CN112509292A - Fault prediction method, device, electronic equipment and computer readable storage medium - Google Patents

Fault prediction method, device, electronic equipment and computer readable storage medium Download PDF

Info

Publication number
CN112509292A
CN112509292A CN202011483059.2A CN202011483059A CN112509292A CN 112509292 A CN112509292 A CN 112509292A CN 202011483059 A CN202011483059 A CN 202011483059A CN 112509292 A CN112509292 A CN 112509292A
Authority
CN
China
Prior art keywords
value
time
sensor
preset
predicted
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
Application number
CN202011483059.2A
Other languages
Chinese (zh)
Other versions
CN112509292B (en
Inventor
杨庆飞
邹仕洪
张广伟
周宏斌
黄浩东
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yuanxin Information Technology Group Co ltd
Original Assignee
Beijing Yuanxin Science and Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Yuanxin Science and Technology Co Ltd filed Critical Beijing Yuanxin Science and Technology Co Ltd
Priority to CN202011483059.2A priority Critical patent/CN112509292B/en
Publication of CN112509292A publication Critical patent/CN112509292A/en
Application granted granted Critical
Publication of CN112509292B publication Critical patent/CN112509292B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18—Status alarms
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The embodiment of the application provides a fault prediction method and device, electronic equipment and a computer readable storage medium, and relates to the field of fault prediction. The method comprises the following steps: acquiring a detection value of a preset attribute of each sensor to the machine in a plurality of sensors within a first detection time preset before the current time; for each sensor, predicting a first predicted value of the sensor at a first predicted time after the current time according to the detection value, a weight value preset by the sensor and an exponential smoothing prediction method; and for each sensor, if the first predicted value of the sensor is greater than a preset first alarm threshold value, generating first prompt information for prompting that the machine is about to fail after the first predicted time, and outputting the first prompt information. According to the embodiment of the application, the accuracy of fault prediction is improved, and prompt can be performed before the machine fails.

Description

Fault prediction method, device, electronic equipment and computer readable storage medium
Technical Field
The present application relates to the field of failure prediction technologies, and in particular, to a failure prediction method, an apparatus, an electronic device, and a computer-readable storage medium.
Background
With the development of technology, various machines and devices are used in industries such as automated production, power generation, transportation, and the like. Machines are typically capable of operating normally for extended periods of time, such as months. And after the machine runs for a long time, the machine is easy to break down, and if the machine breaks down, the use of the machine is greatly influenced, and even the machine is damaged.
In the existing scheme, the fault of the machine can be predicted, but the accuracy of the fault prediction is not high, and misleading can be caused to a user, so how to improve the accuracy of the fault prediction becomes the requirement of the prior art.
Disclosure of Invention
The purpose of the present application is to solve at least one of the above technical drawbacks, and to provide the following solutions:
in a first aspect, a method for fault prediction is provided, where the method includes:
acquiring a detection value of a preset attribute of each sensor to the machine in a plurality of sensors within a first detection time preset before the current time;
for each sensor, predicting a first predicted value of the sensor at a first predicted time after the current time according to the detection value, a weight value preset by the sensor and an exponential smoothing prediction method;
and for each sensor, if the first predicted value of the sensor is greater than a preset first alarm threshold value, generating first prompt information for prompting that the machine is about to fail after the first predicted time, and outputting the first prompt information.
In a second aspect, an apparatus for fault prediction is provided, the apparatus comprising:
the acquisition module is used for acquiring the detection value of the preset attribute of each sensor of the plurality of sensors to the machine within the preset first detection time before the current time;
the first prediction module is used for predicting a first prediction value of the sensor at a first prediction time after the current time according to the detection value, a weight value preset by the sensor and an exponential smoothing prediction method for each sensor;
and the first prompting module is used for generating first prompting information for prompting that the machine is about to fail after the first prediction time if the first predicted value of each sensor is greater than a preset first alarm threshold value, and outputting the first prompting information.
In a third aspect, an electronic device is provided, which includes:
one or more processors;
a memory;
one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: the method of fault prediction according to the first aspect of the present application is performed.
In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor, implements the failure prediction method shown in the first aspect of the present application.
The beneficial effect that technical scheme that this application provided brought is: after the detection value of the preset attribute of each sensor to the machine is obtained, the first prediction value of the first prediction time sensor after the current time can be predicted according to the detection value, the weight value preset by the sensor and the index smooth prediction method, if the first prediction value of the sensor is larger than a preset first alarm threshold value, first prompt information used for prompting that the machine is about to break down after the first prediction time is generated, the first prompt information is output, the generated first prediction value is accurate, the failure prediction accuracy is improved, prompt can be performed before the machine breaks down, a user can intervene before the machine breaks down, the frequency of machine breaking down is reduced, and damage of the machine to the machine due to the machine breaking down is reduced.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.
Fig. 1 is a schematic application environment diagram of a failure prediction method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a fault prediction method according to an embodiment of the present application;
FIG. 3 is a detailed flowchart of step S202 in FIG. 2;
fig. 4 is a schematic flow chart of a fault prediction method according to an embodiment of the present application;
fig. 5 is a schematic flow chart of a fault prediction method according to an embodiment of the present application;
fig. 6 is a schematic diagram illustrating an electronic device applied to a fault prediction method according to an embodiment of the present application displaying a first predicted value, a first alarm threshold, and a second alarm threshold;
fig. 7 is a schematic structural diagram of a failure prediction apparatus according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device for failure prediction according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The present application provides a failure prediction method, apparatus, electronic device and computer-readable storage medium, which are intended to solve the above technical problems in the prior art.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
The failure prediction method provided by the application can be applied to an application environment as shown in fig. 1 and is used for predicting the failure of the machine 101. Specifically, the electronic device 102 is in communication connection with a sensor on the terminal, and the electronic device 102 acquires a detection value of a preset attribute of the machine 101 by each sensor of a plurality of sensors within a first detection time preset before the current time; for each sensor, predicting a first predicted value of a first predicted time sensor after the current time according to a detection value, a weight value preset by the sensor and an exponential smoothing prediction method; for each sensor, if the first predicted value of the sensor is greater than a preset first alarm threshold value, first prompt information for prompting that the machine 101 will fail after the first predicted time is generated, and the first prompt information is output.
Those skilled in the art will appreciate that the electronic device may comprise a terminal, server, or other electronic device. In the present application, a "terminal" may be a Mobile phone, a tablet computer, a Personal Digital Assistant (PDA), a Mobile Internet Device (MID), or other terminal devices; a "server" may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.
Referring to fig. 2, an embodiment of the present application provides a fault prediction method for predicting a fault of a machine, where the fault prediction method may be applied to the electronic device, and the method includes:
s201: and acquiring a detection value of each sensor of the plurality of sensors on the preset attribute of the machine within a first detection time preset before the current time.
The fault prediction method is used for predicting the fault of the machine. The specific type, use, and the like of the machine are not limited, and the machine may be a rotating machine, a moving machine, or the like, and the machine may be used to generate power, output kinetic energy, or the like. The preset property of the machine is not limited, and the preset property of the machine can be the temperature, the pressure, the rotating speed, the vibration, the displacement and the like of the machine. Each machine may include one or more detection points, and different detection points may detect the same or different preset attributes.
The number and type of the plurality of sensors are not limited, and the plurality of sensors may include at least one sensor or a plurality of sensors. The preset properties of the machine detected by the different sensors may be the same or different. For example, the sensors include sensor A for detecting a temperature value at a first location of the machine, sensor B for detecting a pressure value at a second location of the machine, and sensor C for detecting a temperature value at a third location of the machine.
The length of the first detection time is not limited, and the first time may be 30 days, 25 days, 20 days, 35 days, 40 days, and the like. The first detection time is taken as 30 days as an example in the application to describe, the detection value of the preset attribute of each sensor of the plurality of sensors to the machine in the first detection time preset before the current time is obtained, and the detection value of the preset attribute of each sensor of the plurality of sensors to the machine in 30 days before the current time can be obtained.
The electronic equipment can acquire the detection values of the sensors in real time and store the acquired detection values, and when needed, the electronic equipment can acquire the detection value of the preset attribute of each sensor of the plurality of sensors to the machine within the first detection time preset before the current time. The electronic equipment can also acquire the detection value of the sensor once every preset interval time; the preset interval time is not limited, and for example, the preset interval time may be 5s, 10s, 1min, 2min, or the like. The acquired detection values may be stored in a preset database to read the stored detection values from the database when necessary.
S202: and for each sensor, predicting a first predicted value of a first predicted time sensor after the current time according to the detection value, a preset weight value of the sensor and an exponential smoothing prediction method.
The specific method of the exponential smoothing prediction method is not limited, and specifically, the exponential smoothing prediction method may be a first exponential smoothing method, a second exponential smoothing method, a third exponential smoothing method, or the like. Each exponential smoothing prediction method comprises a preset smoothing coefficient; the smoothing factor determines the level of smoothing and the speed of response to the difference between the predicted and actual results. And for each sensor, predicting a first predicted value of the sensor at a certain time after the current time according to the detection value, a weight value preset by the sensor and an exponential smoothing prediction method.
The specific size of the smoothing coefficient is not limited, and in the present application, the smoothing coefficient is greater than or equal to 0.1, the smoothing coefficient is less than or equal to 1, the smoothing coefficient may also be less than or equal to 0.99, and the smoothing coefficient may be set as needed. The specific size of the weight value preset by the sensor is not limited, and in the application, the weight value is greater than or equal to 0.1 and less than or equal to 1. The length of the first predicted time is not limited, for example, the first predicted time may be 10 days, 7 days, 3 days, 1 day, 12h, 6h, etc. In the present application, the first prediction time is described as 7 days.
Referring to fig. 3, predicting a first predicted value of a first predicted time sensor after a current time according to a detection value, a weight value preset by the sensor, and an exponential smoothing prediction method includes:
s301: and determining the primary exponential smoothing value and the secondary exponential smoothing value at the first computing moment according to the detection value at the first computing moment, the primary exponential smoothing value at the previous computing moment of the first computing moment, the secondary exponential smoothing value at the previous computing moment of the first computing moment and a preset smoothing coefficient, wherein the detection value at the computing moment is the average value of the detection values of each sensor in a preset time segment.
In the embodiment of the application, the exponential smoothing prediction method is a quadratic exponential smoothing method. In the present application, in order to distinguish different calculation times, the different calculation times are divided into a first calculation time, a second calculation time, and the like. The time length of the time segment is not limited, and the time length of the time segment can be 1 day, 0.5 day, 1 hour, the detection period of the acquired detection value, and the like. Specifically, when the time segment is 1 day, the detection value at one calculation time is the average value of the detection values in the corresponding day; if the time segment is 1 hour, the detection value of one calculation moment is the average value of the detection values in the corresponding 1 hour; when the time segment is a detection period, specifically, if one detection period is 10s, that is, the detection value of the sensor is obtained every 10s, the detection value of the time segment is the detection value in the corresponding detection period. It will be appreciated that there is only one detection value in a detection period and that the detection values need not be averaged.
In the embodiment of the present application, the first detection time is 30 days, and the time segment corresponding to the calculation time is 1 day. In the second exponential smoothing method, a first exponential smoothing value and a second exponential smoothing value need to be calculated, a calculation formula of the first exponential smoothing value is (formula 1), and a calculation formula of the second exponential smoothing value is (formula 2), which is specifically as follows:
Figure BDA0002838159540000061
Figure BDA0002838159540000062
wherein S ist (1)Calculating a first exponential smoothing value of the time t, alpha is a smoothing coefficient, xtAs a detected value at the time of the tth calculation,
Figure BDA0002838159540000063
calculating a first exponential smoothing value at the moment for the t-1; st (2)The second order exponentially smoothed value at the time of the tth calculation,
Figure BDA0002838159540000064
a second order exponentially smoothed value at time is calculated for the t-1.
As can be seen from the formula, at the first calculation time, the first exponential smoothing value at the first time needs to be calculated according to the smoothing coefficient, the detection value at the first calculation time, and the first exponential smoothing value at the previous calculation time of the first calculation time; at the first calculation time, it is necessary to calculate a second exponential smoothing value at the first time based on the smoothing coefficient, the first exponential smoothing value at the first time, and the second exponential smoothing value at the previous calculation time from the first calculation time.
If the first detection time is 30 days, and the time segment corresponding to the calculation time is 1 day, the first exponential smoothing value and the second exponential smoothing value of the first day of the 30 days need to be calculated first, and the first exponential smoothing value and the second exponential smoothing value of the second day need to be calculated when needed. It can be understood that, in a first time segment, for example, in a first day of 30 days, at a calculation time corresponding to the time segment, there is no primary exponential smoothing value at a calculation time immediately preceding the calculation time, nor is there a secondary exponential smoothing value at a calculation time immediately preceding the calculation time. In the present application, when the first-order exponential smoothing value at the first calculation time is calculated, if there is no first-order exponential smoothing value at a calculation time immediately preceding the first calculation time, the detection value at the first calculation time is used as the first-order exponential smoothing value at the calculation time immediately preceding the first calculation time; when the second-order exponential smoothing value at the first calculation time is calculated, if the second-order exponential smoothing value at the calculation time immediately preceding the first calculation time does not exist, the detection value at the first calculation time is used as the second-order exponential smoothing value at the calculation time immediately preceding the first calculation time.
S302: and determining a first predicted value at a second calculation time according to the first exponential smoothing value and the second exponential smoothing value at the first calculation time and a weight value preset by the sensor, and taking the second calculation time as a new first calculation time, and if the new first calculation time does not include a detection value, taking the first predicted value at the second calculation time as a new detection value at the first calculation time, wherein the second calculation time is the next calculation time of the first calculation time.
The calculation formula of the quadratic exponential smoothing method is as follows:
xt+1＝at+btxT (formula 3)
at＝2St (1)-St (2)(formula 4)
Figure BDA0002838159540000071
Wherein x ist+1Calculating a first predicted value at the T +1 th moment, wherein T is a weight value preset by the sensor, and atAnd btAs an intermediate parameter, St (1)For the first exponential smoothing value of the time of the tth calculation, St (2)And alpha is a smoothing coefficient.
The weight value preset by the sensor is not limited, and may be determined according to the type of the detected attribute of the sensor, or according to the importance degree of the position of the machine detected by the sensor. The weight value preset by the sensor may also be determined according to other manners, which are not specifically described in this application.
According to a formula, a first predicted value at a second calculation time is determined according to a first exponential smoothing value and a second exponential smoothing value at the first calculation time and a weight value preset by the sensor, and the second calculation time is the next calculation time of the first calculation time.
If the first detection time is 30 days and the time segment corresponding to the calculation time is 1 day, then there may be no case of a detection value when calculating the first predicted value after the current time, for example, when calculating the first predicted value on day 32, that is, when predicting the first predicted value on day 2 after the current time, there is no case of a detection value on day 31, then the first predicted value on day 31 is taken as the detection value on day 31, that is, the second calculation time is taken as a new first calculation time, and if the new first calculation time does not include a detection value, the first predicted value on the second calculation time is taken as a new detection value on the first calculation time.
S303: repeatedly determining a primary exponential smoothing value and a secondary exponential smoothing value at the first computing time according to a detection value at the first computing time, a primary exponential smoothing value at a previous computing time at the first computing time, a secondary exponential smoothing value at a previous computing time at the first computing time and a preset smoothing coefficient, wherein for each sensor, the detection value at the computing time is an average value of the detection values of the sensor in a preset time segment, determining a first predicted value at the second computing time according to the primary exponential smoothing value at the first computing time, the secondary exponential smoothing value and a preset weight value of the sensor, and taking the second computing time as a new first computing time; and if the new first calculation time does not comprise the detection value, taking the first prediction value of the second calculation time as the detection value of the new first calculation time, wherein the second calculation time is the next calculation time of the first calculation time until the first prediction value of the first prediction time sensor after the current time is calculated.
And (3) obtaining a first predicted value of the next calculation time after each execution of the step (S201) and the step (S202), and repeatedly executing the step (S201) and the step (S202) until the first predicted value of the sensor at the first prediction time after the current time is calculated, for example, until the first predicted value of the sensor at the 7 th day after the current time is calculated.
S203: and aiming at each sensor, if the first predicted value of the sensor is greater than a preset first alarm threshold value, generating first prompt information for prompting that the machine is about to fail after the first predicted time, and outputting the first prompt information.
The first alarm threshold is used for prompting when the first predicted value of the sensor is greater than a preset first alarm threshold, and the prompting mode is not limited and can be prompt in the modes of voice, characters and the like. The magnitude of the first alarm threshold is not limited.
The first alarm threshold value can be determined according to the size of a corresponding detection value when the machine fails. It is understood that the first prompt message may also include a location where the machine will fail, a sensor corresponding to the location where the machine will fail, and the like.
According to the fault prediction method provided by the embodiment of the application, after the detection value of the preset attribute of each sensor to the machine is obtained, the first prediction value of the first prediction time sensor after the current time can be predicted according to the detection value, the weight value preset by the sensor and the index smooth prediction method, if the first prediction value of the sensor is larger than the preset first alarm threshold value, the first prompt information used for prompting that the machine is about to fail after the first prediction time is generated, the first prompt information is output, the generated first prediction value is accurate, the fault prediction accuracy is improved, the prompt can be performed before the machine fails, a user can intervene before the machine fails, the frequency of the machine fails is reduced, and the damage of the machine to the machine due to the occurrence of the fault is reduced.
Referring to fig. 4, a possible implementation manner is further provided in the embodiments of the present application, and the method for predicting a fault may further include:
s401: and for each sensor, if the first predicted value of the sensor is greater than a preset first alarm threshold value, predicting a second predicted value of the sensor after the current time according to a detection value of the sensor in a second detection time preset before the current time, a weight value preset by the sensor and an index smooth prediction method, wherein the second detection time is less than the first detection time, and the second prediction time is less than the first prediction time.
The second detection time is less than the first detection time, and the second prediction time is less than the first prediction time. The specific duration of the second detection time is not limited, nor is the specific duration of the second prediction time. If the first detection time is 30 days, the second detection time may be 7 days, if the first prediction time is 7 days, the second prediction time may be 1 day. In the embodiment of the application, namely when a first predicted value of a sensor at a first predicted time after the current time is greater than a preset first alarm threshold value, the machine is possibly in failure at the first predicted time, and prediction is performed according to a detected value of the sensor within a second detection time shorter than the current time to obtain a second predicted value, so that the obtained second predicted value is more accurate. In the present application, the second predicted value of the second predicted time sensor after the current time is predicted is the same as the first predicted value of the first predicted time sensor after the current time is predicted, and a detailed description is not given in the embodiments of the present application. It is to be understood that the time segment of the calculation time used when predicting the second predicted value may be smaller than the time segment of the calculation time used when predicting the first predicted value. Specifically, if the time segment of the calculation time used when predicting the first prediction value is 1 day, the time segment of the calculation time used when predicting the second prediction value may be 1h, so that the obtained second prediction value is more accurate.
S402: and for each sensor, if the second predicted value of the sensor is greater than the preset first alarm threshold value, generating second prompt information for prompting that the machine is about to fail after the second predicted time, and outputting the second prompt information.
The prompting mode of the second prompting message can be the same as or different from the prompting mode of the first prompting message.
According to the embodiment of the application, the output second prompt information is more accurate.
Referring to fig. 5, a possible implementation manner is further provided in the embodiments of the present application, and the method for predicting a fault may further include:
s501: and for each sensor, if the second predicted value of the sensor is greater than a preset first alarm threshold value, predicting the fault time of the sensor with the third predicted value greater than the preset second alarm threshold value according to the detection value of the sensor in a third detection time preset before the current time, the preset weight value of the sensor and an index smoothing prediction method, wherein the third detection time is less than the second detection time, and the second alarm threshold value is greater than the first alarm threshold value.
The third detection time is less than the second detection time. The specific duration of the third detection time is not limited. If the second detection time is 7 days, the third detection time may be 1 day or 1 hour. In the embodiment of the application, when the second predicted value is larger than the preset first alarm threshold value, the machine is possibly in failure at the second predicted time, and the third predicted value is obtained by selecting to predict according to the detection value of the sensor within the third detection time shorter than the current time, so that the obtained third predicted value is more accurate. In the present application, the scheme of predicting the third predicted value of the sensor after the current time is the same as the scheme of predicting the first predicted value and the second predicted value of the sensor after the current time, and a detailed description is not given in the embodiments of the present application. It is to be understood that the time segment of the calculation time used when predicting the third predicted value may be smaller than the time segment of the calculation time used when predicting the second predicted value. Specifically, if the time segment of the calculation time used when predicting the first predicted value is 1h, the time segment of the calculation time used when predicting the third predicted value may be one detection period, so that the obtained third predicted value is more accurate.
In the embodiment of the application, the prediction time needing to be predicted is not determined any more, but the fault time when the third prediction value of the sensor is greater than the preset second alarm threshold value is determined, the third prediction value is calculated backwards in sequence, and if the third prediction value is greater than the second alarm threshold value after the current time is 5h, the machine is possible to be in fault after the current time is 5 h.
S502: and if the fault time is less than or equal to the preset fault threshold time, generating third prompt information for prompting that the machine is about to have a fault, outputting the third prompt information, and/or controlling the machine to stop working.
If the fault time is less than or equal to the preset fault threshold time, which indicates that the machine is close to the time when the fault occurs and the machine is about to fail, third prompt information for prompting that the machine is about to fail can be generated and output. The prompting mode of the third prompting message can be the same as or different from the prompting mode of the first prompting message.
If the failure time is less than or equal to the preset failure threshold time, the machine can be controlled to stop working if necessary in order to prevent the machine from really failing.
S503: and if the machine stops working, acquiring a weighted value corresponding to the updated target sensor and/or acquiring a smoothing coefficient in an exponential smoothing prediction method corresponding to the updated target sensor, wherein the target sensor is a sensor corresponding to a first predicted value smaller than a preset first alarm threshold value.
When the machine stops working, the electronic device may automatically control the machine to stop working, or the user may manually control the machine to stop working. One machine may include a plurality of sensors that detect a preset attribute of the machine, and when the failure time of one sensor is calculated to be less than or equal to a preset failure threshold time according to a detection value of the one sensor, the first prediction values corresponding to the other sensors may be further less than a first alarm threshold, and the sensor corresponding to the first prediction value that is less than the preset first alarm threshold is a target sensor.
If the machine stops working, a user can modify the weight value corresponding to the target sensor and/or the smoothing coefficient in the exponential smoothing prediction method corresponding to the target sensor, and can also automatically set the weight value corresponding to the self-modified target sensor and/or the smoothing coefficient in the exponential smoothing prediction method corresponding to the target sensor, so that the electronic equipment can acquire the weight value corresponding to the updated target sensor and/or the smoothing coefficient in the exponential smoothing prediction method corresponding to the updated target sensor, and the predicted value of the sensor can be predicted more accurately in the following process.
In the application, the updated weight value corresponding to the target sensor is smaller than the weight value before updating, and the updated smooth coefficient corresponding to the target sensor is smaller than the smooth coefficient before updating. If the updated weight value corresponding to the target sensor is smaller than the weight value before updating by 0.1, the updated smoothing coefficient corresponding to the target sensor is smaller than the smoothing coefficient before updating by 0.01.
The embodiment of the present application further provides a possible implementation manner, and the failure prediction method further includes:
and for each sensor, if the first predicted value of the sensor at the first predicted time after the current time is greater than a preset first alarm threshold value, controlling the machine to stop working.
If the first predicted value of the sensor is greater than the preset first alarm threshold value at the first predicted time after the current time, the machine can be controlled to stop working if necessary. It can be understood that the machine can also be controlled to stop working if the second predicted value of the sensor is greater than the preset first alarm threshold value.
The embodiment of the present application further provides a possible implementation manner, where the first prompt information further includes a failure rate of the machine, and before generating the first prompt information for prompting that the machine will fail after the first prediction time and outputting the first prompt information, the method further includes:
and calculating the fault rate of the machine according to the total number of the sensors, the preset weight value of each sensor and the number of the sensors corresponding to the first predicted value larger than the preset first alarm threshold value.
Calculating the failure rate of the machine, which can be calculated according to equation 6:
Figure BDA0002838159540000121
in formula 6, P is the failure rate of the machine, n is the number of sensors corresponding to the first predicted value greater than the preset first alarm threshold, and TnAnd N is the total number of the sensors, wherein the first predicted value is larger than the weight value of the sensor corresponding to the preset first alarm threshold value. As can be seen from equation 6, when the failure rate of the machine is calculated, the weight corresponding to the sensor corresponding to the first predicted value greater than the preset first alarm threshold is used to calculate the failure rate of the machineAnd adding the weight values, and dividing by the total number of the sensors to obtain the fault rate of the machine.
Referring to fig. 6, a possible implementation manner is further provided in the embodiments of the present application, and the method for predicting a fault further includes:
and displaying the first alarm threshold value in a preset coordinate system, and displaying the corresponding relation between the first predicted value and time.
The first alarm threshold value A is displayed in a preset coordinate system, the corresponding relation between the first predicted value C and time is displayed, so that a user can visually see the difference value between the first predicted value C and the first alarm threshold value A, and when the user sees and displays the first alarm threshold value A and the first predicted value C, the user can quickly and visually know whether the detected attribute of the corresponding sensor is about to be abnormal or not so as to determine whether the machine is about to fail or not.
It can be understood that the second alarm threshold B may also be displayed in a preset coordinate system, which is convenient for the user to view the relationship between the predicted value and the second alarm threshold B. It is understood that the second predicted value and the third predicted value may be displayed in a predetermined coordinate system.
Referring to fig. 7, an embodiment of the present application provides a failure prediction apparatus 700, where the failure prediction apparatus 700 may include:
the acquisition module 701 is used for acquiring a detection value of a preset attribute of each sensor of the plurality of sensors to the machine within a first detection time preset before the current time;
a first prediction module 702, configured to predict, for each sensor, a first predicted value of a first predicted time sensor after a current time according to a detection value, a weight value preset by the sensor, and an exponential smoothing prediction method;
the first prompting module 703 is configured to, for each sensor, generate first prompting information for prompting that the machine will fail after a first prediction time if a first predicted value of the sensor is greater than a preset first alarm threshold, and output the first prompting information.
According to the fault prediction device provided by the embodiment of the application, after the detection value of the preset attribute of each sensor to the machine is obtained, the first prediction value of the first prediction time sensor after the current time can be predicted according to the detection value, the weight value preset by the sensor and the index smooth prediction method, if the first prediction value of the sensor is larger than the preset first alarm threshold value, the first prompt information used for prompting that the machine is about to fail after the first prediction time is generated, the first prompt information is output, the generated first prediction value is accurate, the fault prediction accuracy is improved, the prompt can be performed before the machine fails, a user can intervene before the machine fails, the frequency of the machine fails is reduced, and the damage of the machine to the machine due to the occurrence of the fault is reduced.
The failure prediction apparatus 700 may further include:
the second prediction module is used for predicting a second prediction value of the sensor after the current time according to a detection value of the sensor in a second detection time preset before the current time, a weight value preset by the sensor and an index smooth prediction method if a first prediction value of the sensor is greater than a preset first alarm threshold value aiming at each sensor, wherein the second detection time is less than the first detection time, and the second prediction time is less than the first prediction time;
and the second prompting module is used for generating second prompting information for prompting that the machine is about to break down after second prediction time aiming at each sensor if a second predicted value of the sensor is greater than a preset first alarm threshold value, and outputting the second prompting information.
The failure prediction apparatus 700 may further include:
a third prediction module, configured to predict, for each sensor, a failure time when a third predicted value of the sensor is greater than a preset second alarm threshold, where the third predicted value is less than the second detection time, and the second alarm threshold is greater than the first alarm threshold, according to a detection value of the sensor within a third detection time preset before the current time, a weight value preset by the sensor, and an index smoothing prediction method;
the third prompting module is used for generating third prompting information for prompting that the machine is about to fail and outputting the third prompting information and/or controlling the machine to stop working if the failure time is less than or equal to the preset failure threshold time;
and the updating module is used for acquiring a weight value corresponding to the updated target sensor and/or acquiring a smoothing coefficient in an exponential smoothing prediction method corresponding to the updated target sensor if the machine stops working, wherein the target sensor is a sensor corresponding to a first predicted value smaller than a preset first alarm threshold value.
The failure prediction apparatus 700 may further include:
and the stopping module is used for controlling the machine to stop working if a first predicted value of each sensor at a first predicted time after the current time is greater than a preset first alarm threshold value.
The failure prediction apparatus 700 may further include:
and the failure rate calculation module is used for calculating the failure rate of the machine according to the total number of the sensors, the preset weight value of each sensor and the number of the sensors corresponding to the first alarm threshold value of which the first predicted value is greater than the preset first alarm threshold value.
The first prediction module 702 includes;
a smooth value calculation unit, configured to determine a primary exponential smooth value and a secondary exponential smooth value at a first calculation time according to a detection value at the first calculation time, a primary exponential smooth value at a previous calculation time of the first calculation time, a secondary exponential smooth value at a previous calculation time of the first calculation time, and a preset smoothing coefficient, where the detection value at the calculation time is an average value of detection values of each sensor in a preset time segment;
the prediction unit is used for determining a first predicted value at a second calculation time according to a primary exponential smoothing value and a secondary exponential smoothing value at the first calculation time and a weight value preset by the sensor, taking the second calculation time as a new first calculation time, and taking the first predicted value at the second calculation time as a new detection value at the first calculation time if the new first calculation time does not include the detection value, wherein the second calculation time is the next calculation time of the first calculation time;
the repeated execution unit is used for repeatedly executing the determination of the first exponential smoothing value and the second exponential smoothing value at the first calculation time according to the detection value at the first calculation time, the first exponential smoothing value at the previous calculation time at the first calculation time, the second exponential smoothing value at the previous calculation time at the first calculation time and a preset smoothing coefficient, wherein for each sensor, the detection value at the calculation time is the average value of the detection values of the sensor in a preset time segment, the first predicted value at the second calculation time is determined according to the first exponential smoothing value at the first calculation time, the second exponential smoothing value and a weight value preset by the sensor, and the second calculation time is used as a new first calculation time; and if the new first calculation time does not comprise the detection value, taking the first prediction value of the second calculation time as the detection value of the new first calculation time, wherein the second calculation time is the next calculation time of the first calculation time until the first prediction value of the first prediction time sensor after the current time is calculated.
The failure prediction apparatus 700 may further include:
and the display module is used for displaying the first alarm threshold value in a preset coordinate system and displaying the corresponding relation between the first predicted value and time.
Referring to fig. 8, in an alternative embodiment, an electronic device is provided, where the electronic device 8000 includes: a processor 8001 and memory 8003. Processor 8001 is coupled to memory 8003, such as via bus 8002. Optionally, the electronic device 8000 may also include a transceiver 8004. In addition, the transceiver 8004 is not limited to one in practical applications, and the structure of the electronic device 8000 does not limit the embodiment of the present application.
Processor 8001 may be a CPU (Central Processing Unit), general purpose Processor, DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (field programmable Gate Array), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. Processor 8001 may also be a combination that implements computing functionality, e.g., comprising one or more microprocessor combinations, DSP and microprocessor combinations, and so forth.
Bus 8002 may include a path to transfer information between the aforementioned components. The bus 8002 may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 8002 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
The Memory 8003 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical Disc storage, optical Disc storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), a magnetic Disc storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to these.
The memory 8003 is used for storing application program codes for executing the scheme of the present application, and the execution is controlled by the processor 8001. Processor 8001 is used to execute application program code stored in memory 8003 to implement what is shown in the foregoing method embodiments.
Among them, electronic devices include but are not limited to: a terminal and a server.
An embodiment of the present application provides an electronic device, including: a memory and a processor; at least one program stored in the memory for execution by the processor to implement the corresponding aspects of the foregoing method embodiments, compared with the prior art, can implement: after the detection value of the preset attribute of each sensor to the machine is obtained, the first prediction value of the first prediction time sensor after the current time can be predicted according to the detection value, the weight value preset by the sensor and the index smooth prediction method, if the first prediction value of the sensor is larger than a preset first alarm threshold value, first prompt information used for prompting that the machine is about to break down after the first prediction time is generated, the first prompt information is output, the generated first prediction value is accurate, the failure prediction accuracy is improved, prompt can be performed before the machine breaks down, a user can intervene before the machine breaks down, the frequency of machine breaking down is reduced, and damage of the machine to the machine due to the machine breaking down is reduced.
The present application provides a computer-readable storage medium, on which a computer program is stored, which, when running on a computer, enables the computer to execute the corresponding content in the foregoing method embodiments. Compared with the prior art, after the detection value of the preset attribute of each sensor to the machine is obtained, the first prediction value of the first prediction time sensor after the current time can be predicted according to the detection value, the preset weight value of the sensor and the index smooth prediction method, if the first prediction value of the sensor is larger than the preset first alarm threshold value, the first prompt information used for prompting that the machine is about to break down after the first prediction time is generated, the first prompt information is output, the generated first prediction value is accurate, the failure prediction accuracy is improved, the prompt can be performed before the machine breaks down, a user can intervene before the machine breaks down, the frequency of machine breaks down is reduced, and damage of the machine to the machine due to the machine breaking down is reduced.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (10)

1. A method of fault prediction, the method comprising:
acquiring a detection value of a preset attribute of each sensor to the machine in a plurality of sensors within a first detection time preset before the current time;
for each sensor, predicting a first predicted value of the sensor at a first predicted time after the current time according to the detection value, a weight value preset by the sensor and an exponential smoothing prediction method;
and for each sensor, if the first predicted value of the sensor is greater than a preset first alarm threshold value, generating first prompt information for prompting that the machine is about to fail after the first predicted time, and outputting the first prompt information.
2. The fault prediction method of claim 1, further comprising:
for each sensor, if a first predicted value of the sensor is greater than a preset first alarm threshold value, predicting a second predicted value of the sensor at a second predicted time after the current time according to a detection value of the sensor in a second detection time preset before the current time, a weight value preset by the sensor and an index smoothing prediction method, wherein the second detection time is less than the first detection time, and the second predicted time is less than the first predicted time;
and for each sensor, if the second predicted value of the sensor is greater than a preset first alarm threshold value, generating second prompt information for prompting that the machine is about to fail after the second predicted time, and outputting the second prompt information.
3. The fault prediction method of claim 2, further comprising:
for each sensor, if a second predicted value of the sensor is greater than a preset first alarm threshold value, predicting fault time when the third predicted value of the sensor is greater than the preset second alarm threshold value according to a detection value of the sensor in a third detection time preset before the current time, a preset weight value of the sensor and an index smooth prediction method, wherein the third detection time is less than the second detection time, and the second alarm threshold value is greater than the first alarm threshold value;
if the fault time is less than or equal to the preset fault threshold time, generating third prompt information for prompting that the machine is about to have a fault, outputting the third prompt information, and/or controlling the machine to stop working;
and if the machine stops working, acquiring a weighted value corresponding to the updated target sensor and/or acquiring a smoothing coefficient in an exponential smoothing prediction method corresponding to the updated target sensor, wherein the target sensor is a sensor corresponding to a first predicted value smaller than a preset first alarm threshold value.
4. The fault prediction method of claim 1, further comprising:
and for each sensor, if the first predicted value of the sensor at the first predicted time after the current time is greater than a preset first alarm threshold value, controlling the machine to stop working.
5. The method of claim 1, wherein the first prompt further includes a failure rate of the machine, and wherein before generating the first prompt for prompting the machine that the machine is about to fail after the first predicted time and outputting the first prompt, the method further comprises:
and calculating the fault rate of the machine according to the total number of the sensors, the preset weight value of each sensor and the number of the sensors corresponding to the condition that the first predicted value is greater than a preset first alarm threshold value.
6. The failure prediction method according to claim 1, wherein predicting a first predicted value of the sensor at a first predicted time after a current time based on the detection value, a weight value preset in the sensor, and an exponential smoothing prediction method includes:
determining a primary exponential smoothing value and a secondary exponential smoothing value at a first computing time according to the detection value at the first computing time, a primary exponential smoothing value at a previous computing time of the first computing time, a secondary exponential smoothing value at the previous computing time of the first computing time and a preset smoothing coefficient, wherein the detection value at the computing time is an average value of detection values of each sensor in a preset time segment;
determining a first predicted value at a second computing time according to the first exponential smoothing value and the second exponential smoothing value at the first computing time and a weight value preset by the sensor, taking the second computing time as a new first computing time, and taking the first predicted value at the second computing time as a new detected value at the first computing time if the new first computing time does not include the detected value, wherein the second computing time is the next computing time of the first computing time;
repeatedly determining a first exponential smoothing value and a second exponential smoothing value at a first computing time according to the detection value at the first computing time, a first exponential smoothing value at a previous computing time of the first computing time, a second exponential smoothing value at the previous computing time of the first computing time and a preset smoothing coefficient, wherein for each sensor, the detection value at the computing time is an average value of detection values of the sensor in a preset time segment, determining a first predicted value at a second computing time according to the first exponential smoothing value at the first computing time, the second exponential smoothing value and a preset weight value of the sensor, and taking the second computing time as a new first computing time; and if the new first calculation time does not comprise the detection value, taking the first prediction value of the second calculation time as the detection value of the new first calculation time, wherein the second calculation time is the next calculation time of the first calculation time until the first prediction value of the sensor at the first prediction time after the current time is calculated.
7. The fault prediction method of claim 1, further comprising:
and displaying the first alarm threshold value in a preset coordinate system, and displaying the corresponding relation between the first predicted value and time.
8. A failure prediction apparatus, comprising:
the acquisition module is used for acquiring the detection value of the preset attribute of each sensor of the plurality of sensors to the machine within the preset first detection time before the current time;
the first prediction module is used for predicting a first prediction value of the sensor at a first prediction time after the current time according to the detection value, a weight value preset by the sensor and an exponential smoothing prediction method for each sensor;
and the first prompting module is used for generating first prompting information for prompting that the machine is about to fail after the first prediction time if the first predicted value of each sensor is greater than a preset first alarm threshold value, and outputting the first prompting information.
9. An electronic device, comprising:
one or more processors;
a memory;
one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to: performing the fault prediction method according to any one of claims 1 to 7.
10. A computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the failure prediction method of any one of claims 1 to 7.
CN202011483059.2A 2020-12-15 2020-12-15 Fault prediction method, device, electronic equipment and computer readable storage medium Active CN112509292B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011483059.2A CN112509292B (en) 2020-12-15 2020-12-15 Fault prediction method, device, electronic equipment and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011483059.2A CN112509292B (en) 2020-12-15 2020-12-15 Fault prediction method, device, electronic equipment and computer readable storage medium

Publications (2)

Publication Number Publication Date
CN112509292A true CN112509292A (en) 2021-03-16
CN112509292B CN112509292B (en) 2022-04-29

Family

ID=74972352

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011483059.2A Active CN112509292B (en) 2020-12-15 2020-12-15 Fault prediction method, device, electronic equipment and computer readable storage medium

Country Status (1)

Country Link
CN (1) CN112509292B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113807211A (en) * 2021-08-31 2021-12-17 武汉理工大学 Equipment operation state early warning method, computer equipment and storage medium
CN114323146A (en) * 2021-12-31 2022-04-12 苏州苏福马机械有限公司 Method and equipment for diagnosing reliability of sensing system of continuous press
CN116684306A (en) * 2023-06-29 2023-09-01 苏州浪潮智能科技有限公司 Fault prediction method, device, equipment and readable storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103699668A (en) * 2013-12-30 2014-04-02 贵州电力试验研究院 Power distribution network electric equipment combination state evaluation method based on data section consistency
EP3089034A1 (en) * 2015-04-29 2016-11-02 Tata Consultancy Services Limited System and method for optimizing energy consumption by processors
CN108376299A (en) * 2018-02-27 2018-08-07 深圳市智物联网络有限公司 A kind of prediction technique and device of running trend of the equipment
CN110851342A (en) * 2019-11-08 2020-02-28 中国工商银行股份有限公司 Fault prediction method, device, computing equipment and computer readable storage medium
CN112016739A (en) * 2020-08-17 2020-12-01 国网山东省电力公司潍坊供电公司 Fault detection method and device, electronic equipment and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103699668A (en) * 2013-12-30 2014-04-02 贵州电力试验研究院 Power distribution network electric equipment combination state evaluation method based on data section consistency
EP3089034A1 (en) * 2015-04-29 2016-11-02 Tata Consultancy Services Limited System and method for optimizing energy consumption by processors
CN108376299A (en) * 2018-02-27 2018-08-07 深圳市智物联网络有限公司 A kind of prediction technique and device of running trend of the equipment
CN110851342A (en) * 2019-11-08 2020-02-28 中国工商银行股份有限公司 Fault prediction method, device, computing equipment and computer readable storage medium
CN112016739A (en) * 2020-08-17 2020-12-01 国网山东省电力公司潍坊供电公司 Fault detection method and device, electronic equipment and storage medium

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113807211A (en) * 2021-08-31 2021-12-17 武汉理工大学 Equipment operation state early warning method, computer equipment and storage medium
CN114323146A (en) * 2021-12-31 2022-04-12 苏州苏福马机械有限公司 Method and equipment for diagnosing reliability of sensing system of continuous press
CN116684306A (en) * 2023-06-29 2023-09-01 苏州浪潮智能科技有限公司 Fault prediction method, device, equipment and readable storage medium
CN116684306B (en) * 2023-06-29 2023-11-03 苏州浪潮智能科技有限公司 Fault prediction method, device, equipment and readable storage medium

Also Published As

Publication number Publication date
CN112509292B (en) 2022-04-29

Similar Documents

Publication Publication Date Title
CN112509292B (en) Fault prediction method, device, electronic equipment and computer readable storage medium
EP4066180A1 (en) Method and apparatus for detecting fault, method and apparatus for training model, and device and storage medium
EP3795975A1 (en) Abnormality sensing apparatus, abnormality sensing method, and abnormality sensing program
JP6370525B1 (en) Inundation prediction system, prediction method, program
CN114216640A (en) Method, apparatus and medium for detecting fault status of industrial equipment
CN116502166A (en) Prediction method, device, equipment and medium based on other equipment data
CN110866682B (en) Underground cable early warning method and device based on historical data
CN115546628A (en) Hydraulic engineering dam crack monitoring method, device, equipment and medium
CN115858311A (en) Operation and maintenance monitoring method and device, electronic equipment and readable storage medium
CN112380073B (en) Fault position detection method and device and readable storage medium
CN110020264B (en) Method and device for determining invalid hyperlinks
CN114412588B (en) Method for monitoring service life of nuclear turbine under action of rapid starting thermal stress
CN113217826B (en) Pipeline water supply pipe network leakage alarm control method, device and medium
CN116089891A (en) Method and system for diagnosing safety condition of pile foundation structure
CN112346552B (en) Power supply monitoring method, device, computer equipment and storage medium
CN115375039A (en) Industrial equipment fault prediction method and device, electronic equipment and storage medium
EP4254094A1 (en) Data processing apparatus, data processing method, and program
CN111176931A (en) Operation monitoring method, operation monitoring device, server and storage medium
CN114615092B (en) Network attack sequence generation method, device, equipment and storage medium
CN114697203B (en) Network fault pre-judging method and device, electronic equipment and storage medium
CN116308303B (en) Maintenance plan generation method, device, equipment and medium based on equipment data
EP4113236A1 (en) Run-time reliability reporting for electrical hardware systems
CN115585773A (en) Electromagnetic bearing gap detection method, classifier generation method and device
CN116066959A (en) Method and device for training refrigerant leakage probability prediction model, electronic equipment and storage medium
CN117662448A (en) Method, apparatus and medium for detecting operation abnormality of pump

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
TR01 Transfer of patent right

Effective date of registration: 20230428

Address after: Room 401, Floor 4, No. 2, Haidian East Third Street, Haidian District, Beijing 100080

Patentee after: Yuanxin Information Technology Group Co.,Ltd.

Address before: 100080 401-06, 4th floor, 2 Haidian East 3rd Street, Haidian District, Beijing

Patentee before: YUANXIN TECHNOLOGY

TR01 Transfer of patent right