CN117632665A - Running state real-time monitoring method for radiator - Google Patents
Running state real-time monitoring method for radiator Download PDFInfo
- Publication number
- CN117632665A CN117632665A CN202410108664.3A CN202410108664A CN117632665A CN 117632665 A CN117632665 A CN 117632665A CN 202410108664 A CN202410108664 A CN 202410108664A CN 117632665 A CN117632665 A CN 117632665A
- Authority
- CN
- China
- Prior art keywords
- temperature
- radiator
- sampling
- abnormal
- moment
- 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 59
- 238000012544 monitoring process Methods 0.000 title claims abstract description 35
- 238000005070 sampling Methods 0.000 claims abstract description 290
- 230000002159 abnormal effect Effects 0.000 claims abstract description 175
- 230000005856 abnormality Effects 0.000 claims abstract description 113
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 11
- 238000001514 detection method Methods 0.000 abstract description 8
- 238000004458 analytical method Methods 0.000 description 5
- 238000013459 approach Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3089—Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of data anomaly detection, in particular to a method for monitoring the running state of a radiator in real time, which comprises the steps of firstly obtaining the temperature and the wind speed of the radiator in the running process of the radiator of a computer; obtaining the temperature abnormality degree according to the fluctuation change condition of the temperature of the radiator in time sequence; combining the temperature abnormality degree, and obtaining abnormal change possibility according to the relevance of the temperature of the radiator and the wind speed of the radiator on time sequence; obtaining the abnormal degree of the radiator according to the abnormal degree and the abnormal change possibility of the temperature of each k neighbor radiator at each sampling moment; the obtained abnormal degree of the radiator is more accurate, and the effect of monitoring the running state of the radiator according to the abnormal degree of the radiator at all sampling moments is better.
Description
Technical Field
The invention relates to the technical field of data anomaly detection, in particular to a method for monitoring the running state of a radiator in real time.
Background
The radiator is a device for timely transferring heat of a heat source to the external environment, is widely applied to the fields of industry, automobiles, electronic equipment and the like, and is used for transferring heat of a computer CPU, absorbing the heat generated by the CPU through the radiator and transferring the heat so as to prevent the CPU from being too high in temperature, ensure the running efficiency of the CPU and ensure the running efficiency of the CPU. Therefore, when the operation state of the radiator is abnormal, the operation efficiency of the CPU is affected, the condition that the CPU is damaged due to the fact that the operation temperature of the CPU is too high is possibly caused, and even potential safety hazards are caused, so that the real-time monitoring of the operation state of the radiator is very important.
When the running state of the radiator is abnormal, the temperature of the radiator can be increased, so that the temperature data of the radiator in time sequence is normally detected abnormally by a k-nearest neighbor algorithm in the prior art, and the running state of the radiator is monitored according to the detected abnormal temperature data of the radiator. However, the principle of anomaly detection by the k-nearest neighbor algorithm is that the anomaly condition of data is determined according to the distance difference of different radiator temperatures in a temperature space, the time correlation and the data amplitude change of the anomaly radiator data are ignored, when the running state of the radiator is abnormal, the situation that the temperatures of the anomaly operation are large and relatively close to each other possibly occurs, the difference between the temperature data of the anomaly radiator is small, the anomaly detection capability of the k-nearest neighbor algorithm on the temperature data of the radiator is poor, and the anomaly degree of the radiator for measuring the temperature of each radiator is small, so that the effect of monitoring the running state of the radiator according to the anomaly degree of the radiator is poor; namely, the effect of the abnormal degree of the radiator obtained by directly carrying out abnormal detection on the temperature data of the radiator through the k nearest neighbor algorithm in the prior art on the operation state monitoring of the radiator is poor.
Disclosure of Invention
In order to solve the technical problem that the effect of the abnormal degree of the radiator obtained by directly detecting the abnormal temperature data of the radiator through the k nearest neighbor algorithm in the prior art on the operation state monitoring of the radiator is poor, the invention aims to provide a real-time operation state monitoring method of the radiator, which adopts the following technical scheme:
the invention provides a method for monitoring the running state of a radiator in real time, which comprises the following steps:
acquiring the temperature and the wind speed of a radiator at each sampling time in the operation process of the computer radiator;
obtaining the temperature abnormality degree of each sampling moment according to the temperature change fluctuation condition of the radiator at each sampling moment in the time sequence neighborhood window of each sampling moment; obtaining abnormal change possibility of each sampling time according to the relevance between the radiator temperature and the radiator wind speed at all sampling times in the time sequence neighborhood window of each sampling time and the fluctuation change condition of the corresponding temperature abnormality degree;
in the temperature data of all sampling moments, the temperature abnormality degree and abnormal change possibility deviation of each k neighbor radiator temperature of the radiator temperature of each sampling moment are corresponding to the sampling moment, and the radiator abnormality degree of each sampling moment is obtained according to the radiator temperature and the radiator wind speed deviation distribution condition;
And monitoring the running state of the radiator according to the abnormal degrees of the radiator at all sampling moments.
Further, the method for acquiring the temperature abnormality degree comprises the following steps:
in time sequence, taking the difference between the radiator temperature at each sampling moment and the radiator temperature at the next sampling moment as the temperature change value at each sampling moment;
taking each sampling moment as a target sampling moment in sequence; in time sequence, taking all sampling moments in a preset neighborhood window of the target sampling moment as neighborhood window moments of the target sampling moment;
in time sequence, taking the difference between the temperature change value of the target sampling moment and the average value of the temperature change values of all corresponding neighborhood window moments as the neighborhood temperature change deviation of the target sampling moment;
the radiator temperatures at all neighborhood window moments are arranged in time sequence at corresponding moments, and then least square fitting is carried out to obtain fitting temperatures at each neighborhood window moment; obtaining the neighborhood temperature variation amplitude of the target sampling moment according to the deviation distribution situation between the radiator temperature at all the neighborhood window moments and the corresponding fitting temperature and the radiator temperature difference between the target sampling moment and the rest neighborhood window moments;
And obtaining the temperature abnormality degree of the target sampling moment according to the radiator temperature, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude of the target sampling moment, wherein the radiator temperature, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude of the target sampling moment are in positive correlation with the temperature abnormality degree.
Further, the method for acquiring the abnormal change possibility comprises the following steps:
in time sequence, taking the ratio of the mean value of the temperature abnormality degrees of all neighborhood window moments corresponding to each sampling moment to the variance of the temperature abnormality degrees of all neighborhood window moments as the reference abnormality possibility of each sampling moment;
in time sequence, delaying a first preset temperature change before each sampling time by a parameter number of sampling times to serve as a temperature delay time of each sampling time;
in time sequence, taking the pearson correlation coefficient between the radiator temperature at all neighborhood window moments and the radiator wind speed at all neighborhood window moments of each sampling moment as the pre-delay correlation degree of each sampling moment; taking the Pearson correlation coefficient between the radiator temperatures at all neighborhood window moments of each sampling moment and the radiator wind speeds at all temperature delay moments corresponding to all neighborhood window moments as the post-delay correlation degree of each sampling moment; taking a positive correlation mapping value of a difference value between the pre-delay association degree and the post-delay association degree as an association abnormality possibility of each sampling moment;
And obtaining the abnormal change probability of each sampling time according to the reference abnormal probability and the associated abnormal probability, wherein the reference abnormal probability and the associated abnormal probability are in positive correlation with the abnormal change probability.
Further, the method for obtaining the abnormal degree of the radiator comprises the following steps:
obtaining all temperature k neighbor moments of each sampling moment through a k neighbor algorithm according to the radiator temperature of all sampling moments;
obtaining an abnormal score weighting weight of each temperature k neighbor moment corresponding to each sampling moment according to the time interval and the abnormal change possibility difference between each sampling moment and each temperature k neighbor moment corresponding to each sampling moment and the temperature abnormality degree and the abnormal change possibility of each temperature k neighbor moment;
according to the abnormal score weighting weights of all k adjacent moments corresponding to each sampling moment, combining the radiator temperature difference and the radiator wind speed difference between each sampling moment and each k adjacent moment to construct a radiator abnormal degree calculation model; and obtaining the abnormal degree of the radiator at each sampling moment according to the abnormal degree calculation model of the radiator.
Further, the method for monitoring the running state of the radiator according to the abnormal degrees of the radiator at all sampling moments comprises the following steps:
calculating the mean value of the abnormal degree of the radiator at all sampling moments, and taking the sampling moment with the abnormal degree of the radiator larger than the mean value of the abnormal degree of the radiator as the abnormal sampling moment; in all neighborhood window moments of each sampling moment, when the number of abnormal sampling moments is larger than a preset abnormal threshold value, the running state of the radiator at the corresponding sampling moment is abnormal; when the number of abnormal sampling moments is smaller than or equal to a preset abnormal threshold value, the radiator is in a normal running state at the corresponding sampling moment.
Further, the method for obtaining the neighborhood temperature variation amplitude comprises the following steps:
taking the difference between the radiator temperature at each neighborhood window moment and the corresponding fitting temperature as the temperature residual error at each neighborhood window moment; taking the difference between the radiator temperature at each neighborhood window time and the radiator temperature at the corresponding target sampling time as the neighborhood temperature difference at each neighborhood window time; taking the sum value between the temperature residual error and the neighborhood temperature difference as the local temperature deviation of each neighborhood window moment; and taking the sum of the local temperature deviations at all the neighborhood window moments as the neighborhood temperature deviation at the target sampling moment.
Further, the method for obtaining the temperature anomaly degree at the target sampling time according to the radiator temperature at the target sampling time, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude comprises the following steps:
and taking the product among the radiator temperature, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude at the target sampling moment as the temperature abnormality degree at the target sampling moment.
Further, the method for obtaining the abnormal change probability of each sampling moment according to the reference abnormal probability and the associated abnormal probability comprises the following steps:
and taking the product of the reference abnormal probability and the associated abnormal probability as the abnormal change probability of each sampling moment.
Further, the calculation formula of the anomaly score weighting weight includes:
wherein,is->The corresponding +.>Abnormal score weighting weights at adjacent moments of the temperatures k; />Is->The corresponding +.>Temperature anomaly degree at adjacent moment of each temperature k; />Is->The corresponding +.>Abnormal change probability at adjacent moment of each temperature k; />Is->The sample times correspond to the +. >The time interval between adjacent moments of the temperature k; />Is->Abnormal change probability at each sampling time.
Further, the construction method of the radiator abnormality degree calculation model comprises the following steps:
wherein,is->Radiator abnormality degree at each sampling time, +.>Is->K-nearest neighbor time number of sampling times, +.>Is->The corresponding +.>Abnormality score weighting weight for each temperature k nearest neighbor time,/->Is->The corresponding +.>Radiator temperature at a moment of adjacent temperature k; />Is->Radiator temperatures corresponding to the sampling moments; />Is the firstThe corresponding +.>Radiator wind speed at a moment of adjacent temperature k; />Is->Radiator wind speeds corresponding to the sampling moments; />Is a normalization function.
The invention has the following beneficial effects:
when the running state of the radiator is abnormal, the situation that the temperature is larger and is relatively close during abnormal working can occur, so that the effect of detecting the abnormality of the radiator by a k-nearest neighbor algorithm for determining data abnormality only based on the difference of the distance between the temperature of the radiator and the temperature space is poor, further analysis is needed according to the characteristics of abnormal radiator data, and the abnormality degree of the radiator at each sampling moment obtained through detection is more accurate. The abnormal condition of the radiator is more likely to occur when the temperature fluctuation which occurs in a short time is more severe for the radiator, so that the temperature abnormality degree is obtained through the temperature fluctuation condition of the radiator in a time sequence neighborhood window at each sampling time, and the abnormal condition of the radiator on the temperature change is primarily reflected through the temperature abnormality degree.
However, it is also required to consider that the temperature fluctuation variation of the radiator may be caused by the increase of the operating power of the computer, so that more heat is generated, and the temperature of the radiator is increased, corresponding to the normal temperature variation; at this time, the radiator can increase the rotation speed to generate larger wind speed to reduce the temperature, so that under normal conditions, the wind speed generated by the radiator can be increased along with the increase of the temperature, and the wind speed and the temperature of the corresponding radiator have certain relevance in time sequence; however, when the radiator is abnormal, the wind speed of the radiator is not changed along with the change of the temperature, namely the correlation between the corresponding wind speed and the temperature is poor; on the basis of the temperature anomaly degree, the method combines the relativity between the radiator temperature and the radiator wind speed at all sampling moments in a time sequence neighborhood window to obtain the anomaly change possibility; that is, the worse the correlation between wind speed and temperature, the greater the degree of temperature abnormality in the time sequence neighborhood window, the more likely the radiator abnormality will occur.
Because the temperature is bigger and closer when the running state of the radiator is abnormal, if the temperature abnormality degree and the abnormality change possibility are combined, the distance calculation in the k-nearest neighbor algorithm is influenced, the weight of the k-nearest neighbor radiator with higher temperature abnormality degree and abnormality change possibility corresponding to the sampling moment is improved, the problem that the temperature is closer when the radiator is abnormal, the effect of the k-nearest neighbor algorithm on abnormal detection of the temperature data of the radiator is worse can be avoided, the obtained abnormal degree of the radiator is more accurate, and the effect of monitoring the running state of the radiator according to the abnormal degree of the radiator at all the sampling moments is better.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for monitoring an operation state of a radiator in real time according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following description refers to the specific implementation, structure, characteristics and effects of a method for monitoring the operation state of a radiator according to the present invention in real time with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the method for monitoring the running state of the radiator in real time.
Referring to fig. 1, a flowchart of a method for monitoring an operation state of a radiator in real time according to an embodiment of the invention is shown, where the method includes:
step S1: and acquiring the temperature and the wind speed of the radiator at each sampling time in the operation process of the computer radiator.
The embodiment of the invention aims to provide a method for monitoring the running state of a radiator in real time, which is used for analyzing according to the change condition of the temperature of the radiator in time sequence and the association condition of the temperature of the radiator and the wind speed of the radiator to obtain the abnormal degree of the radiator at each sampling moment and detecting the running state of the radiator according to the abnormal degree of the radiator at all sampling moments. It is therefore first necessary to obtain the radiator temperature and the radiator wind speed at each sampling instant during the operation of the computer radiator.
In the embodiment of the invention, the temperature sensor is arranged on the surface of the radiator to collect the temperature of the radiator corresponding to each sampling time, the rotation speed of the radiator fan is collected to obtain the wind speed data of the radiator, the rotation speed of the radiator fan can be directly displayed on a computer through a software means, an operator can also collect the rotation speed of the fan through the rotation speed sensor arranged on the surface of the fan to obtain the wind speed data of the radiator, and the operator can also collect the temperature of the radiator and the wind speed of the radiator through other methods according to the specific implementation environment, and further description is omitted herein. Further, the embodiment of the invention sets the sampling frequency to be acquired once per second, namely the time interval between adjacent sampling moments is 1 second, and the air speed and the temperature of the radiator are acquired once at each sampling moment; in order to facilitate analysis, the embodiment of the invention sets the sampling time period to be 30 minutes before the current time, namely all the sampling times corresponding to the follow-up time are all sampling times within 30 minutes; the implementer can set the sampling frequency and the length of the sampling time period according to the specific implementation environment, and no further description is given here. It should be noted that, the computer radiator is provided with a CPU radiator and a GPU radiator, and the corresponding analysis methods are the same.
Step S2: obtaining the temperature abnormality degree of each sampling moment according to the temperature change fluctuation condition of the radiator at each sampling moment in the time sequence neighborhood window of each sampling moment; and obtaining the abnormal change possibility of each sampling time according to the relevance between the radiator temperature and the radiator wind speed at all sampling times in the time sequence neighborhood window of each sampling time and the fluctuation change condition of the corresponding temperature abnormality degree.
The heat radiator is abnormal, which is usually caused by overhigh temperature, when the heat radiator cannot transfer heat effectively, the equipment temperature can rise to exceed the normal temperature bearing range of each part of the heat radiator, so that the heat radiator is abnormal, and therefore, for the heat radiator, when the temperature fluctuation in a short time is more severe, the heat radiator is more likely to be abnormal, and the embodiment of the invention obtains the temperature abnormality degree of each sampling moment according to the temperature variation fluctuation condition of the heat radiator at each sampling moment in a time sequence neighborhood window of each sampling moment.
Preferably, the method for acquiring the temperature abnormality degree includes:
in time sequence, the difference between the radiator temperature at each sampling moment and the radiator temperature at the next sampling moment is taken as a temperature change value at each sampling moment, the temperature change value can reflect the corresponding temperature change at each sampling moment and reflect the change amplitude of the temperature at the corresponding moment, but the temperature abnormality of the radiator is violent fluctuation in a short time, so that the abnormal condition of the radiator cannot be accurately represented by the instantaneous change only, and the radiator temperature in the adjacent time is required to be combined for analysis, and therefore, the embodiment of the invention takes each sampling moment as the target sampling moment in sequence; in time sequence, all sampling moments in a preset neighborhood window of the target sampling moment are used as neighborhood window moments of the target sampling moment, in the embodiment of the invention, the preset neighborhood window is set to be 20 sampling moments before and after the target sampling moment is taken as a center, namely, in the preset neighborhood window, 10 sampling moments are corresponding to the front of the target sampling moment, 10 sampling moments are corresponding to the rear of the target sampling moment, and an implementer can automatically adjust the size of the preset neighborhood window according to specific implementation environments and will not be further described herein.
And taking the difference between the temperature change value of the target sampling moment and the average value of the temperature change values of all corresponding neighborhood window moments as the neighborhood temperature change deviation of the target sampling moment in time sequence. And the average value of the temperature change values at all the neighborhood window moments represents the overall temperature change condition of the radiator temperature corresponding to the target sampling moment in the neighborhood time range, and when the temperature change value at the target sampling moment is larger than the temperature change average condition difference, the degree of abnormality occurrence of the temperature at the corresponding moment is larger, namely, the temperature abnormality degree is larger when the neighborhood temperature change deviation is larger.
The radiator temperatures at all neighborhood window moments are arranged in time sequence at corresponding moments, and then least square fitting is carried out to obtain fitting temperatures at each neighborhood window moment; the fitting temperature can represent the temperature change trend in a preset neighborhood window to a certain extent, and the larger the deviation between the radiator temperature and the fitting temperature is, the larger the difference between the radiator temperature and the overall trend of the temperature is, the more abnormality is likely to occur; in addition, under the condition that the radiator normally operates, the temperature of the radiator is kept stable, and the difference between the temperature of each sampling time and the temperature of the adjacent sampling time is small, so that when the difference between the temperature of the target sampling time and the temperature of each corresponding neighborhood window time is larger, the abnormal temperature of the target sampling time is indicated; therefore, the embodiment of the invention obtains the neighborhood temperature change amplitude of the target sampling moment according to the deviation distribution situation between the radiator temperature at all the neighborhood window moments and the corresponding fitting temperature and the radiator temperature difference between the target sampling moment and the rest neighborhood window moments.
Preferably, the method for acquiring the neighborhood temperature variation amplitude includes:
taking the difference between the radiator temperature at each neighborhood window time and the corresponding fitting temperature as the temperature residual error at each neighborhood window time, wherein the larger the temperature residual error is, the larger the difference between the radiator temperature at the corresponding neighborhood window time and the temperature change trend is, the more abnormal the corresponding neighborhood window time is locally; taking the difference between the radiator temperature at each neighborhood window time and the radiator temperature at the corresponding target sampling time as the neighborhood temperature difference at each neighborhood window time, wherein the larger the corresponding neighborhood temperature difference is, the larger the difference between the target sampling time and the neighborhood window time is, namely the more obvious temperature instability change condition exists between the target sampling time and the neighborhood window time; further taking the sum value between the temperature residual error and the neighborhood temperature difference as the local temperature deviation of each neighborhood window moment; and taking the sum of the local temperature deviations of all the neighborhood window moments as the neighborhood temperature deviation of the target sampling moment, so that the larger the difference between the overall temperature and the temperature change trend of each neighborhood window moment of the target sampling moment is, the larger the corresponding neighborhood temperature deviation is, namely the more likely the radiator abnormality is generated.
The higher the temperature of the radiator is, the more likely to be abnormal, so that the temperature abnormality degree of the target sampling moment is obtained further according to the temperature of the radiator, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude at the target sampling moment, and the temperature of the radiator, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude at the target sampling moment are in positive correlation with the temperature abnormality degree.
Preferably, the method for obtaining the temperature anomaly degree at the target sampling moment according to the radiator temperature, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude at the target sampling moment comprises the following steps:
the larger the radiator temperature is, the larger the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude are, the more the radiator is likely to have temperature abnormality, so that the product among the radiator temperature, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude at the target sampling moment is taken as the temperature abnormality degree at the target sampling moment. It should be noted that, the practitioner may also obtain the temperature abnormality degree by other methods than the product, for example, the sum of the radiator temperature, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude is used as the temperature abnormality degree, which is not further described herein.
In the embodiment of the invention, each sampling time is taken as the first sampling time in sequenceThe sampling time is->The method for acquiring the temperature abnormality degree at each sampling time comprises the following steps:
wherein,is->Temperature abnormality degree at each sampling time, +.>Is->Radiator temperature at each sampling instant, +.>Is->The number of neighborhood window moments corresponding to the sampling moments, < >>Is->The corresponding +.>Radiator temperature at each neighborhood window instant; />Is->The corresponding +.>Fitting temperatures at the moments of the neighborhood windows; />Is->Temperature change values at each sampling instant; />Is->The average value of the temperature change values of all neighborhood window moments corresponding to the sampling moments; />Is an absolute value symbol; />Is->The corresponding +.>Temperature residual at the moment of the individual neighborhood window, +.>Is->The corresponding +.>Neighborhood temperature differences at each neighborhood window time; />Is->The corresponding +.>Local temperature deviation of the moments of the individual neighborhood windows +.>Is->Neighborhood temperature deviation corresponding to each sampling moment; />Is->Neighborhood temperature variation amplitude corresponding to each sampling moment.
However, it is also required to consider that the temperature fluctuation variation of the radiator may be caused by the increase of the operating power of the computer, so that more heat is generated, and the temperature of the radiator is increased, corresponding to the normal temperature variation; at this time, the radiator can increase the rotation speed to generate larger wind speed to reduce the temperature, so that under normal conditions, the wind speed generated by the radiator can be increased along with the increase of the temperature, and the wind speed and the temperature of the corresponding radiator have certain relevance in time sequence; however, when the radiator is abnormal, the wind speed of the radiator is not changed along with the change of the temperature, namely the correlation between the corresponding wind speed and the temperature is poor; therefore, the method and the device analyze the relevance between the radiator temperature and the radiator wind speed at all sampling moments in the time sequence neighborhood window on the basis of the temperature abnormality degree, and the embodiment of the invention obtains the abnormality change possibility of each sampling moment according to the relevance between the radiator temperature and the radiator wind speed at all sampling moments in the time sequence neighborhood window at each sampling moment and the fluctuation change condition of the corresponding temperature abnormality degree.
Preferably, the method for acquiring the possibility of abnormal change includes:
and taking the ratio of the mean value of the temperature abnormality degrees of all the neighborhood window moments corresponding to each sampling moment to the variance of the temperature abnormality degrees of all the neighborhood window moments as the reference abnormality possibility of each sampling moment in time sequence. For each sampling instant, the greater the degree of temperature anomaly, the greater the likelihood of an anomaly change; in order to avoid the influence of accidental factors, if the temperature anomaly degree of the neighborhood window moment corresponding to the sampling moment is large, the possibility of corresponding anomaly change is larger, so that the average value of the corresponding temperature anomaly degree is taken as a molecule. The smaller the variance of the temperature abnormality degree at all the neighborhood window moments, the more stable the temperature abnormality degree at the corresponding neighborhood window moment is maintained, and the larger the average value of the temperature abnormality degree is, the smaller the variance is, the larger the whole temperature abnormality degree at the neighborhood window moment at the sampling moment is, namely the greater the possibility of abnormality is. The greater the reference abnormality probability, the greater the abnormality change probability.
Further, considering the time sequence correlation between the wind speed and the temperature, delaying the first preset temperature change before each sampling time by a parameter number of sampling times in time sequence to serve as the temperature delay time of each sampling time. In the embodiment of the invention, the preset temperature change delay parameter is set to be 5, that is, the wind speed and the temperature change delay are 5 seconds, and the implementer needs to adjust according to the specific implementation environment. And taking the pearson correlation coefficient between the radiator temperature at all neighborhood window moments and the radiator wind speed at all neighborhood window moments of each sampling moment as the pre-delay correlation degree of each sampling moment in time sequence. Namely, pearson correlation coefficients between data sequences corresponding to radiator temperatures corresponding to all neighborhood window moments and data sequences corresponding to radiator wind speeds corresponding to all neighborhood window moments. And taking the Pearson correlation coefficient between the radiator temperatures at all neighborhood window moments of each sampling moment and the radiator wind speeds at all temperature delay moments corresponding to all neighborhood window moments as the post-delay correlation degree of each sampling moment. Namely, pearson correlation coefficients between data sequences corresponding to the radiator temperatures at all neighborhood window moments and data sequences corresponding to the radiator wind speeds at all temperature delay moments at all neighborhood window moments.
And taking the positive correlation mapping value of the difference between the pre-delay correlation degree and the post-delay correlation degree as the correlation abnormality possibility of each sampling moment. After time is delayed, the relevance of the change of the wind speed and the change of the temperature should be larger under normal conditions, if the wind speed and the temperature are smaller than those before delay, the possibility of occurrence of abnormality is larger, so that the relevance degree before delay and the relevance degree after delay are poor, and the corresponding relevance abnormality possibility is obtained after positive correlation mapping adjustment of a value range, and the possibility of occurrence of abnormality is larger when the relevance abnormality possibility is larger.
And further, obtaining the abnormal change probability of each sampling time according to the reference abnormal probability and the associated abnormal probability, wherein the reference abnormal probability and the associated abnormal probability are in positive correlation with the abnormal change probability. Preferably, the method for obtaining the abnormal change probability of each sampling time according to the reference abnormal probability and the associated abnormal probability comprises the following steps:
since the greater the reference abnormality probability, the greater the associated abnormality probability, the greater the possibility of occurrence of an abnormality, the product between the reference abnormality probability and the associated abnormality probability is taken as the abnormality variation probability at each sampling timing.
In an embodiment of the invention, the firstThe method for acquiring the abnormal change possibility of each sampling moment comprises the following steps:
wherein,is->Possibility of abnormal change at each sampling instant, +.>Is->Average value of temperature abnormality degree of all neighborhood window moments corresponding to each sampling moment; />Is->Variance of temperature abnormality degree of all neighborhood window moments corresponding to the sampling moments; />Is->The correlation degree before delay corresponding to each sampling moment; />Is->The post-delay association degrees corresponding to the sampling moments; />Is an exponential function with a base of natural constant.
Step S3: and in the temperature data of all the sampling moments, the abnormal degree and the abnormal change possibility deviation of the temperature of each k neighbor radiator temperature of the radiator temperature of each sampling moment are corresponding to the sampling moment, and the abnormal degree of the radiator of each sampling moment is obtained according to the deviation distribution condition of the radiator temperature and the radiator wind speed.
Because the temperature is larger and is closer to the temperature during abnormal operation when the running state of the radiator is abnormal, if the temperature abnormality degree and the abnormality change possibility are combined, the distance calculation in the k-nearest neighbor algorithm is influenced, the weight of the k-nearest neighbor radiator with larger temperature abnormality degree and abnormality change possibility at the corresponding sampling moment is improved, the problem that the temperature is closer to the temperature during abnormal operation, the effect of the k-nearest neighbor algorithm on abnormal detection of the temperature data of the radiator is worse can be avoided, and the obtained abnormal degree of the radiator is more accurate. Therefore, in the temperature data of all sampling moments, the temperature abnormality degree and abnormal change possibility deviation of each k neighbor radiator temperature of the radiator temperature of each sampling moment are corresponding to the sampling moment, and the radiator abnormality degree of each sampling moment is obtained according to the radiator temperature and the radiator wind speed deviation distribution condition.
Preferably, the method for acquiring the abnormal degree of the radiator comprises the following steps:
and obtaining all temperature k neighbor moments of each sampling moment by a k neighbor algorithm according to the radiator temperature of all sampling moments. Note that the temperature k near moment at each sampling moment is obtained by the corresponding radiator temperature in the temperature space. If the weight of the temperature of the k-nearest neighbor radiator with larger temperature abnormality degree and abnormality change probability is to be improved, the temperature abnormality degree and the abnormality change probability at the temperature k-nearest neighbor moment are required to be combined for weighted analysis; the abnormality of the radiator is reflected by data change in a period of time, so that the temporal proximity degree can be used as a weight to influence the abnormality degree of the radiator at each sampling time in all temperature k adjacent time; similarly, the corresponding degree of closeness of the possibility of abnormal change can also represent the degree of closeness under the same abnormal state to a certain extent; therefore, according to the embodiment of the invention, the abnormal score weighting weight of each temperature k neighbor moment corresponding to each sampling moment is obtained according to the time interval and the abnormal change possibility difference between each sampling moment and each temperature k neighbor moment corresponding to each sampling moment and the temperature abnormality degree and the abnormal change possibility of each temperature k neighbor moment.
Preferably, the calculation formula of the anomaly score weighting weight includes:
wherein,is->The corresponding +.>Abnormal score weighting weights at adjacent moments of the temperatures k; />Is->The corresponding +.>Temperature anomaly degree at adjacent moment of each temperature k; />Is->The corresponding +.>Abnormal change probability at adjacent moment of each temperature k; />Is->The sample times correspond to the +.>The time interval between adjacent moments of the temperature k; />Is->Abnormal change probability at each sampling time. Due to the need to increase the degree of temperature abnormality and the possibility of abnormal changeThe larger k-nearest neighbor radiator temperature corresponds to the weight of the sampling moment, so that the temperature abnormality degree and the abnormal change possibility of each temperature k-nearest neighbor moment are taken as molecules. In addition, since the anomaly of the radiator is reflected by the change of data in a period of time, the closer the time is, the greater the possibility that the radiator between the corresponding temperature k adjacent moment and the corresponding sampling moment is in the same state is, and the greater the corresponding weight is; the smaller the corresponding time interval is, the closer the corresponding time is, so the time interval between the sampling time and the temperature k adjacent time is taken as a denominator; similarly, the abnormal change probability reflects the relevance of the wind speed and the temperature of the radiator on time sequence, so that the smaller the difference between the abnormal change probability is, the more the radiator between the corresponding temperature k adjacent moment and the corresponding sampling moment is in the same state, and the larger the corresponding weight is; the difference between the sampling instant and the instant of the temperature k neighbor is therefore taken as denominator.
After obtaining the abnormal score weighting weight of each temperature k adjacent moment of each sampling moment, further correcting the distance of data between each sampling moment and the corresponding temperature k adjacent moment according to the abnormal score weighting weight; for the data distance, although the temperature k adjacent moment is obtained through the approach degree on the temperature space, under normal conditions, the data of the temperature approach should be relatively close to the corresponding wind speed, so the data distance is measured through the difference of the temperature of the radiator and the difference of the wind speed of the radiator; according to the embodiment of the invention, according to the abnormal score weighting weights of all k adjacent moments corresponding to each sampling moment, a radiator abnormal degree calculation model is constructed by combining the radiator temperature difference and the radiator wind speed difference between each sampling moment and each k adjacent moment; and obtaining the abnormal degree of the radiator at each sampling moment according to the abnormal degree calculation model of the radiator.
Preferably, the method for constructing the radiator abnormality degree calculation model comprises the following steps:
wherein,is->Radiator abnormality degree at each sampling time, +.>Is->K-nearest neighbor time number of sampling times, +.>Is- >The corresponding +.>Abnormality score weighting weight for each temperature k nearest neighbor time,/->Is->The corresponding +.>Radiator temperature at a moment of adjacent temperature k; />Is->Radiator temperatures corresponding to the sampling moments; />Is the firstThe corresponding +.>Radiator wind speed at a moment of adjacent temperature k; />Is->Radiator wind speeds corresponding to the sampling moments; />Is a normalization function. According to the embodiment of the invention, the data distance is measured through the temperature difference of the radiator and the wind speed difference of the radiator, so that the data distance is measured through +.>Characterization of the radiator temperature difference by +.>Characterizing the difference of wind speeds of the radiators, and characterizing the corresponding data distance after combination; the practitioner can also go through other methods, such as +.>Characterizing the data distance; the distance of the data between each sampling time and the corresponding temperature k adjacent time is required to be corrected through the abnormal score weighting weight, so that the distance of the data is weighted through the normalized abnormal score weighting weight, and the weighted distance of each temperature k adjacent time at each sampling time is obtained; further combining with the principle of a k-nearest neighbor algorithm, the abnormal degree of each sampling moment, namely the abnormal degree of the radiator, is represented by the corrected data distance between each sampling moment and each temperature k-nearest neighbor moment.
Step S4: and monitoring the running state of the radiator according to the abnormal degrees of the radiator at all sampling moments.
And after obtaining the abnormal degree of the radiator at each sampling moment, monitoring the running state of the radiator according to the abnormal degree of the radiator at all sampling moments. Preferably, the method for monitoring the running state of the radiator according to the abnormal degree of the radiator at all sampling moments comprises the following steps:
and calculating the mean value of the abnormal degrees of the radiator at all sampling moments, and taking the sampling moment with the abnormal degree of the radiator larger than the mean value of the abnormal degrees of the radiator as the abnormal sampling moment. The larger the abnormality degree of the radiator is, the more likely the radiator is abnormal, so that the sampling time with larger abnormality degree of the radiator can be screened out by taking the average value of the abnormality degrees of the radiator at all sampling times as a threshold value. When the abnormal degree of the radiator is more than the average value, the more likely the radiator is abnormal, so that in all neighborhood window moments of each sampling moment, when the number of abnormal sampling moments is more than a preset abnormal threshold value, the running state of the radiator is abnormal at the corresponding sampling moment; when the number of abnormal sampling moments is smaller than or equal to a preset abnormal threshold value, the radiator is in a normal running state at the corresponding sampling moment. In the embodiment of the invention, the preset abnormal threshold is set to 2, and the implementer can adjust the preset abnormal threshold according to the specific implementation environment.
In summary, the invention firstly obtains the radiator temperature and the radiator wind speed in the running process of the computer radiator; obtaining the temperature abnormality degree according to the fluctuation change condition of the temperature of the radiator in time sequence; combining the temperature abnormality degree, and obtaining abnormal change possibility according to the relevance of the temperature of the radiator and the wind speed of the radiator on time sequence; obtaining the abnormal degree of the radiator according to the abnormal degree and the abnormal change possibility of the temperature of each k neighbor radiator at each sampling moment; the obtained abnormal degree of the radiator is more accurate, and the effect of monitoring the running state of the radiator according to the abnormal degree of the radiator at all sampling moments is better.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. A method for monitoring an operating state of a radiator in real time, the method comprising:
acquiring the temperature and the wind speed of a radiator at each sampling time in the operation process of the computer radiator;
obtaining the temperature abnormality degree of each sampling moment according to the temperature change fluctuation condition of the radiator at each sampling moment in the time sequence neighborhood window of each sampling moment; obtaining abnormal change possibility of each sampling time according to the relevance between the radiator temperature and the radiator wind speed at all sampling times in the time sequence neighborhood window of each sampling time and the fluctuation change condition of the corresponding temperature abnormality degree;
in the temperature data of all sampling moments, the temperature abnormality degree and abnormal change possibility deviation of each k neighbor radiator temperature of the radiator temperature of each sampling moment are corresponding to the sampling moment, and the radiator abnormality degree of each sampling moment is obtained according to the radiator temperature and the radiator wind speed deviation distribution condition;
and monitoring the running state of the radiator according to the abnormal degrees of the radiator at all sampling moments.
2. The method for monitoring the operation state of the radiator in real time according to claim 1, wherein the method for obtaining the temperature abnormality degree comprises the following steps:
In time sequence, taking the difference between the radiator temperature at each sampling moment and the radiator temperature at the next sampling moment as the temperature change value at each sampling moment;
taking each sampling moment as a target sampling moment in sequence; in time sequence, taking all sampling moments in a preset neighborhood window of the target sampling moment as neighborhood window moments of the target sampling moment;
in time sequence, taking the difference between the temperature change value of the target sampling moment and the average value of the temperature change values of all corresponding neighborhood window moments as the neighborhood temperature change deviation of the target sampling moment;
the radiator temperatures at all neighborhood window moments are arranged in time sequence at corresponding moments, and then least square fitting is carried out to obtain fitting temperatures at each neighborhood window moment; obtaining the neighborhood temperature variation amplitude of the target sampling moment according to the deviation distribution situation between the radiator temperature at all the neighborhood window moments and the corresponding fitting temperature and the radiator temperature difference between the target sampling moment and the rest neighborhood window moments;
and obtaining the temperature abnormality degree of the target sampling moment according to the radiator temperature, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude of the target sampling moment, wherein the radiator temperature, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude of the target sampling moment are in positive correlation with the temperature abnormality degree.
3. The method for monitoring the operation state of the radiator in real time according to claim 2, wherein the method for acquiring the possibility of abnormal change comprises the following steps:
in time sequence, taking the ratio of the mean value of the temperature abnormality degrees of all neighborhood window moments corresponding to each sampling moment to the variance of the temperature abnormality degrees of all neighborhood window moments as the reference abnormality possibility of each sampling moment;
in time sequence, delaying a first preset temperature change before each sampling time by a parameter number of sampling times to serve as a temperature delay time of each sampling time;
in time sequence, taking the pearson correlation coefficient between the radiator temperature at all neighborhood window moments and the radiator wind speed at all neighborhood window moments of each sampling moment as the pre-delay correlation degree of each sampling moment; taking the Pearson correlation coefficient between the radiator temperatures at all neighborhood window moments of each sampling moment and the radiator wind speeds at all temperature delay moments corresponding to all neighborhood window moments as the post-delay correlation degree of each sampling moment; taking a positive correlation mapping value of a difference value between the pre-delay association degree and the post-delay association degree as an association abnormality possibility of each sampling moment;
And obtaining the abnormal change probability of each sampling time according to the reference abnormal probability and the associated abnormal probability, wherein the reference abnormal probability and the associated abnormal probability are in positive correlation with the abnormal change probability.
4. The method for monitoring the operation state of the radiator in real time according to claim 1, wherein the method for obtaining the abnormality degree of the radiator comprises the following steps:
obtaining all temperature k neighbor moments of each sampling moment through a k neighbor algorithm according to the radiator temperature of all sampling moments;
obtaining an abnormal score weighting weight of each temperature k neighbor moment corresponding to each sampling moment according to the time interval and the abnormal change possibility difference between each sampling moment and each temperature k neighbor moment corresponding to each sampling moment and the temperature abnormality degree and the abnormal change possibility of each temperature k neighbor moment;
according to the abnormal score weighting weights of all k adjacent moments corresponding to each sampling moment, combining the radiator temperature difference and the radiator wind speed difference between each sampling moment and each k adjacent moment to construct a radiator abnormal degree calculation model; and obtaining the abnormal degree of the radiator at each sampling moment according to the abnormal degree calculation model of the radiator.
5. The method for monitoring the operation state of the radiator according to claim 2, wherein the method for monitoring the operation state of the radiator according to the abnormality degree of the radiator at all sampling moments comprises the following steps:
calculating the mean value of the abnormal degree of the radiator at all sampling moments, and taking the sampling moment with the abnormal degree of the radiator larger than the mean value of the abnormal degree of the radiator as the abnormal sampling moment; in all neighborhood window moments of each sampling moment, when the number of abnormal sampling moments is larger than a preset abnormal threshold value, the running state of the radiator at the corresponding sampling moment is abnormal; when the number of abnormal sampling moments is smaller than or equal to a preset abnormal threshold value, the radiator is in a normal running state at the corresponding sampling moment.
6. The method for monitoring the operation state of the radiator in real time according to claim 2, wherein the method for obtaining the neighborhood temperature variation range comprises the following steps:
taking the difference between the radiator temperature at each neighborhood window moment and the corresponding fitting temperature as the temperature residual error at each neighborhood window moment; taking the difference between the radiator temperature at each neighborhood window time and the radiator temperature at the corresponding target sampling time as the neighborhood temperature difference at each neighborhood window time; taking the sum value between the temperature residual error and the neighborhood temperature difference as the local temperature deviation of each neighborhood window moment; and taking the sum of the local temperature deviations at all the neighborhood window moments as the neighborhood temperature deviation at the target sampling moment.
7. The method for monitoring the operation state of the radiator in real time according to claim 2, wherein the method for obtaining the temperature anomaly degree at the target sampling time according to the radiator temperature at the target sampling time, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude comprises the following steps:
and taking the product among the radiator temperature, the neighborhood temperature variation deviation and the neighborhood temperature variation amplitude at the target sampling moment as the temperature abnormality degree at the target sampling moment.
8. A method for monitoring the operation state of a radiator in real time according to claim 3, wherein the method for obtaining the abnormal change probability at each sampling time according to the reference abnormal probability and the associated abnormal probability comprises:
and taking the product of the reference abnormal probability and the associated abnormal probability as the abnormal change probability of each sampling moment.
9. The method for monitoring the operation state of a radiator according to claim 4, wherein the calculation formula of the anomaly score weighting weight includes:
wherein,is->The corresponding +.>Abnormal score weighting weights at adjacent moments of the temperatures k; / >Is->The corresponding +.>Temperature anomaly degree at adjacent moment of each temperature k; />Is->The corresponding +.>Temperature of eachAbnormal change probability at the moment of the adjacent degree k; />Is->The sample times correspond to the +.>The time interval between adjacent moments of the temperature k; />Is->Abnormal change probability at each sampling time.
10. The method for monitoring the operation state of a radiator in real time according to claim 4, wherein the method for constructing the radiator abnormality degree calculation model comprises the following steps:
wherein,is->Radiator abnormality degree at each sampling time, +.>Is->K-nearest neighbor time number of sampling times, +.>Is->The corresponding +.>Abnormality score weighting weight for each temperature k nearest neighbor time,/->Is->The corresponding +.>Radiator temperature at a moment of adjacent temperature k; />Is->Radiator temperatures corresponding to the sampling moments; />Is->The corresponding +.>Radiator wind speed at a moment of adjacent temperature k; />Is->Radiator wind speeds corresponding to the sampling moments;is a normalization function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410108664.3A CN117632665B (en) | 2024-01-26 | 2024-01-26 | Running state real-time monitoring method for radiator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410108664.3A CN117632665B (en) | 2024-01-26 | 2024-01-26 | Running state real-time monitoring method for radiator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117632665A true CN117632665A (en) | 2024-03-01 |
| CN117632665B CN117632665B (en) | 2024-04-05 |
Family
ID=90021967
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410108664.3A Active CN117632665B (en) | 2024-01-26 | 2024-01-26 | Running state real-time monitoring method for radiator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117632665B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117892095A (en) * | 2024-03-14 | 2024-04-16 | 山东泰开电力电子有限公司 | Intelligent detection method for faults of heat dissipation system for energy storage system |
| CN118094485A (en) * | 2024-04-26 | 2024-05-28 | 湖南防灾科技有限公司 | Overhead line icing thickness analysis method suitable for complex micro-topography |
| CN118500538A (en) * | 2024-07-18 | 2024-08-16 | 茌平鲁环汽车散热器有限公司 | Method for monitoring working condition of automobile radiating fin |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130151179A1 (en) * | 2011-12-13 | 2013-06-13 | Schneider Electric USA, Inc. | Automated monitoring for changes in energy consumption patterns |
| US20140278165A1 (en) * | 2013-03-14 | 2014-09-18 | Johnson Controls Technology Company | Systems and methods for analyzing energy consumption model data |
| CN115081966A (en) * | 2022-08-22 | 2022-09-20 | 南通俊朗智能科技有限公司 | Abnormal state monitoring method and aluminum alloy extrusion process controller applying same |
| CN117131314A (en) * | 2023-10-25 | 2023-11-28 | 山东力驰市政建设工程有限公司 | Mixed material temperature monitoring and regulating system for asphalt pavement construction |
| CN117422719A (en) * | 2023-12-19 | 2024-01-19 | 东莞市富其扬电子科技有限公司 | Production quality detection method for high-end chip radiator |
-
2024
- 2024-01-26 CN CN202410108664.3A patent/CN117632665B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130151179A1 (en) * | 2011-12-13 | 2013-06-13 | Schneider Electric USA, Inc. | Automated monitoring for changes in energy consumption patterns |
| US20140278165A1 (en) * | 2013-03-14 | 2014-09-18 | Johnson Controls Technology Company | Systems and methods for analyzing energy consumption model data |
| CN115081966A (en) * | 2022-08-22 | 2022-09-20 | 南通俊朗智能科技有限公司 | Abnormal state monitoring method and aluminum alloy extrusion process controller applying same |
| CN117131314A (en) * | 2023-10-25 | 2023-11-28 | 山东力驰市政建设工程有限公司 | Mixed material temperature monitoring and regulating system for asphalt pavement construction |
| CN117422719A (en) * | 2023-12-19 | 2024-01-19 | 东莞市富其扬电子科技有限公司 | Production quality detection method for high-end chip radiator |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117892095A (en) * | 2024-03-14 | 2024-04-16 | 山东泰开电力电子有限公司 | Intelligent detection method for faults of heat dissipation system for energy storage system |
| CN117892095B (en) * | 2024-03-14 | 2024-05-28 | 山东泰开电力电子有限公司 | Intelligent detection method for faults of heat dissipation system for energy storage system |
| CN118094485A (en) * | 2024-04-26 | 2024-05-28 | 湖南防灾科技有限公司 | Overhead line icing thickness analysis method suitable for complex micro-topography |
| CN118500538A (en) * | 2024-07-18 | 2024-08-16 | 茌平鲁环汽车散热器有限公司 | Method for monitoring working condition of automobile radiating fin |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117632665B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117632665B (en) | Running state real-time monitoring method for radiator | |
| CN117290802B (en) | Host power supply operation monitoring method based on data processing | |
| CN110849645B (en) | Initial diagnosis method for GIS mechanical fault | |
| CN116340795B (en) | Operation data processing method for pure oxygen combustion heating furnace | |
| CN117196353B (en) | Environmental pollution assessment and monitoring method and system based on big data | |
| US20200410042A1 (en) | Abnormality detection device, abnormality detection method, and non-transitory computer-readable medium | |
| CN116772285B (en) | Intelligent building heating load safety real-time monitoring method | |
| CN117571107B (en) | Intelligent unattended wagon balance anomaly monitoring system | |
| CN116881673B (en) | Shield tunneling machine operation and maintenance method based on big data analysis | |
| CN116226766B (en) | High-voltage electrical apparatus running state monitoring system | |
| CN115127194B (en) | Method, equipment and medium for detecting faults of central air conditioner water chilling unit | |
| CN117196446B (en) | Product risk real-time monitoring platform based on big data | |
| CN117892246A (en) | Data processing method for intelligent switch cabinet | |
| CN117349664B (en) | On-line monitoring method and system for sprouting vegetable growth environment | |
| CN118312727A (en) | Cooling system temperature monitoring method for intelligent carbon dioxide incubator | |
| CN116878590B (en) | Intelligent service collaborative operation management system | |
| CN115291652B (en) | Dynamic evaluation method for evaluating CPU physique of concentrator | |
| CN116090939A (en) | Artificial intelligence-based method for identifying and tracking problem products in supply chain | |
| CN113408383B (en) | Audible noise invalid data judgment method based on bounded beta (g, h) distribution and MWKPCA | |
| CN117648587B (en) | Motor locked rotor high-sensitivity detection method | |
| CN117905651B (en) | Structure monitoring method based on deformation analysis | |
| CN111980853A (en) | Pitch control method and device and computer readable storage medium | |
| Ismael et al. | LFDDRA-IoT: Lightweight Faulty Data Detection and Recovery Approach for Internet of Things | |
| TW202125138A (en) | Abnormality diagnosis device and program capable of accurately determining a state of a device to be diagnosed | |
| Pushpalatha | Ruziicka Similarity Feature Selection Based Generalized Linear Regression Analysis For Weather Forecasting Using Big 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 |