to be detected in the whole operation process of the connected motor to be detected, directly acquires the real-time state data of the motor to be detected when fault judgment is needed to be carried out on the motor to be detected, and inputs the real-time state data into a motor fault judgment model obtained by carrying out federal machine learning training in advance. After the terminal equipment obtains the real-time state data of the motor to be detected and inputs the real-time state data into the motor fault judgment model, the motor fault judgment model carries out model training calculation on the real-time state data and outputs a calculation result, and the terminal equipment receives the calculation result and is used for determining whether the motor to be detected breaks down or not. After the terminal equipment receives the calculation result output by the motor fault model, if the calculation result indicates that the motor is not in fault, the terminal equipment determines that the motor to be detected is not in fault, or if the calculation result indicates that the motor is in fault, the terminal equipment determines that the motor to be detected is in fault, and therefore a corresponding prompt message is output.
The motor fault identification method and the motor fault identification system realize that the motor fault identification and judgment are carried out by carrying out federal machine learning training on the basis of the state data of the collected samples of the motors to obtain the model, so that complex professional calculation is not required to be carried out on a large amount of real-time state data of the motors, the operation of fault judgment on the motors is simplified, the fault judgment accuracy is effectively improved, and the motor fault judgment efficiency is greatly improved.
After describing the application of the motor fault determination method provided by the embodiment of the present invention to a terminal device connected to a plurality of motors, next, describing the application of the motor fault determination method provided by the embodiment of the present invention to any one electrode of the plurality of motors, referring to fig. 4, where fig. 4 is a schematic flow chart of the motor fault determination method provided by the embodiment of the present invention, and the motor fault determination method provided by the embodiment of the present invention is applied to any one motor of the plurality of motors connected to the terminal device in a wired or wireless manner, and the motor fault determination method provided by the embodiment of the present invention includes:
step 401: and carrying out federal learning training with other motors based on local sample state data to obtain a motor fault judgment model.
The motor locally acquires sample state data based on a model training instruction of the receiving terminal device, then uses the sample state data to perform machine learning training on a local model until the local model converges, or after the number of times of machine learning training aiming at the local model reaches the maximum iteration number, each model parameter of the local model is uploaded to the terminal equipment, so that the terminal equipment integrates the model parameters uploaded by the motors respectively to generate a complete machine learning model as a model to be confirmed, then, the motor receives the model to be confirmed issued by the terminal device, tests the model to be confirmed locally and feeds back a test result, and the terminal equipment determines the model to be confirmed as a motor fault judgment model capable of accurately judging whether the motor to be detected has a fault or not based on the test result.
It should be noted that, in this embodiment, for a detailed process of obtaining a motor fault determination model by performing federal learning training on a motor and a plurality of other motors based on local sample state data, reference may be made to the entire specific implementation manners of step a, step A1 (including step a101) to step A4 (including step a401 to step a404) in the foregoing embodiment, which are not described herein again.
Step 402: acquiring real-time state data of a motor, and inputting the real-time state data into the motor fault judgment model;
when the motor needs to perform fault judgment at the current moment, acquiring real-time state data of the current moment, and inputting the real-time state data into a motor fault judgment model obtained by performing federal machine learning training in advance.
It should be noted that, in this embodiment, for a detailed process of acquiring real-time status data by the motor and inputting the real-time status data into the motor fault determination model, reference may be made to the entire specific implementation manner of step 301 and step 3011 in the foregoing embodiment, and details are not described here again.
Step S403: receiving a calculation result output by the motor fault judgment model after training calculation based on the real-time state data;
after the motor obtains the real-time state data and inputs the real-time state data into the motor fault judgment model, the motor fault judgment model performs model training calculation on the real-time state data and outputs a calculation result, and the motor receives the calculation result to determine whether a fault occurs at the current moment.
Step S404: and determining whether the motor to be detected fails according to the calculation result.
It should be noted that, in the present embodiment, the calculation result includes a motor failure and a motor failure.
After the motor receives a calculation result output by the motor fault model, if the calculation result indicates that the motor is not in fault, the terminal equipment determines that no fault occurs at the current moment, or if the calculation result indicates that the motor is in fault, the terminal equipment determines that the current moment is in fault and outputs a corresponding prompt message.
By applying the above embodiment of the invention, based on the model training instruction of the receiving terminal device, sample state data is collected locally, and then utilized after machine learning training is performed on a local model until the local model converges, or after the number of times of machine learning training aiming at the local model reaches the maximum iteration number, each model parameter of the local model is uploaded to the terminal equipment, so that the terminal equipment integrates the model parameters uploaded by the motors respectively to generate a complete machine learning model as a model to be confirmed, then, the motor receives the model to be confirmed issued by the terminal device, tests the model to be confirmed locally and feeds back a test result, and the terminal equipment determines the model to be confirmed as a motor fault judgment model capable of accurately judging whether the motor to be detected has a fault or not based on the test result. When the motor needs to perform fault judgment at the current moment, acquiring real-time state data of the current moment, and inputting the real-time state data into a motor fault judgment model obtained by performing federal machine learning training in advance. The motor fault judgment model carries out model training calculation aiming at the real-time state data and outputs a calculation result, the motor receives the calculation result and is used for determining whether the current time is faulted, namely, after the motor receives the calculation result output by the motor fault model, if the calculation result indicates that the motor is faultless, the terminal equipment determines that the current time is faulted, or if the calculation result indicates that the motor is faulted, the terminal equipment determines that the current time is faulted so as to output a corresponding prompt message.
The motor fault identification method and the motor fault identification system realize that the motor fault identification and judgment are carried out by carrying out federal machine learning training on the basis of the state data of the collected samples of the motors to obtain the model, so that complex professional calculation is not required to be carried out on a large amount of real-time state data of the motors, the operation of fault judgment on the motors is simplified, the fault judgment accuracy is effectively improved, and the motor fault judgment efficiency is greatly improved.
An embodiment of the present invention further provides a terminal device, where the terminal device includes:
a memory for storing executable instructions;
and the processor is used for realizing the application method of the multi-classification model provided by the embodiment of the invention when the processor executes the executable instructions stored in the memory.
Embodiments of the present invention also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instruction from the computer readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method for judging the fault of the motor provided by the embodiment of the invention.
The embodiment of the invention also provides a computer-readable storage medium, which stores executable instructions, and when the executable instructions are executed by a processor, the application method of the multi-classification model provided by the embodiment of the invention is realized.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories. The computer may be a variety of computing devices including intelligent terminals and servers.
In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
The above description is only an example of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and scope of the present invention are included in the protection scope of the present invention.
Claims (10)
1. A fault judgment method of a motor is applied to a terminal device connected with a plurality of motors, and comprises the following steps:
the method comprises the steps of obtaining real-time state data of a motor to be detected, and inputting the real-time state data into a preset motor fault judgment model, wherein the motor fault judgment model is obtained by carrying out federal learning training based on sample state data of a plurality of motors;
receiving a calculation result output by the motor fault judgment model after training calculation based on the real-time state data;
and determining whether the motor to be detected fails according to the calculation result.
2. The method of determining a failure of an electric motor according to claim 1, further comprising:
and controlling the plurality of motors to carry out federal learning training based on respective sample state data to obtain a motor fault judgment model.
3. The method according to claim 2, wherein the step of controlling the plurality of motors to perform federal learning training based on respective sample state data to obtain a motor failure determination model includes:
controlling the motors to locally acquire sample state data and performing machine learning training of a local model based on the sample state data;
receiving model parameters of respective local models uploaded by the motors, and integrating the model parameters to generate a model to be confirmed;
distributing the model to be confirmed to the motors for testing and receiving test results returned by the motors respectively;
and determining the model to be confirmed as a motor fault judgment model according to the test result.
4. The method according to claim 3, wherein the test result includes model calculation accuracy and model calculation inaccuracy, and the step of determining the model to be confirmed as the motor fault determination model according to the test result includes:
if the received test result is that the model calculation is accurate, determining that the model to be confirmed is the motor fault judgment model;
if the received test result is that the model calculation is inaccurate, controlling a corresponding motor to train the model to be confirmed again locally based on the sample state data and uploading new model parameters;
integrating the new model parameters to generate a new model to be confirmed and testing the new model to be confirmed to obtain a new test result;
and if the new test result is that the model calculation is accurate, determining the new model to be confirmed as the motor fault judgment model.
5. The method of claim 1, wherein the sample state data includes motor real-time operating parameters and ambient noise data, and wherein the step of controlling each of the plurality of motors to locally collect sample state data and perform machine learning training of a local model based on the sample state data comprises:
distributing model training instructions to the motors so that the motors can locally acquire the motor real-time operation parameters and the environmental noise data according to the model training instructions and locally perform machine learning training on local models based on the motor real-time operation parameters and the environmental noise data.
6. The method for determining a fault of an electric motor according to any one of claims 1 to 5, wherein the motor fault determination model is stored in a block chain, and the step of inputting the real-time status data into a preset motor fault determination model includes:
and extracting the motor fault judgment model from the block chain, and inputting the real-time state data into the motor fault judgment model.
7. A fault judgment method of a motor is applied to the motor, and is characterized by comprising the following steps:
carrying out federal learning training with other motors based on local sample state data to obtain a motor fault judgment model;
acquiring real-time state data of a motor, and inputting the real-time state data into the motor fault judgment model;
receiving a calculation result output by the motor fault judgment model after training calculation based on the real-time state data;
and determining whether the motor to be detected fails according to the calculation result.
8. A failure determination device for a motor, wherein the failure determination device for a motor is applied to a terminal device connected to a plurality of motors, and the failure determination device for a motor comprises:
the motor fault diagnosis system comprises an acquisition module, a fault diagnosis module and a fault diagnosis module, wherein the acquisition module is used for acquiring real-time state data of a motor to be detected and inputting the real-time state data into a preset motor fault diagnosis model, and the motor fault diagnosis model is obtained by carrying out federal learning training based on sample state data of a plurality of motors;
the receiving module is used for receiving a calculation result output after the motor fault judgment model carries out training calculation based on the real-time state data;
the determining module is used for determining whether the motor to be detected fails according to the calculation result;
wherein, the fault diagnosis device of motor still is applied to motor itself, the fault diagnosis device of motor still includes:
and the model training module is used for carrying out federal learning training with other motors based on local sample state data to obtain a motor fault judgment model.
9. A terminal device, characterized in that the terminal device comprises:
a memory for storing executable instructions;
a processor for implementing the method of determining a fault in an electrical machine of any one of claims 1 to 6 or claim 7 when executing executable instructions stored in the memory.
10. A computer-readable storage medium storing executable instructions for implementing the method of determining a fault in an electric machine according to any one of claims 1 to 6 or claim 7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110180726.8A CN113033605A (en) | 2021-02-08 | 2021-02-08 | Motor fault judgment method and device, terminal equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110180726.8A CN113033605A (en) | 2021-02-08 | 2021-02-08 | Motor fault judgment method and device, terminal equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113033605A true CN113033605A (en) | 2021-06-25 |
Family
ID=76461268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110180726.8A Pending CN113033605A (en) | 2021-02-08 | 2021-02-08 | Motor fault judgment method and device, terminal equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033605A (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160132566A1 (en) * | 2014-11-10 | 2016-05-12 | Red Hat, Inc. | Native federation view suggestion |
| US20190050515A1 (en) * | 2018-06-27 | 2019-02-14 | Intel Corporation | Analog functional safety with anomaly detection |
| CN109872040A (en) * | 2019-01-17 | 2019-06-11 | 南京航空航天大学 | A kind of two part relation probability of malfunction methods of risk assessment of aero-engine |
| CN110568360A (en) * | 2019-09-12 | 2019-12-13 | 华中科技大学 | lithium battery aging diagnosis method based on fuzzy logic algorithm |
| WO2020051193A1 (en) * | 2018-09-05 | 2020-03-12 | Translational Imaging Innovations Llc | Methods, systems and computer program products for retrospective data mining |
| CN110929290A (en) * | 2019-12-04 | 2020-03-27 | 南京如般量子科技有限公司 | Private key threshold backup, loss reporting and recovery system and method based on alliance chain |
| CN111143308A (en) * | 2019-12-26 | 2020-05-12 | 许昌中科森尼瑞技术有限公司 | Federal learning-based high-low voltage motor data processing method, system and device |
| CN111537945A (en) * | 2020-06-28 | 2020-08-14 | 南方电网科学研究院有限责任公司 | Intelligent ammeter fault diagnosis method and equipment based on federal learning |
| CN111557012A (en) * | 2018-12-03 | 2020-08-18 | 戴斯数字有限责任公司 | Cross-sensor predictive inference |
| EP3699825A2 (en) * | 2019-02-22 | 2020-08-26 | Ubotica Technologies Ltd. | Systems and methods for deploying and updating neural networks at the edge of a network |
| CN111722043A (en) * | 2020-06-29 | 2020-09-29 | 南方电网科学研究院有限责任公司 | Power equipment fault detection method, device and system |
| CN111881447A (en) * | 2020-06-28 | 2020-11-03 | 中国人民解放军战略支援部队信息工程大学 | Intelligent evidence obtaining method and system for malicious code fragments |
| CN112101489A (en) * | 2020-11-18 | 2020-12-18 | 天津开发区精诺瀚海数据科技有限公司 | Equipment fault diagnosis method driven by united learning and deep learning fusion |
| CN112183764A (en) * | 2020-10-12 | 2021-01-05 | 中国石油大学(华东) | Internet of things equipment fault detection method based on block chain and federal learning |
| US20210012225A1 (en) * | 2019-08-29 | 2021-01-14 | S20.ai, Inc. | Machine learning based ranking of private distributed data, models and compute resources |
| CN112288573A (en) * | 2020-12-25 | 2021-01-29 | 支付宝(杭州)信息技术有限公司 | Method, device and equipment for constructing risk assessment model |
| CN112668128A (en) * | 2020-12-21 | 2021-04-16 | 国网辽宁省电力有限公司物资分公司 | Method and device for selecting terminal equipment nodes in federated learning system |
-
2021
- 2021-02-08 CN CN202110180726.8A patent/CN113033605A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160132566A1 (en) * | 2014-11-10 | 2016-05-12 | Red Hat, Inc. | Native federation view suggestion |
| US20190050515A1 (en) * | 2018-06-27 | 2019-02-14 | Intel Corporation | Analog functional safety with anomaly detection |
| WO2020051193A1 (en) * | 2018-09-05 | 2020-03-12 | Translational Imaging Innovations Llc | Methods, systems and computer program products for retrospective data mining |
| CN111557012A (en) * | 2018-12-03 | 2020-08-18 | 戴斯数字有限责任公司 | Cross-sensor predictive inference |
| CN109872040A (en) * | 2019-01-17 | 2019-06-11 | 南京航空航天大学 | A kind of two part relation probability of malfunction methods of risk assessment of aero-engine |
| EP3699825A2 (en) * | 2019-02-22 | 2020-08-26 | Ubotica Technologies Ltd. | Systems and methods for deploying and updating neural networks at the edge of a network |
| US20210012225A1 (en) * | 2019-08-29 | 2021-01-14 | S20.ai, Inc. | Machine learning based ranking of private distributed data, models and compute resources |
| CN110568360A (en) * | 2019-09-12 | 2019-12-13 | 华中科技大学 | lithium battery aging diagnosis method based on fuzzy logic algorithm |
| CN110929290A (en) * | 2019-12-04 | 2020-03-27 | 南京如般量子科技有限公司 | Private key threshold backup, loss reporting and recovery system and method based on alliance chain |
| CN111143308A (en) * | 2019-12-26 | 2020-05-12 | 许昌中科森尼瑞技术有限公司 | Federal learning-based high-low voltage motor data processing method, system and device |
| CN111537945A (en) * | 2020-06-28 | 2020-08-14 | 南方电网科学研究院有限责任公司 | Intelligent ammeter fault diagnosis method and equipment based on federal learning |
| CN111881447A (en) * | 2020-06-28 | 2020-11-03 | 中国人民解放军战略支援部队信息工程大学 | Intelligent evidence obtaining method and system for malicious code fragments |
| CN111722043A (en) * | 2020-06-29 | 2020-09-29 | 南方电网科学研究院有限责任公司 | Power equipment fault detection method, device and system |
| CN112183764A (en) * | 2020-10-12 | 2021-01-05 | 中国石油大学(华东) | Internet of things equipment fault detection method based on block chain and federal learning |
| CN112101489A (en) * | 2020-11-18 | 2020-12-18 | 天津开发区精诺瀚海数据科技有限公司 | Equipment fault diagnosis method driven by united learning and deep learning fusion |
| CN112668128A (en) * | 2020-12-21 | 2021-04-16 | 国网辽宁省电力有限公司物资分公司 | Method and device for selecting terminal equipment nodes in federated learning system |
| CN112288573A (en) * | 2020-12-25 | 2021-01-29 | 支付宝(杭州)信息技术有限公司 | Method, device and equipment for constructing risk assessment model |
Non-Patent Citations (3)
| Title |
|---|
| WEISHAN ZHANG: "Dynamic-Fusion-Based Federated Learning for COVID-19 Detection", 《IEEE INTERNET OF THINGS JOURNAL》, no. 8, 4 February 2021 (2021-02-04), pages 15884 * |
| YANG ZHAO等: "Privacy-Preserving Blockchain-Based Federated Learning for IoT Devices", 《ARXIV》, 1 February 2021 (2021-02-01), pages 1 - 4 * |
| 刘耕: "联邦学习在5G云边协同场景中的原理和应用综述", 《通讯世界》, no. 7, 31 July 2020 (2020-07-31), pages 50 - 52 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110378463B (en) | Artificial intelligence model standardization training platform and automatic system | |
| CN109523752B (en) | Equipment fault early warning method and device, electronic equipment and medium | |
| CN107390056B (en) | Detect the method and system of charging pile | |
| WO2019116354A1 (en) | Training of artificial neural networks using safe mutations based on output gradients | |
| CN109143094B (en) | Abnormal data detection method and device for power battery | |
| CN103676939B (en) | A kind of Auto-Test System based on OSEK straight-forward network administrative mechanisms | |
| CN107577607A (en) | User interface automated testing method, device, electronic equipment, storage medium | |
| CN107608291A (en) | A kind of intelligent substation application function linkage rule verification method and system | |
| WO2016195897A1 (en) | System for analytic model development | |
| CN108470000A (en) | Communicating terminal Software Automatic Testing Method, system and medium | |
| CN107168844B (en) | Performance monitoring method and device | |
| CN114385480A (en) | Hardware-in-loop test system for automatic verification of FOTA function of vehicle | |
| CN109005079A (en) | A kind of detection method and device of electric automobile charging pile communication protocol | |
| CN107817789A (en) | CAN emulation test system | |
| CN114048024A (en) | Task deployment method, device, equipment, storage medium and product | |
| CN114936062A (en) | Method, device, equipment, system and storage medium for automatically debugging equipment | |
| CN109324956A (en) | System detection method, equipment and computer readable storage medium | |
| CN113033605A (en) | Motor fault judgment method and device, terminal equipment and computer storage medium | |
| Surya et al. | Dashboard for Industrial Load Control and Remote Power Factor Correction Based on Adafruit's MQTT | |
| CN105717472A (en) | Electric energy quality monitoring terminal simulator | |
| CN111506305A (en) | Tool kit generation method and device, computer equipment and readable storage medium | |
| CN113326113B (en) | Task processing method and device, electronic equipment and storage medium | |
| CN115827353A (en) | Fault diagnosis method and device | |
| CN114942890A (en) | User interface testing method, device, equipment and medium | |
| CN109065111A (en) | A kind of cloud platform health check system and method based on docker |
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 |