CN111290371A - Method and device for remote diagnosis of Internet of things equipment and electronic equipment - Google Patents
Method and device for remote diagnosis of Internet of things equipment and electronic equipment Download PDFInfo
- Publication number
- CN111290371A CN111290371A CN202010157588.7A CN202010157588A CN111290371A CN 111290371 A CN111290371 A CN 111290371A CN 202010157588 A CN202010157588 A CN 202010157588A CN 111290371 A CN111290371 A CN 111290371A
- Authority
- CN
- China
- Prior art keywords
- equipment
- data
- internet
- actual
- things
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004171 remote diagnosis Methods 0.000 title claims abstract description 25
- 238000005070 sampling Methods 0.000 claims abstract description 85
- 238000012549 training Methods 0.000 claims abstract description 80
- 238000003745 diagnosis Methods 0.000 claims abstract description 70
- 230000003068 static effect Effects 0.000 claims abstract description 29
- 230000005856 abnormality Effects 0.000 claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims description 8
- 230000008901 benefit Effects 0.000 abstract description 5
- 238000010801 machine learning Methods 0.000 abstract description 4
- 230000002349 favourable effect Effects 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 101100435070 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) APN2 gene Proteins 0.000 description 2
- 101100268779 Solanum lycopersicum ACO1 gene Proteins 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 101100401199 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) SAM2 gene Proteins 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a method and a device for remote diagnosis of Internet of things equipment and electronic equipment. The method comprises the steps of configuring static equipment data of a plurality of pieces of equipment of the Internet of things to be trained, and respectively collecting equipment operation data of the plurality of pieces of equipment of the Internet of things to be trained at a plurality of sampling time points to form a training characteristic data set; training by utilizing the training characteristic data set to obtain a diagnosis model for representing the corresponding relation between the sampling time point and the equipment operation data; and carrying out remote diagnosis on the equipment of the Internet of things to be diagnosed based on the diagnosis model. A training characteristic data set is formed by collecting a large amount of equipment operation data of some Internet of things equipment, so that machine learning can be carried out by using the training characteristic data set to obtain a diagnosis model, and whether the Internet of things equipment is abnormal or not can be remotely diagnosed. Therefore, the remote diagnosis method can save diagnosis time, can quickly obtain a diagnosis result, is favorable for quickly solving the problem of equipment abnormality, and improves economic benefits.
Description
Technical Field
The invention belongs to the technical field of communication, and particularly relates to a remote diagnosis method for equipment of the Internet of things, a remote diagnosis device for the equipment of the Internet of things and electronic equipment.
Background
The structure of modern manufacturing equipment is gradually complicated, the automation degree is higher and higher, a plurality of devices integrate a plurality of advanced technologies such as machinery, electronics, automatic control, computers and the like, and various components in the devices are mutually linked and interdependent, so that the difficulty of equipment fault diagnosis is increased. Because a lot of uncertain factors exist in a manufacturing field, various faults inevitably occur in the operation process of equipment, and once the faults occur, whether the faults can be rapidly diagnosed and dispatched is very important for manufacturing enterprises. Users of mechanical remanufacturing equipment are both line-of-production workers and technicians who are generally only able to solve a few simple problems when the system is more serious. When a complex fault occurs, the problem can be solved only by the help of related experts, but if the fault occurs every time, it is not practical to ask a diagnosis expert to the field, so that a new requirement is provided for fault diagnosis of mechanical manufacturing equipment, namely how to overcome the limitation of region and time and realize the cooperative diagnosis of remote experts. In recent years, the Internet technology is rapidly developed along with the global information construction, and the Internet technology breaks through the limitation of the traditional communication mode, so that information exchange is more free, rapid and convenient.
The remote fault diagnosis of the equipment is mainly characterized in that the equipment and the diagnosis resource are separated in regions, the diagnosis resource providing service and the diagnosed equipment are communicated through a network to form a loose logic whole, and the diagnosed equipment is remotely diagnosed through network connection.
In the case of the current network, it is usually necessary to remotely diagnose a plurality of devices in the network by a plurality of experienced personnel (usually equipment manufacturers or operator maintenance personnel) to determine whether the devices are faulty, because the current network is basically a heterogeneous network, a network (such as hua shi, zhongxing, H3C, etc.) composed of devices of different manufacturers, and remote fault diagnosis of network devices becomes time-consuming and labor-consuming, and it is difficult to quickly obtain a diagnosis result until a fault occurs, and it is still difficult to quickly recover.
Disclosure of Invention
The invention aims to solve at least one of the technical problems in the prior art, and provides a method for remotely diagnosing equipment of the internet of things, a device for remotely diagnosing the equipment of the internet of things and electronic equipment.
In one aspect of the invention, a method for remotely diagnosing equipment of the internet of things is provided, which comprises the following steps:
respectively configuring equipment static data of a plurality of pieces of equipment of the Internet of things to be trained, wherein the equipment static data comprises equipment network basic information and equipment self basic information;
respectively acquiring equipment operation data of a plurality of pieces of equipment of the Internet of things to be trained at a plurality of sampling time points to form a training characteristic data set, wherein the equipment operation data comprises equipment network characteristic data and equipment resource utilization data;
training by using the training feature data set to obtain a diagnosis model, wherein the diagnosis model is used for representing the corresponding relation between the sampling time point and the equipment operation data;
and carrying out remote diagnosis on the equipment of the Internet of things to be diagnosed based on the diagnosis model.
In some optional embodiments, before the training with the training feature data set to obtain the diagnostic model, the method further includes:
respectively extracting characteristic values of the equipment operation data of each sampling time point;
respectively calculating the standard deviation of each characteristic value corresponding to each sampling time point;
and comparing each characteristic value of each sampling time point with the corresponding standard deviation respectively, and removing the characteristics corresponding to the characteristic values which do not meet the preset relation with the standard deviation from the training characteristic data set.
In some alternative embodiments, the predetermined relationship is that the characteristic value is not greater than 3 times the standard deviation.
In some optional embodiments, after the features corresponding to the feature values that do not satisfy the predetermined relationship with the standard deviation are removed from the training feature data set and before the training is performed by using the training feature data set to obtain the diagnostic model, the method further includes:
and respectively calculating the arithmetic mean value of each characteristic value corresponding to each sampling time point, and taking each arithmetic mean value as the characteristic reference value of the corresponding sampling time point.
In some optional embodiments, the device network basic information includes the number of device interfaces, device interface bandwidth, and uplink and downlink interface interconnection states of the device; and/or the presence of a gas in the gas,
the basic information of the equipment comprises address/port information acquired by equipment data, the number of CPU cores of the equipment, the internal memory capacity of the equipment and the capacity of a hard disk of the equipment; and/or the presence of a gas in the gas,
the equipment network characteristic data comprises the state of an equipment interface and the quantity of data messages transmitted and received by the equipment interface; and/or the presence of a gas in the gas,
the device resource utilization data comprises device CPU utilization rate, device memory utilization rate, device hard disk utilization rate, device thread/process number and device open port state.
In some optional embodiments, the remotely diagnosing the to-be-diagnosed internet of things device based on the diagnosis model includes:
acquiring actual static data and actual running data of the equipment of the Internet of things to be diagnosed at an actual sampling time point, wherein the actual static data of the equipment comprises actual network basic information of the equipment and actual self basic information of the equipment, and the actual running data of the equipment comprises actual network characteristic data of the equipment and actual resource utilization data of the equipment;
inputting the actual sampling time points into the diagnostic model to obtain device expected operating data corresponding to the actual sampling time points, the device expected operating data including device expected network characteristic data and device expected resource utilization data;
comparing the actual operating data of the equipment with the expected operating data of the equipment to output a diagnosis result.
In some optional embodiments, the acquiring, at an actual sampling time point, device actual operation data of the to-be-diagnosed internet of things device includes:
acquiring actual operation data of the equipment of the Internet of things to be diagnosed for multiple times at the actual sampling time point;
calculating an average value of the actual operation data of the equipment;
the comparing the actual operating data of the equipment with the expected operating data of the equipment to output the diagnosis result comprises:
comparing the average of the actual operating data of the device with the expected data of the device corresponding to the actual sampling time point in the time dimension to output a diagnosis result.
In some optional embodiments, the comparing the actual operation data of the device with the expected operation data of the device to output the diagnosis result comprises:
comparing the device actual resource utilization data with device expected resource utilization data, and comparing the device actual network characteristic data with the device expected network characteristic data;
responding to the fact that the actual resource utilization data of the equipment do not accord with the expected resource utilization data of the equipment, judging whether the actual static data of the equipment are modified or not, if not, outputting a general alarm for the abnormality of the Internet of things equipment to be diagnosed, and outputting an important alarm for the abnormality of the Internet of things equipment to be diagnosed after continuously outputting the general alarm for the abnormality of the Internet of things equipment to be diagnosed for multiple times;
responding to the fact that the actual network feature data of the equipment do not accord with the expected feature data of the equipment, judging whether the network feature data of the uplink and downlink Internet of things equipment of the Internet of things equipment to be diagnosed are abnormal or not, and if yes, outputting an important alarm that the Internet of things equipment to be diagnosed is abnormal; and if not, outputting the general alarm for the abnormality of the Internet of things equipment to be diagnosed.
In another aspect of the present invention, an apparatus for remotely diagnosing an internet of things device is provided, including:
the system comprises a configuration module, a training module and a training module, wherein the configuration module is used for respectively configuring equipment static data of a plurality of pieces of equipment of the Internet of things to be trained, and the equipment static data comprises equipment network basic information and equipment self basic information;
the system comprises an acquisition module, a training module and a training module, wherein the acquisition module is used for respectively acquiring equipment operation data of a plurality of pieces of equipment of the Internet of things to be trained at a plurality of sampling time points to form a training characteristic data set, and the equipment operation data comprises equipment network characteristic data and equipment resource utilization data;
the training module is used for training by utilizing the training characteristic data set to obtain a diagnosis model, and the diagnosis model is used for representing the corresponding relation between the sampling time point and the equipment operation data;
and the diagnosis module is used for carrying out remote diagnosis on the equipment of the Internet of things to be diagnosed based on the diagnosis model.
In some optional embodiments, the method further comprises, before the training with the training feature data set to obtain the diagnostic model, a calculation module specifically configured to:
respectively extracting characteristic values of the equipment operation data of each sampling time point;
respectively calculating the standard deviation of each characteristic value corresponding to each sampling time point;
and comparing each characteristic value of each sampling time point with the corresponding standard deviation respectively, and removing the characteristics corresponding to the characteristic values which do not meet the preset relation with the standard deviation from the training characteristic data set.
In some alternative embodiments, the predetermined relationship is that the characteristic value is not greater than 3 times the standard deviation.
In some optional embodiments, after the features corresponding to the feature values that do not satisfy the predetermined relationship with the standard deviation are removed from the training feature data set and before the training is performed by using the training feature data set to obtain the diagnostic model, the calculation module is further configured to:
and respectively calculating the arithmetic mean value of each characteristic value corresponding to each sampling time point, and taking each arithmetic mean value as the characteristic reference value of the corresponding sampling time point.
In some optional embodiments, the device network basic information includes the number of device interfaces, device interface bandwidth, and uplink and downlink interface interconnection states of the device; and/or the presence of a gas in the gas,
the basic information of the equipment comprises address/port information acquired by equipment data, the number of CPU cores of the equipment, the internal memory capacity of the equipment and the capacity of a hard disk of the equipment; and/or the presence of a gas in the gas,
the equipment network characteristic data comprises the state of an equipment interface and the quantity of data messages transmitted and received by the equipment interface; and/or the presence of a gas in the gas,
the device resource utilization data comprises device CPU utilization rate, device memory utilization rate, device hard disk utilization rate, device thread/process number and device open port state.
In some alternative embodiments, the diagnostic module includes an acquisition sub-module, an input sub-module, and a comparison sub-module; wherein, be used for specifically:
the acquisition submodule is used for acquiring actual static data of the equipment of the Internet of things to be diagnosed and actual operation data of the equipment at an actual sampling time point, wherein the actual static data of the equipment comprises actual network basic information of the equipment and actual self basic information of the equipment, and the actual operation data of the equipment comprises actual network characteristic data of the equipment and actual resource utilization data of the equipment;
the input submodule is used for inputting the actual sampling time point into the diagnostic model so as to obtain expected operation data of the equipment corresponding to the actual sampling time point, and the expected operation data of the equipment comprises expected network characteristic data of the equipment and expected resource utilization data of the equipment;
the comparison submodule is used for comparing the actual operation data of the equipment with the expected operation data of the equipment so as to output a diagnosis result.
In some optional embodiments, the acquisition sub-module is further specifically configured to acquire, at the actual sampling time point, actual device operating data of the to-be-diagnosed internet of things device for multiple times, and calculate an average value of the actual device operating data;
the comparison sub-module is specifically further configured to compare the average value of the actual operating data of the device with the expected data of the device corresponding to the actual sampling time point in the time dimension, so as to output a diagnosis result.
In some optional embodiments, the comparison sub-module is further configured to:
comparing the device actual resource utilization data with device expected resource utilization data, and comparing the device actual network characteristic data with the device expected network characteristic data;
responding to the fact that the actual resource utilization data of the equipment do not accord with the expected resource utilization data of the equipment, judging whether the actual static data of the equipment are modified or not, if not, outputting a general alarm for the abnormality of the Internet of things equipment to be diagnosed, and outputting an important alarm for the abnormality of the Internet of things equipment to be diagnosed after continuously outputting the general alarm for the abnormality of the Internet of things equipment to be diagnosed for multiple times;
responding to the fact that the actual network feature data of the equipment do not accord with the expected feature data of the equipment, judging whether the network feature data of the uplink and downlink Internet of things equipment of the Internet of things equipment to be diagnosed are abnormal or not, and if yes, outputting an important alarm that the Internet of things equipment to be diagnosed is abnormal; and if not, outputting the general alarm for the abnormality of the Internet of things equipment to be diagnosed.
In another aspect of the present invention, an electronic device is provided, including:
one or more processors;
a storage unit for storing one or more programs which, when executed by the one or more processors, enable the one or more processors to implement the method according to the preceding description.
In another aspect of the invention, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, is adapted to carry out the method according to the above description.
In another aspect of the invention, a computer program is provided, which, when being executed by a processor, is capable of carrying out the method according to the above description.
According to the method and the device for remotely diagnosing the equipment of the Internet of things, disclosed by the invention, the training characteristic data set is formed by collecting a large amount of equipment operation data of some equipment of the Internet of things, so that machine learning can be carried out by utilizing the training characteristic data set to obtain a diagnosis model, and whether the equipment of the Internet of things is abnormal or not can be remotely diagnosed. Therefore, the remote diagnosis method can save diagnosis time, can quickly obtain a diagnosis result, is favorable for quickly solving the problem of equipment abnormality, and improves economic benefits.
Drawings
Fig. 1 is a schematic structural diagram of an electronic device according to a first embodiment of the present invention;
fig. 2 is a flowchart of a remote diagnosis method for internet of things devices according to a second embodiment of the present invention;
FIG. 3 is a data baseline diagram of CPU utilization according to a third embodiment of the present invention;
FIG. 4 is a diagram illustrating a data baseline for receiving the number of packet increments according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus for remotely diagnosing internet of things devices according to a fifth embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
First, an example electronic device for implementing an apparatus for remote diagnosis of internet of things devices and a method for remote diagnosis of internet of things devices according to an embodiment of the present invention is described with reference to fig. 1.
As shown in FIG. 1, electronic device 200 includes one or more processors 210, one or more memory devices 220, one or more input devices 230, one or more output devices 240, and the like, interconnected by a bus system 250 and/or other form of connection mechanism. It should be noted that the components and structures of the electronic device shown in fig. 1 are exemplary only, and not limiting, and the electronic device may have other components and structures as desired.
The processor 210 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 200 to perform desired functions.
Storage 220 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. On which one or more computer program instructions may be stored that may be executed by a processor to implement client functionality (implemented by the processor) and/or other desired functionality in embodiments of the invention described below. Various applications and various data, such as various data used and/or generated by the applications, may also be stored in the computer-readable storage medium.
The input device 230 may be a device used by a user to input instructions and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.
The output device 240 may output various information (e.g., images or sounds) to an outside (e.g., a user), and may include one or more of a display, a speaker, and the like.
In the following, a method for remote diagnosis of an internet of things device according to an embodiment of the invention will be described with reference to fig. 2.
As shown in fig. 2, a method S100 for remote diagnosis of an internet of things device includes:
and S110, respectively configuring static data of a plurality of pieces of equipment of the Internet of things to be trained, wherein the static data of the equipment comprises basic information of an equipment network and basic information of the equipment.
Specifically, in this step, the device network basic information may include, for example, the number of device interfaces, the device interface bandwidth, the interconnection status of the interfaces of the upstream and downstream devices (for example, the ETH1 interface of the a device is connected to the ETH2 interface of the B device), and the like. The basic information of the device itself may include, for example, address/port information of device data acquisition, a device CPU core number, a device memory capacity, a device hard disk capacity, and the like.
And S120, respectively acquiring device operation data of a plurality of pieces of equipment of the Internet of things to be trained at a plurality of sampling time points to form a training feature data set, wherein the device operation data comprises device network feature data and device resource utilization data.
Specifically, in this step, the plurality of sampling time points may be, for example, several time points fixed every day from monday to sunday, such as 8:00, 8:30, 9:00, 9:30, 10:00, 10:30, 13:00, 13:30, 14:00, 14:30, and the like, or several sampling dates may be extracted every month, such as several time points fixed every day from 1 day, 5 days, 10 days, and the like, each month. Of course, those skilled in the art may select other sampling time points according to actual needs, and this embodiment is not limited to this. In this step, the device network characteristic data may include, for example, a state (Up/Down) of the device interface, a quantity of data packets transmitted and received by the device interface, and the like. The device resource utilization data may include, for example, a device CPU utilization, a device memory utilization, a device hard disk utilization, a device thread/process number, a device open port state, and the like.
S130, training by using the training characteristic data set to obtain a diagnosis model, wherein the diagnosis model is used for representing the corresponding relation between the sampling time point and the equipment operation data.
Specifically, in this step, a baseline learning manner may be adopted, and the diagnostic model is obtained by training using the training feature data set. For example, as shown in fig. 3, in step S120, for the CPU utilization, the CPU utilization data corresponding to 13 sampling time points, i.e., 1:10 sampling time points, 1:20 … to 3:10 sampling time points, respectively, may be fitted to a relevant CPU utilization baseline when the discrete CPU utilization is used for baseline learning, as shown in fig. 3. The CPU utilization baseline is one of the diagnostic models, and thus, as long as any one sampling time point is input into the diagnostic model, it corresponds to one CPU utilization value. For another example, as shown in fig. 4, for the increment of the packet received by ETH1, that is, the number of data packets to be transmitted and received by the device interface, the increment of the packet received corresponding to 13 sampling time points, such as sampling time points 1:10, 1:20 … to 3:10, may be fitted to a relevant baseline of the increment of the packet received when the discrete increment of the packet is used for baseline learning, as shown in fig. 4. The baseline of the increment of the received data packet is one of the diagnostic models, so that the increment of one received data packet corresponds to any sampling time point input into the diagnostic model. Of course, according to different operation data of the device, other data baselines, such as hard disk utilization rate, memory utilization rate, etc., may also be obtained.
And S140, carrying out remote diagnosis on the equipment of the Internet of things to be diagnosed based on the diagnosis model.
Specifically, in this step, as described in step S130, the diagnosis model may be a data baseline of each feature in the device operation data, so that the device actual operation data of the to-be-diagnosed internet of things device may be obtained and compared with the data baseline, thereby implementing remote diagnosis of the device.
According to the method for remotely diagnosing the equipment of the Internet of things, a training characteristic data set is formed by collecting a large amount of equipment operation data of some equipment of the Internet of things, so that machine learning can be carried out by using the training characteristic data set to obtain a diagnosis model, and whether the equipment of the Internet of things is abnormal or not can be remotely diagnosed. Therefore, the remote diagnosis method of the embodiment can save diagnosis time, can quickly obtain a diagnosis result, is beneficial to quickly solving the problem of equipment abnormality, and improves economic benefits.
In some optional embodiments, before the training with the training feature data set to obtain the diagnostic model, the method further includes:
and respectively extracting the characteristic value of the running data of each device at each sampling time point. And respectively calculating the standard deviation of each characteristic value corresponding to each sampling time point. And comparing each characteristic value of each sampling time point with the corresponding standard deviation respectively, and removing the characteristics corresponding to the characteristic values which do not meet the preset relation with the standard deviation from the training characteristic data set.
Exemplarily, assuming that data is normally distributed, and anomaly-removed data (normally distributed data is almost totally concentrated in an interval (μ -3 σ, μ +3 σ), and the probability of exceeding the range is only less than 0.3%. an algorithm is adopted to realize error data elimination, taking device operation data as the CPU utilization rate as an example to explain, assuming that ten pieces of CPU utilization rate data of ten pieces of training internet-of-things devices are respectively collected at one sampling time point, the data is expressed as:
D={(S1,0.2)、(S2,0.25)、(S3,0.3)、(S4,0.9)、(S5,0.8)、(S6,0.45)、(S7,0.2)、(S8,0.1)、(S9,0.45)、(S10,0.7)}。
the standard deviation of the utilization rates of the ten CPUs is calculated to be 0.28, then whether the utilization rate value of the CPU corresponding to each sampling time point is greater than 3 times of the standard deviation or not is judged, and the CPU utilization rate value 0.9 corresponding to the fourth training device S4 is found to be greater than 3 times of the standard deviation through calculation, so that the CPU utilization rate acquired at this time can be judged to be error data and needs to be eliminated, the accuracy of the finally obtained training feature data set can be ensured, a proper diagnosis model can be obtained through training, and the diagnosis yield of remote diagnosis of the Internet of things device by using the diagnosis model can be improved.
It should be noted that, besides the above-mentioned manner to eliminate the error data, a person skilled in the art may select some other eliminating manners according to actual needs, and this embodiment does not specifically limit this.
In some optional embodiments, after the features corresponding to the feature values that do not satisfy the predetermined relationship with the standard deviation are removed from the training feature data set and before the training is performed by using the training feature data set to obtain the diagnostic model, the method further includes:
and respectively calculating the arithmetic mean value of each characteristic value corresponding to each sampling time point, and taking each arithmetic mean value as the characteristic reference value of the corresponding sampling time point.
For example, taking ten pieces of CPU utilization as an example, after the device operation data of the training internet of things is eliminated in S4, at each sampling time point, an average value of the device operation data of the multiple training internet of things devices at the sampling time point needs to be calculated, and the average value is used as a feature reference value of the sampling time point. For example, after the culling S4, the average value of the above data D is 0.38, and therefore, 0.38 is taken as the characteristic reference value of the CPU utilization at the sampling time point.
According to the method for remotely diagnosing the equipment in the Internet of things, the arithmetic mean value is used as the corresponding characteristic reference value of the sampling time point, so that the accuracy of a finally obtained training characteristic data set can be ensured, a proper diagnosis model can be obtained through training, and the diagnosis yield of remotely diagnosing the equipment in the Internet of things by using the diagnosis model is improved.
In some optional embodiments, the remotely diagnosing the to-be-diagnosed internet of things device based on the diagnosis model includes:
and acquiring actual static data and actual running data of the equipment of the Internet of things to be diagnosed at an actual sampling time point, wherein the actual static data of the equipment comprises actual network basic information of the equipment and actual self basic information of the equipment, and the actual running data of the equipment comprises actual network characteristic data of the equipment and actual resource utilization data of the equipment.
Specifically, in this step, the actual device operation data of the internet of things device to be diagnosed may be collected at regular time (for example, every 2 minutes), and mainly includes the actual device network characteristic data and the actual device resource utilization data, where the network characteristic data includes the state (Up/Down) of the interface and the statistics of the data packets received and transmitted by the interface; the resource utilization data of the device includes cpu utilization, memory utilization, hard disk utilization, thread/process number of the device, open port condition of the device, and the like. The method comprises the steps of collecting actual static data of the equipment of the Internet of things to be diagnosed at regular time (for example, every 2 minutes), obtaining actual configuration modification conditions of the equipment, and eliminating the conditions that data mutation and false alarm are caused due to equipment parameter configuration of personnel.
Inputting the actual sampling time points into the diagnostic model to obtain device expected operating data corresponding to the actual sampling time points, the device expected operating data including device expected network characteristic data and device expected resource utilization data.
Comparing the actual operating data of the equipment with the expected operating data of the equipment to output a diagnosis result.
In some optional embodiments, the acquiring, at an actual sampling time point, device actual operation data of the to-be-diagnosed internet of things device includes acquiring, at the actual sampling time point, device actual operation data of the to-be-diagnosed internet of things device multiple times. And calculating the average value of the actual operation data of the equipment. Comparing the average of the actual operating data of the device with the expected data of the device corresponding to the actual sampling time point in the time dimension to output a diagnosis result.
Specifically, in this step, an average value is calculated based on the acquired data (the baseline is data in units of every 10 minutes, and the average value is calculated by sampling 5 times continuously during the diagnosis process), and comparison is performed on the baseline based on a time dimension (for example, data of 10 points in the current Monday is compared with data of 10 points in the baseline of the last Monday), so as to obtain a diagnosis result.
In some optional embodiments, the comparing the actual operation data of the device with the expected operation data of the device to output the diagnosis result comprises:
comparing the device actual resource utilization data with device expected resource utilization data, and comparing the device actual network characteristic data with the device expected network characteristic data;
and in response to the fact that the actual resource utilization data of the equipment do not accord with the expected resource utilization data of the equipment, judging whether the actual static data of the equipment are modified, if not, outputting a general alarm of the abnormality of the Internet of things equipment to be diagnosed, and outputting an important alarm of the abnormality of the Internet of things equipment to be diagnosed after continuously outputting the general alarm of the abnormality of the Internet of things equipment to be diagnosed for multiple times.
Responding to the fact that the actual network feature data of the equipment do not accord with the expected feature data of the equipment, judging whether the network feature data of the uplink and downlink Internet of things equipment of the Internet of things equipment to be diagnosed are abnormal or not, and if yes, outputting an important alarm that the Internet of things equipment to be diagnosed is abnormal; and if not, outputting the general alarm for the abnormality of the Internet of things equipment to be diagnosed.
The method for remotely diagnosing the equipment of the Internet of things has the important advantages that the remote equipment diagnosis is comprehensively carried out by combining a set of mechanism and algorithm and other external influence factors such as artificial factors and factors of network uplink and downlink equipment, and the method for judging whether the remote equipment has a fault or not is low in cost, high in real-time performance and high in accuracy, so that more accurate service is provided for a client more continuously.
In another aspect of the present invention, as shown in fig. 5, there is provided an apparatus 100 for remote diagnosis of an internet of things device, where the apparatus 100 may be applied to the diagnosis method described above, and specific contents thereof may refer to the related descriptions above, which are not described herein again. The apparatus 100 comprises:
the configuration module 110 is configured to configure device static data of a plurality of internet of things devices to be trained, where the device static data includes device network basic information and device self basic information;
the acquisition module 120 is configured to acquire device operation data of a plurality of internet of things devices to be trained at a plurality of sampling time points, respectively, to form a training feature data set, where the device operation data includes device network feature data and device resource utilization data;
a training module 130, configured to perform training using the training feature data set to obtain a diagnostic model, where the diagnostic model is used to represent a correspondence between the sampling time point and the device operation data;
and the diagnosis module 140 is used for performing remote diagnosis on the internet of things equipment to be diagnosed based on the diagnosis model.
The device for remotely diagnosing the equipment in the Internet of things forms a training characteristic data set by collecting a large amount of equipment operation data of some equipment in the Internet of things, so that machine learning can be carried out by using the training characteristic data set, a diagnosis model is obtained, and whether the equipment in the Internet of things is abnormal or not is remotely diagnosed. Therefore, the remote diagnosis device of the embodiment can save diagnosis time, can quickly obtain a diagnosis result, is beneficial to quickly solving the problem of equipment abnormality, and improves economic benefits.
In some optional embodiments, as shown in fig. 5, the apparatus 100 further includes a calculation module 150, before the training with the training feature data set to obtain the diagnostic model, the calculation module 150 is specifically configured to:
respectively extracting characteristic values of the equipment operation data of each sampling time point;
respectively calculating the standard deviation of each characteristic value corresponding to each sampling time point;
and comparing each characteristic value of each sampling time point with the corresponding standard deviation respectively, and removing the characteristics corresponding to the characteristic values which do not meet the preset relation with the standard deviation from the training characteristic data set.
In some alternative embodiments, the predetermined relationship is that the characteristic value is not greater than 3 times the standard deviation.
In some optional embodiments, after the features corresponding to the feature values that do not satisfy the predetermined relationship with the standard deviation are removed from the training feature data set and before the training is performed by using the training feature data set to obtain the diagnostic model, the calculation module 150 is further configured to:
and respectively calculating the arithmetic mean value of each characteristic value corresponding to each sampling time point, and taking each arithmetic mean value as the characteristic reference value of the corresponding sampling time point.
In some optional embodiments, the device network basic information includes the number of device interfaces, device interface bandwidth, and uplink and downlink interface interconnection states of the device; and/or the presence of a gas in the gas,
the basic information of the equipment comprises address/port information acquired by equipment data, the number of CPU cores of the equipment, the internal memory capacity of the equipment and the capacity of a hard disk of the equipment; and/or the presence of a gas in the gas,
the equipment network characteristic data comprises the state of an equipment interface and the quantity of data messages transmitted and received by the equipment interface; and/or the presence of a gas in the gas,
the device resource utilization data comprises device CPU utilization rate, device memory utilization rate, device hard disk utilization rate, device thread/process number and device open port state.
In some alternative embodiments, as shown in fig. 5, the diagnostic module 140 includes an acquisition submodule 141, an input submodule 142, and a comparison submodule 143; wherein, be used for specifically:
the acquisition submodule 141 is configured to acquire device actual static data and device actual operation data of the to-be-diagnosed internet of things device at an actual sampling time point, where the device actual static data includes device actual network basic information and device actual self basic information, and the device actual operation data includes device actual network feature data and device actual resource utilization data;
the input sub-module 142 is configured to input the actual sampling time point into the diagnostic model to obtain expected device operation data corresponding to the actual sampling time point, where the expected device operation data includes expected device network characteristic data and expected device resource utilization data;
the comparison sub-module 143 is configured to compare the actual operation data of the device with the expected operation data of the device, so as to output a diagnosis result.
In some optional embodiments, the collecting sub-module 141 is further specifically configured to collect, at the actual sampling time point, device actual operation data of the to-be-diagnosed internet of things device for multiple times, and calculate an average value of the device actual operation data;
the comparison sub-module 143 is further configured to compare the average value of the actual operation data of the device with the expected data of the device corresponding to the actual sampling time point in the time dimension, so as to output a diagnosis result.
In some optional embodiments, the comparing sub-module 143 is further configured to:
comparing the device actual resource utilization data with device expected resource utilization data, and comparing the device actual network characteristic data with the device expected network characteristic data;
responding to the fact that the actual resource utilization data of the equipment do not accord with the expected resource utilization data of the equipment, judging whether the actual static data of the equipment are modified or not, if not, outputting a general alarm for the abnormality of the Internet of things equipment to be diagnosed, and outputting an important alarm for the abnormality of the Internet of things equipment to be diagnosed after continuously outputting the general alarm for the abnormality of the Internet of things equipment to be diagnosed for multiple times;
responding to the fact that the actual network feature data of the equipment do not accord with the expected feature data of the equipment, judging whether the network feature data of the uplink and downlink Internet of things equipment of the Internet of things equipment to be diagnosed are abnormal or not, and if yes, outputting an important alarm that the Internet of things equipment to be diagnosed is abnormal; and if not, outputting the general alarm for the abnormality of the Internet of things equipment to be diagnosed.
In another aspect of the present invention, an electronic device is provided, including:
one or more processors;
a storage unit for storing one or more programs which, when executed by the one or more processors, enable the one or more processors to implement the method according to the preceding description.
In another aspect of the invention, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, is adapted to carry out the method according to the above description.
The computer readable medium may be included in the apparatus, device, system, or may exist separately.
The computer readable storage medium may be any tangible medium that can contain or store a program, and may be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, more specific examples of which include, but are not limited to: a portable computer diskette, a hard disk, an optical fiber, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may also include a propagated data signal with computer readable program code embodied therein, for example, in a non-transitory form, such as in a carrier wave or in a carrier wave, wherein the carrier wave is any suitable carrier wave or carrier wave for carrying the program code.
In another aspect of the invention, a computer program is provided, which when executed by a processor is capable of implementing the method according to the above description.
It will be appreciated that the computer program may be stored on a computer storage medium such as the Random Access Memory (RAM), Read Only Memory (ROM), erasable programmable read only memory (EPROM or flash memory), portable compact disc read only memory (CD-ROM), and the like, described above.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.
Claims (10)
1. A method for remotely diagnosing equipment of the Internet of things is characterized by comprising the following steps:
respectively configuring equipment static data of a plurality of pieces of equipment of the Internet of things to be trained, wherein the equipment static data comprises equipment network basic information and equipment self basic information;
respectively acquiring equipment operation data of a plurality of pieces of equipment of the Internet of things to be trained at a plurality of sampling time points to form a training characteristic data set, wherein the equipment operation data comprises equipment network characteristic data and equipment resource utilization data;
training by using the training feature data set to obtain a diagnosis model, wherein the diagnosis model is used for representing the corresponding relation between the sampling time point and the equipment operation data;
and carrying out remote diagnosis on the equipment of the Internet of things to be diagnosed based on the diagnosis model.
2. The method of claim 1, further comprising, prior to said training with said training feature dataset to obtain a diagnostic model:
respectively extracting characteristic values of the equipment operation data of each sampling time point;
respectively calculating the standard deviation of each characteristic value corresponding to each sampling time point;
and comparing each characteristic value of each sampling time point with the corresponding standard deviation respectively, and removing the characteristics corresponding to the characteristic values which do not meet the preset relation with the standard deviation from the training characteristic data set.
3. The method of claim 2, wherein the predetermined relationship is that the characteristic value is not greater than 3 times the standard deviation.
4. The method of claim 2, wherein after the features corresponding to feature values that do not satisfy the predetermined relationship with the standard deviation are removed from the training feature data set and before training with the training feature data set to obtain a diagnostic model, the method further comprises:
and respectively calculating the arithmetic mean value of each characteristic value corresponding to each sampling time point, and taking each arithmetic mean value as the characteristic reference value of the corresponding sampling time point.
5. The method according to any one of claims 1 to 4, wherein the device network basic information includes the number of device interfaces, the bandwidth of the device interfaces, and the uplink and downlink interface interconnection states of the devices; and/or the presence of a gas in the gas,
the basic information of the equipment comprises address/port information acquired by equipment data, the number of CPU cores of the equipment, the internal memory capacity of the equipment and the capacity of a hard disk of the equipment; and/or the presence of a gas in the gas,
the equipment network characteristic data comprises the state of an equipment interface and the quantity of data messages transmitted and received by the equipment interface; and/or the presence of a gas in the gas,
the device resource utilization data comprises device CPU utilization rate, device memory utilization rate, device hard disk utilization rate, device thread/process number and device open port state.
6. The method according to any one of claims 1-4, wherein the remotely diagnosing the IOT device to be diagnosed based on the diagnosis model comprises:
acquiring actual static data and actual running data of the equipment of the Internet of things to be diagnosed at an actual sampling time point, wherein the actual static data of the equipment comprises actual network basic information of the equipment and actual self basic information of the equipment, and the actual running data of the equipment comprises actual network characteristic data of the equipment and actual resource utilization data of the equipment;
inputting the actual sampling time points into the diagnostic model to obtain device expected operating data corresponding to the actual sampling time points, the device expected operating data including device expected network characteristic data and device expected resource utilization data;
comparing the actual operating data of the equipment with the expected operating data of the equipment to output a diagnosis result.
7. The method of claim 6,
the collecting of the actual operation data of the to-be-diagnosed internet of things equipment at the actual sampling time point comprises the following steps:
acquiring actual operation data of the equipment of the Internet of things to be diagnosed for multiple times at the actual sampling time point;
calculating an average value of the actual operation data of the equipment;
the comparing the actual operating data of the equipment with the expected operating data of the equipment to output the diagnosis result comprises:
comparing the average of the actual operating data of the device with the expected data of the device corresponding to the actual sampling time point in the time dimension to output a diagnosis result.
8. The method of claim 6, wherein comparing the actual operational data of the plant to the expected operational data of the plant to output a diagnostic result comprises:
comparing the device actual resource utilization data with device expected resource utilization data, and comparing the device actual network characteristic data with the device expected network characteristic data;
responding to the fact that the actual resource utilization data of the equipment do not accord with the expected resource utilization data of the equipment, judging whether the actual static data of the equipment are modified or not, if not, outputting a general alarm for the abnormality of the Internet of things equipment to be diagnosed, and outputting an important alarm for the abnormality of the Internet of things equipment to be diagnosed after continuously outputting the general alarm for the abnormality of the Internet of things equipment to be diagnosed for multiple times;
responding to the fact that the actual network feature data of the equipment do not accord with the expected feature data of the equipment, judging whether the network feature data of the uplink and downlink Internet of things equipment of the Internet of things equipment to be diagnosed are abnormal or not, and if yes, outputting an important alarm that the Internet of things equipment to be diagnosed is abnormal; and if not, outputting the general alarm for the abnormality of the Internet of things equipment to be diagnosed.
9. An apparatus for remote diagnosis of internet of things equipment, comprising:
the system comprises a configuration module, a training module and a training module, wherein the configuration module is used for respectively configuring equipment static data of a plurality of pieces of equipment of the Internet of things to be trained, and the equipment static data comprises equipment network basic information and equipment self basic information;
the system comprises an acquisition module, a training module and a training module, wherein the acquisition module is used for respectively acquiring equipment operation data of a plurality of pieces of equipment of the Internet of things to be trained at a plurality of sampling time points to form a training characteristic data set, and the equipment operation data comprises equipment network characteristic data and equipment resource utilization data;
the training module is used for training by utilizing the training characteristic data set to obtain a diagnosis model, and the diagnosis model is used for representing the corresponding relation between the sampling time point and the equipment operation data;
and the diagnosis module is used for carrying out remote diagnosis on the equipment of the Internet of things to be diagnosed based on the diagnosis model.
10. An electronic device, comprising:
one or more processors;
a storage unit to store one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-8.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010148799 | 2020-03-05 | ||
CN2020101487994 | 2020-03-05 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111290371A true CN111290371A (en) | 2020-06-16 |
CN111290371B CN111290371B (en) | 2021-08-10 |
Family
ID=71028643
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010157588.7A Expired - Fee Related CN111290371B (en) | 2020-03-05 | 2020-03-09 | Method and device for remote diagnosis of Internet of things equipment and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111290371B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114567467A (en) * | 2022-02-17 | 2022-05-31 | 广州贝鼎科技有限公司 | Data exchange method and system for gateway and server of Internet of things |
CN115527203A (en) * | 2022-10-21 | 2022-12-27 | 中粮工程装备无锡有限公司 | Grain drying remote control method and system based on Internet of things |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217216A (en) * | 2014-09-01 | 2014-12-17 | 华为技术有限公司 | Method and device for generating detection model, method and device for detecting target |
CN105848086A (en) * | 2015-01-29 | 2016-08-10 | 宏达国际电子股份有限公司 | Internet of things system and control method thereof |
CN107948921A (en) * | 2018-01-04 | 2018-04-20 | 深圳知路科技有限公司 | The base station intelligence quick deployment method and device of UWB alignment systems |
CN108458885A (en) * | 2017-11-30 | 2018-08-28 | 镇江赛尔尼柯自动化有限公司 | Ship Remote Fault Diagnosis and Decision-making support system |
CN109116224A (en) * | 2018-08-03 | 2019-01-01 | 罗孚电气(厦门)有限公司 | Low-voltage frame circuit breaker method for diagnosing faults, device and calculating equipment |
CN109214595A (en) * | 2018-10-23 | 2019-01-15 | 中核核电运行管理有限公司 | Nuclear power plant's main pump three-level seal failure prediction technique based on big data analysis |
KR20190021560A (en) * | 2017-08-23 | 2019-03-06 | 주식회사 에스씨티 | Failure prediction system using big data and failure prediction method |
CN109524139A (en) * | 2018-10-23 | 2019-03-26 | 中核核电运行管理有限公司 | A kind of real-time device performance monitoring method based on equipment working condition variation |
CN109657945A (en) * | 2018-12-06 | 2019-04-19 | 华中科技大学 | A kind of industrial process fault diagnosis method based on data-driven |
CN109842373A (en) * | 2019-04-15 | 2019-06-04 | 国网河南省电力公司电力科学研究院 | Diagnosing failure of photovoltaic array method and device based on spatial and temporal distributions characteristic |
CN110307983A (en) * | 2019-06-19 | 2019-10-08 | 电子科技大学 | Unmanned plane Method for Bearing Fault Diagnosis based on CNN-Bagging |
CN110460662A (en) * | 2019-09-18 | 2019-11-15 | 中用科技有限公司 | The processing method and system of internet of things data |
CN110455537A (en) * | 2019-09-18 | 2019-11-15 | 合肥工业大学 | A kind of Method for Bearing Fault Diagnosis and system |
CN110794799A (en) * | 2019-11-28 | 2020-02-14 | 桂林电子科技大学 | Big data system with fault diagnosis function applied to industrial production |
-
2020
- 2020-03-09 CN CN202010157588.7A patent/CN111290371B/en not_active Expired - Fee Related
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104217216A (en) * | 2014-09-01 | 2014-12-17 | 华为技术有限公司 | Method and device for generating detection model, method and device for detecting target |
CN105848086A (en) * | 2015-01-29 | 2016-08-10 | 宏达国际电子股份有限公司 | Internet of things system and control method thereof |
KR20190021560A (en) * | 2017-08-23 | 2019-03-06 | 주식회사 에스씨티 | Failure prediction system using big data and failure prediction method |
CN108458885A (en) * | 2017-11-30 | 2018-08-28 | 镇江赛尔尼柯自动化有限公司 | Ship Remote Fault Diagnosis and Decision-making support system |
CN107948921A (en) * | 2018-01-04 | 2018-04-20 | 深圳知路科技有限公司 | The base station intelligence quick deployment method and device of UWB alignment systems |
CN109116224A (en) * | 2018-08-03 | 2019-01-01 | 罗孚电气(厦门)有限公司 | Low-voltage frame circuit breaker method for diagnosing faults, device and calculating equipment |
CN109214595A (en) * | 2018-10-23 | 2019-01-15 | 中核核电运行管理有限公司 | Nuclear power plant's main pump three-level seal failure prediction technique based on big data analysis |
CN109524139A (en) * | 2018-10-23 | 2019-03-26 | 中核核电运行管理有限公司 | A kind of real-time device performance monitoring method based on equipment working condition variation |
CN109657945A (en) * | 2018-12-06 | 2019-04-19 | 华中科技大学 | A kind of industrial process fault diagnosis method based on data-driven |
CN109842373A (en) * | 2019-04-15 | 2019-06-04 | 国网河南省电力公司电力科学研究院 | Diagnosing failure of photovoltaic array method and device based on spatial and temporal distributions characteristic |
CN110307983A (en) * | 2019-06-19 | 2019-10-08 | 电子科技大学 | Unmanned plane Method for Bearing Fault Diagnosis based on CNN-Bagging |
CN110460662A (en) * | 2019-09-18 | 2019-11-15 | 中用科技有限公司 | The processing method and system of internet of things data |
CN110455537A (en) * | 2019-09-18 | 2019-11-15 | 合肥工业大学 | A kind of Method for Bearing Fault Diagnosis and system |
CN110794799A (en) * | 2019-11-28 | 2020-02-14 | 桂林电子科技大学 | Big data system with fault diagnosis function applied to industrial production |
Non-Patent Citations (1)
Title |
---|
朱伟超: "基于机器学习的工业物联网设备故障诊断***的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114567467A (en) * | 2022-02-17 | 2022-05-31 | 广州贝鼎科技有限公司 | Data exchange method and system for gateway and server of Internet of things |
CN115527203A (en) * | 2022-10-21 | 2022-12-27 | 中粮工程装备无锡有限公司 | Grain drying remote control method and system based on Internet of things |
CN115527203B (en) * | 2022-10-21 | 2023-08-25 | 中粮工程装备无锡有限公司 | Cereal drying remote control method and system based on Internet of things |
Also Published As
Publication number | Publication date |
---|---|
CN111290371B (en) | 2021-08-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10732618B2 (en) | Machine health monitoring, failure detection and prediction using non-parametric data | |
US11561959B2 (en) | Method and system for automatic anomaly detection in data | |
US11165799B2 (en) | Anomaly detection and processing for seasonal data | |
EP3323046A1 (en) | Apparatus and method of leveraging machine learning principals for root cause analysis and remediation in computer environments | |
CN111290371B (en) | Method and device for remote diagnosis of Internet of things equipment and electronic equipment | |
CN110647447B (en) | Abnormal instance detection method, device, equipment and medium for distributed system | |
CN109523027B (en) | Boiler operation data monitoring method and device based on Bayesian network | |
CN112801316A (en) | Fault positioning method, system equipment and storage medium based on multi-index data | |
US20220027332A1 (en) | Time-series data condensation and graphical signature analysis | |
CN113342608A (en) | Method and device for monitoring streaming computing engine task | |
WO2020044898A1 (en) | Device status monitoring device and program | |
CN114503132A (en) | Debugging and profiling of machine learning model training | |
CN111626498A (en) | Equipment operation state prediction method, device, equipment and storage medium | |
CN112162528B (en) | Fault diagnosis method, device, equipment and storage medium of numerical control machine tool | |
CN115269315A (en) | Abnormity detection method, device, equipment and medium | |
CN114003466A (en) | Fault root cause positioning method for micro-service application program | |
CN114881112A (en) | System anomaly detection method, device, equipment and medium | |
CN112948154A (en) | System abnormity diagnosis method, device and storage medium | |
CN113051135A (en) | Application thread pool monitoring method and thread pool monitoring device | |
CN112712305A (en) | Aircraft system and health assessment method and device thereof | |
CN113138872A (en) | Abnormal processing device and method for database system | |
US11989083B2 (en) | Method and device for determining at least one machine involved in an anomaly detected in a complex computing infrastructure | |
CN113672600B (en) | Abnormality detection method and system | |
CN114564853B (en) | Evaluation report generation method based on FMEA data and electronic equipment | |
US11886453B2 (en) | Quantization of data streams of instrumented software and handling of delayed or late data |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210810 |