CN114322446A - Cooling system fault early warning method and device, cooling system and operation machine - Google Patents
Cooling system fault early warning method and device, cooling system and operation machine Download PDFInfo
- Publication number
- CN114322446A CN114322446A CN202111659422.6A CN202111659422A CN114322446A CN 114322446 A CN114322446 A CN 114322446A CN 202111659422 A CN202111659422 A CN 202111659422A CN 114322446 A CN114322446 A CN 114322446A
- Authority
- CN
- China
- Prior art keywords
- early warning
- water temperature
- cooling system
- data
- cooling water
- 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
- 238000001816 cooling Methods 0.000 title claims abstract description 188
- 238000000034 method Methods 0.000 title claims abstract description 67
- 239000000498 cooling water Substances 0.000 claims abstract description 136
- 230000002159 abnormal effect Effects 0.000 claims abstract description 42
- 230000007704 transition Effects 0.000 claims abstract description 20
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 68
- 238000012549 training Methods 0.000 claims description 33
- 238000012360 testing method Methods 0.000 claims description 27
- 239000010720 hydraulic oil Substances 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 10
- 230000007257 malfunction Effects 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 9
- 238000012795 verification Methods 0.000 description 10
- 238000000605 extraction Methods 0.000 description 9
- 238000012216 screening Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 239000008358 core component Substances 0.000 description 2
- 230000017525 heat dissipation Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a cooling system fault early warning method, a cooling system fault early warning device, a cooling system and an operating machine, wherein the method comprises the following steps: acquiring working condition information of carrier equipment corresponding to a cooling system; selecting a corresponding fault early warning mode according to the working condition information of the carrier equipment corresponding to the cooling system; the fault early warning mode comprises a cold start early warning mode, a transition early warning mode and a dynamic early warning mode; and based on the selected fault early warning mode, carrying out fault early warning on the abnormal cooling water temperature in the cooling system. Through setting up multiple trouble early warning mode, can select corresponding trouble early warning mode to realize cooling water temperature anomaly early warning according to the operating mode information of the carrier equipment that cooling system corresponds, compare in single trouble early warning mode, this early warning scheme is more targeted, and the fault detection result is more accurate, reliable.
Description
Technical Field
The invention relates to the technical field of fault detection, in particular to a cooling system fault early warning method and device, a cooling system and an operating machine.
Background
The cooling system is used as a part for helping heat dissipation of core components in the equipment, the working stability of the cooling system is an important factor influencing the safe operation of the equipment, and if the abnormality of the cooling system is not found in time, the core components of the equipment can be damaged, and even safety accidents can be caused.
However, the existing cooling system fault detection method has the problems of single fault detection and early warning mode and low reliability of fault detection results, and is difficult to meet the requirements of practical application.
Disclosure of Invention
The invention provides a cooling system fault early warning method, a cooling system fault early warning device, a cooling system and an operating machine, which are used for solving the defects that a cooling system fault detection method in the prior art is single in fault detection and early warning mode and low in reliability of fault detection results.
In a first aspect, the present invention provides a fault early warning method for a cooling system, including:
acquiring working condition information of carrier equipment corresponding to a cooling system;
selecting a corresponding fault early warning mode according to the working condition information of the carrier equipment corresponding to the cooling system; the fault early warning mode comprises a cold start early warning mode, a transition early warning mode and a dynamic early warning mode;
and carrying out fault early warning on the abnormal cooling water temperature in the cooling system based on the selected fault early warning mode.
According to the fault early warning method for the cooling system, the working condition information of the carrier equipment corresponding to the cooling system comprises the access time of the cooling system and the equipment operation data.
According to the fault early warning method for the cooling system, provided by the invention, a corresponding fault early warning mode is selected according to the working condition information of the carrier equipment corresponding to the cooling system, and the fault early warning method comprises the following steps:
judging whether the access duration of the cooling system is lower than a preset duration lower limit value or not, and if the access duration of the cooling system is lower than the duration lower limit value, selecting a cold start early warning mode;
if the access time length of the cooling system is between a preset time length lower limit value and a preset time length upper limit value or the access time length of the cooling system is higher than the time length lower limit value and a small number of fields of equipment operation data are omitted, selecting a transition early warning mode;
and if the access time of the cooling system is higher than the upper limit threshold of the time, selecting a dynamic early warning mode.
According to the fault early warning method for the cooling system, when the selected fault early warning mode is the cold start early warning mode, fault early warning is carried out on abnormal cooling water temperature in the cooling system based on the selected fault early warning mode, and the fault early warning method comprises the following steps:
acquiring cooling water temperature data of the cooling system in a preset time period;
and judging whether the highest value of the cooling water temperature in the cooling water temperature data is higher than a preset unified water temperature threshold and the time length of the cooling water temperature in the cooling water temperature data which is higher than the unified water temperature threshold exceeds a preset over-limit time length threshold, if so, judging that the cooling water temperature is abnormal and carrying out fault early warning.
According to the fault early warning method for the cooling system, when the selected fault early warning mode is the transition early warning mode, fault early warning is carried out on abnormal cooling water temperature in the cooling system based on the selected fault early warning mode, and the fault early warning method comprises the following steps:
acquiring cooling water temperature data and historical water temperature data of the cooling system in a preset time period;
and judging whether the maximum value of the cooling water temperature in the cooling water temperature data is higher than the maximum water temperature threshold in the historical water temperature data and the time length of the maximum water temperature in the historical water temperature data exceeds a preset time-exceeding threshold, and if so, judging that the cooling water temperature is abnormal and carrying out fault early warning.
According to the fault early warning method for the cooling system, provided by the invention, when the selected fault early warning mode is the dynamic early warning mode, fault early warning is carried out on abnormal cooling water temperature in the cooling system based on the selected fault early warning mode, and the fault early warning method comprises the following steps:
acquiring actual operation data of carrier equipment corresponding to the cooling system in a preset time period;
obtaining characteristic data and a cooling water temperature measured value of the cooling system based on the actual operation data;
inputting the characteristic data into a cooling water temperature prediction model to obtain a cooling water temperature prediction value output by the cooling water temperature prediction model; the cooling water temperature prediction model is obtained by training and testing a nonlinear regression model based on sample characteristic data and sample label data of the cooling system;
the measured value of the cooling water temperature is differed with the predicted value of the cooling water temperature to obtain a water temperature difference value statistic value;
and comparing the water temperature difference value statistic value with a preset water temperature difference value statistic value threshold, and if the water temperature difference value statistic value is larger than the water temperature difference value statistic value threshold, judging that the cooling water temperature is abnormal and carrying out fault early warning.
According to the fault early warning method for the cooling system, the training process of the cooling water temperature prediction model comprises the following steps:
acquiring original sample data of a cooling system;
extracting sample characteristic data and sample label data from the original sample data; the sample characteristic data comprises one or more of an environment temperature statistic value, a hydraulic oil temperature statistic value and an engine rotating speed statistic value, and the sample label data comprises a cooling water temperature statistic value;
and training and testing a nonlinear regression model based on the sample characteristic data and the sample label data to obtain a cooling water temperature prediction model.
In a second aspect, the present invention further provides a cooling system fault early warning device, including:
the acquisition module is used for acquiring the working condition information of the carrier equipment corresponding to the cooling system;
the first processing module is used for selecting a corresponding fault early warning mode according to the working condition information of the carrier equipment corresponding to the cooling system; the fault early warning mode comprises a cold start early warning mode, a transition early warning mode and a dynamic early warning mode;
and the second processing module is used for carrying out fault early warning on the abnormal cooling water temperature in the cooling system based on the selected fault early warning mode.
In a third aspect, the invention further provides a cooling system, wherein the cooling system uses any one of the above-mentioned fault early warning methods, and the cooling system uses the above-mentioned fault early warning method, so that the fault of the abnormal self-cooling water temperature can be timely and reliably early warned.
In a fourth aspect, the invention further provides a working machine, which includes the cooling system, and by using the cooling system, the working machine can find abnormal faults of cooling water temperature in time and perform early warning in time in the working process, so that the working process is safer.
According to the cooling system fault early warning method, the cooling system fault early warning device, the cooling system and the operation machine, multiple fault early warning modes are set, the corresponding fault early warning mode can be selected according to the working condition information of the carrier equipment corresponding to the cooling system, and the abnormal early warning of the cooling water temperature is realized.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a cooling system fault warning method provided by the present invention;
FIG. 2 is a schematic diagram of a training and testing process of a cooling water temperature prediction model;
FIG. 3 is a schematic diagram of a data feature extraction process;
FIG. 4 is a schematic structural diagram of a cooling system fault warning device provided by the present invention;
fig. 5 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The cooling system fault warning method, the cooling system fault warning device, the cooling system and the working machine provided by the invention are described below with reference to fig. 1 to 4.
Fig. 1 illustrates a cooling system fault warning method provided by an embodiment of the present invention, where the method includes:
step 110: and acquiring working condition information of the carrier equipment corresponding to the cooling system.
The operating condition information of the carrier device corresponding to the cooling system in this embodiment may include access duration data of the cooling system and device operation data. The carrier device refers to a device or a working machine provided with a cooling system, and the device operation data can comprise one or more of ambient temperature data, hydraulic oil temperature data and engine rotating speed data.
Step 120: selecting a corresponding fault early warning mode according to the working condition information of the carrier equipment corresponding to the cooling system; the fault early warning mode comprises a cold start early warning mode, a transition early warning mode and a dynamic early warning mode.
In order to realize the targeted early warning mode setting, three fault early warning modes are correspondingly set according to the access duration of the cooling system and whether the equipment operation data exists, so that a fault early warning scheme can be pertinently started, and the early warning effect is better.
In this embodiment, the process of selecting the corresponding fault early warning mode according to the operating condition information of the carrier device corresponding to the cooling system may specifically include:
judging whether the access duration of the cooling system is lower than a preset duration lower limit value or not, and if the access duration of the cooling system is lower than the duration lower limit value, selecting a cold start early warning mode;
if the access time of the cooling system is between a preset time lower limit value and a preset time upper limit value or the access time of the cooling system is higher than the time lower limit value and a small number of fields of equipment operation data are omitted, selecting a transition early warning mode;
and if the access duration of the cooling system is higher than the upper limit threshold of the duration, selecting a dynamic early warning mode.
In practical applications, the access duration of the cooling system may be determined by the access duration of the work machine (i.e., carrier device) to which it is attached.
For example, the lower limit value of the duration may be set to be one month, the upper limit value of the duration may be one year, when the access duration of the cooling system is less than one month, it may be determined that the cooling system is a newly accessed system, and a cold start early warning mode may be selected because relevant working condition data of the cooling system cannot be obtained.
When the access duration of the cooling system is longer than one month but shorter than one year, or although the access duration of the cooling system is longer than one month, even longer than one year, the relevant equipment operation data cannot be obtained, at this time, because the effective data of the hydraulic system is shorter than one year, or because the equipment operation data is incomplete, based on the existing data of the hydraulic system at present, dynamic early warning cannot be performed in a model training mode, and only a transition early warning mode can be adopted.
When the access time of the cooling system is longer than one year and relevant equipment operation data also exist, the dynamic early warning mode is adopted.
Step 130: and based on the selected fault early warning mode, carrying out fault early warning on the abnormal cooling water temperature in the cooling system.
When the selected fault early warning mode is the cold start early warning mode, based on the selected fault early warning mode, the fault early warning is performed on the abnormal cooling water temperature in the cooling system, and the fault early warning method may include:
acquiring cooling water temperature data of a cooling system in a preset time period;
and judging whether the highest value of the cooling water temperature in the cooling water temperature data is higher than a preset unified water temperature threshold and the time length of the cooling water temperature in the cooling water temperature data which is higher than the unified water temperature threshold exceeds a preset over-limit time length threshold, if so, judging that the cooling water temperature is abnormal and carrying out fault early warning.
When the cold start early warning mode is adopted, a preset time interval can be set to be one day, and by judging whether the highest value of the cooling water temperature of the cooling system every day is higher than a preset unified water temperature threshold value or not and whether the duration time exceeding the threshold value exceeds an over-limit time threshold value or not, if the two judgment results are both met, the water temperature abnormity can be judged to occur, and fault early warning is needed.
In the practical application process, the unified water temperature threshold and the time-out-of-limit threshold can be reasonably set according to the practical application scene, and meanwhile, the unified water temperature thresholds of all newly-accessed hydraulic systems can be set to be consistent.
When the selected fault early warning mode is the transition early warning mode, based on the selected fault early warning mode, fault early warning is carried out on abnormal cooling water temperature in the cooling system, and the fault early warning method comprises the following steps:
acquiring cooling water temperature data and historical water temperature data of a cooling system in a preset time period;
and judging whether the highest value of the cooling water temperature in the cooling water temperature data is higher than the highest water temperature threshold in the historical water temperature data and the time length of the highest water temperature threshold in the historical water temperature data exceeds the time length exceeding threshold, if so, judging that the cooling water temperature is abnormal and carrying out fault early warning.
When the transition early warning mode is adopted, the preset time interval can be set to be one day, whether the highest value of the cooling water temperature of the cooling system per day exceeds the highest threshold value of the water temperature in the historical water temperature data or not is judged, and whether the time length exceeding the highest threshold value of the water temperature exceeds the time length exceeding threshold value or not is judged, if the two conditions are met, the cooling water temperature is judged to be abnormal, and fault early warning can be triggered.
It should be noted that the maximum water temperature threshold in the transient warning mode is obtained based on historical data of the cooling system itself, so the threshold is not uniform and may be slightly different from cooling system to cooling system. Of course, in the actual application process, the water temperature threshold obtained based on the historical data may not be the highest value of the water temperature in the historical data, and may be set reasonably according to actual needs.
In the practical application process, in order to ensure the reliability of the historical water temperature data, the historical water temperature data within a certain time range near the preset time period can be selected, for example, when the preset time period is one day, the historical water temperature data within the first half month of the day can be selected, and the selected historical water temperature data is relatively close to the current detection time, so that the data reliability is higher.
When the selected fault early warning mode is the dynamic early warning mode, based on the selected fault early warning mode, fault early warning is carried out on abnormal cooling water temperature in the cooling system, and the fault early warning method comprises the following steps:
acquiring actual operation data of carrier equipment corresponding to a cooling system in a preset time period;
obtaining characteristic data and a cooling water temperature measured value of the cooling system based on the actual operation data;
inputting the characteristic data into a cooling water temperature prediction model to obtain a cooling water temperature prediction value output by the cooling water temperature prediction model; the cooling water temperature prediction model is obtained by training and testing a nonlinear regression model based on sample characteristic data and sample label data of a cooling system;
the measured value of the cooling water temperature is differed with the predicted value of the cooling water temperature to obtain a water temperature difference value statistic value;
and comparing the water temperature difference value statistic value with a preset water temperature difference value statistic value threshold, and if the water temperature difference value statistic value is larger than the water temperature difference value statistic value threshold, judging that the cooling water temperature is abnormal and carrying out fault early warning.
When the dynamic early warning mode is adopted, a cooling water temperature prediction model of each carrier device (i.e. a working machine to which a cooling system is attached) can be established in units of the carrier devices, and the process of training and testing the model can include:
firstly, acquiring original sample data of a cooling system; the original sample data can comprise one or more of ambient temperature data, hydraulic oil temperature data and engine rotating speed data, and also comprises cooling water temperature data;
then, extracting sample characteristic data and sample label data from the original sample data; the sample characteristic data comprises one or more of an environment temperature statistic value, a hydraulic oil temperature statistic value and an engine rotating speed statistic value, and the sample label data comprises a cooling water temperature statistic value;
and finally, training and testing the nonlinear regression model based on the sample characteristic data and the sample label data to obtain a cooling water temperature prediction model.
In this embodiment, a flow of model training and model testing of the cooling water temperature prediction model is shown in fig. 2, and specifically includes:
step 201: the method comprises the steps of obtaining original sample data, obtaining related data when a hydraulic system works normally by collecting sensor data of different columns (namely different types), namely the original sample data, wherein the data collection frequency can be set reasonably according to actual needs, and part of data in the original sample data can be used as training data.
Step 202: and (3) preprocessing training data, namely setting a screening rule for each column sensor data, removing noise points in the data and ensuring the accuracy of a training data set. In this embodiment, for example, the original sample data includes hydraulic oil temperature and cooling water temperature, and the set screening rule is as follows:
50 ℃ and < cooling water temperature <113 ℃;
30 ℃ and <90 ℃ of hydraulic oil temperature;
the standard deviation of the cooling water temperature is greater than 0;
the standard deviation of the hydraulic oil temperature is greater than 0;
the number of data sample points is > 100.
Step 203: and training data feature extraction, namely extracting data features for each cooling system in a sliding window mode, wherein the specific feature extraction principle is shown in fig. 3, raw data is two-dimensional structured data, each row is data of different types of sensors at the same moment, and each column is data of each sensor at different moments. The dashed frame is a time sliding window, including the amount of raw data used for extracting each feature data, and in order to ensure sufficient data amount in the feature data of the training set, the size of the time sliding window may be 2 hours in general, and the size of the window may be 1 day during online running. The offset between each window is the sliding window time span, the offset of the training data is generally set to be half of the window size, and the offset can be set to be 1 day during online runtime.
In the feature extraction part, fnn represents feature data extracted from a time sliding window, and mainly includes one or any one of ambient temperature statistics, hydraulic oil temperature statistics, and engine speed statistics, and specifically may include an ambient temperature quantile (which may be a 99% quantile), an ambient temperature median, an ambient temperature standard deviation, a hydraulic oil temperature quantile value (which may be a 99% quantile), a hydraulic oil temperature median, a hydraulic oil temperature standard deviation, an engine speed quantile (which may be a 99% quantile), an engine speed median, an engine speed standard deviation, and a current month. labeln represents label data corresponding to the time sliding window, and the label is a cooling water temperature statistic value, specifically, a cooling water temperature quantile value (which may be a 99% quantile).
Step 204: and establishing a regression model between the characteristics and the water temperature, and training the nonlinear regression model by using the extracted characteristic data and the extracted label data to establish the nonlinear regression model of the characteristic data and the label data.
Step 205: and calculating a residual error between the predicted value and the true value of the model, inputting the characteristic data in the training data into the model based on the obtained nonlinear regression model to obtain a corresponding predicted value of the cooling water temperature, and subtracting the predicted value of the cooling water temperature from a measured value (namely the true value) in the training data to obtain residual error data.
Step 206: and determining a residual threshold, wherein the difference between the actually measured value of the cooling water temperature and the predicted value of the cooling water temperature can be calculated through prediction of a nonlinear regression model, so as to obtain residual data, the statistical value of the residual can be selected as a residual threshold, and the residual threshold can be used as a water temperature difference value statistical threshold for judging whether the water temperature is abnormal or not.
In the step of determining the residual threshold, the residual threshold can also be determined by using a verification data set, namely, part of data is taken from original sample data to be used as the verification data set, after the pretreatment and the feature extraction which are the same as those of training data, the feature data and the label data of the verification data set are obtained, the feature data is input into a nonlinear regression model obtained by training, a cooling water temperature verification value can be obtained, then the cooling water temperature verification value is differed with an actual measurement value in the label data, and then the residual threshold can be determined.
Step 207: and constructing a test data set, and taking partial data in the original sample data as test data.
Step 208: test data preprocessing, wherein the screening condition of the upper limit threshold of the cooling water temperature is removed in the test data preprocessing process, noise points in the data are removed through screening, and the specific screening rule can be as follows:
the temperature of cooling water is more than 50 ℃;
30 ℃ and <90 ℃ of hydraulic oil temperature;
the standard deviation of the cooling water temperature is greater than 0;
the standard deviation of the hydraulic oil temperature is greater than 0;
the number of data sample points is > 100.
Step 209: and (4) extracting the features of the test data, wherein the feature extraction mode of the feature extraction is generally consistent with that of the training data given in the step 203, and finally obtaining a test data set for model test, which is composed of the feature data and the label data.
Step 210: and model prediction, namely predicting the characteristic data through a nonlinear regression model obtained through training to obtain a model test value.
Step 211: and calculating the difference between the test value of the model and the real value (namely the label data) in the test data set to obtain residual data.
Step 212: and comparing the pre-obtained residual error threshold value with the residual error data obtained in the step 211 to determine whether each residual error in the residual error data exceeds the residual error threshold value, if so, performing fault early warning of abnormal water temperature, and completing model test to obtain a cooling water temperature prediction model.
The implementation process of the cooling system fault warning method is described in detail below by using a specific example.
In the embodiment, taking the cooling system failure prediction of a certain pile machine as an example, the equipment user submits a failure order in 2021, 4 months and 8 days, and confirms that the equipment fails on the current day.
In the first step, sampling data of each sensor on the pile machine, which is related to a cooling system, is obtained, and raw data are obtained. The sensors mainly comprise an ambient temperature sensor, a cooling water temperature sensor, an engine rotating speed sensor and a hydraulic oil temperature sensor corresponding to the cooling system.
And secondly, dividing a data set, segmenting the data set according to time, taking the data collected from 2019.1.1-2020.3.1 as a training data set, taking the data collected from 2020.3.1-2021.3.1 as a verification data set, and taking the data collected from 2021.3.1-2021.5.1 as a test data set.
And thirdly, performing data screening and feature extraction on the data set, wherein the time sliding window of the training set is 2 hours, 6607 data examples are obtained, and 6607 data examples are adopted for training to obtain a lightgbm regression model.
And fourthly, performing data screening and feature extraction on the verification data set, wherein the size of a time sliding window of the verification set is 2 hours, 5120 data examples are obtained, a lightgbm regression model obtained through training is adopted to predict verification features, the difference between the actual cooling water temperature and the predicted cooling water temperature in the verification data set is obtained, a residual error curve is drawn, and in order to avoid the influence of noise points in the data, 99% quantiles of the residual error data are taken as a residual error threshold value.
And fifthly, screening and extracting the characteristics of the test data set, wherein the cooling water temperature parameter is not screened, the time sliding window of the test set is 1 day, the test characteristics are predicted by adopting a model obtained by training, the difference between the actual cooling water temperature and the predicted cooling water temperature in the test data set is obtained, a residual error curve is drawn, the residual error threshold value obtained in the fourth step is compared with each residual error point in the residual error curve, whether each residual error point exceeds the residual error threshold value or not is judged, if the residual error point exceeds the residual error threshold value, the water temperature is abnormal, and fault early warning is needed.
Sixthly, residual errors of 2021 year, 4 months and 1 day in the final actual measurement result exceed a residual error threshold value, and the fault early warning time is about seven days earlier than the actual fault time. Therefore, the early warning method can timely and accurately early warn the abnormal water temperature fault of the cooling system in advance.
Therefore, the cooling system fault early warning method provided by the embodiment of the invention can carry out cold start of fault prediction on a newly accessed cooling system by setting a plurality of fault early warning modes, and meanwhile, as the access time length is prolonged, more reliable fault early warning function can be realized by using the historical data of the system, so that the precision of fault early warning is effectively improved.
The cooling system fault early warning device provided by the invention is described below, and the cooling system fault early warning device described below and the cooling system fault early warning method described above can be referred to correspondingly.
Fig. 4 shows a cooling system fault early warning device provided by an embodiment of the present invention, which includes:
an obtaining module 410, configured to obtain working condition information of a carrier device corresponding to a cooling system;
the first processing module 420 is configured to select a corresponding fault early warning mode according to the working condition information of the carrier device corresponding to the cooling system; the fault early warning mode comprises a cold start early warning mode, a transition early warning mode and a dynamic early warning mode;
and the second processing module 430 is configured to perform fault early warning on abnormal cooling water temperature in the cooling system based on the selected fault early warning mode.
Specifically, the operating condition information of the carrier device corresponding to the cooling system may include access time data of the cooling system and device operation data.
In an exemplary embodiment, the first processing module 420 is specifically configured to:
judging whether the access duration of the cooling system is lower than a preset duration lower limit value or not, and if the access duration of the cooling system is lower than the duration lower limit value, selecting a cold start early warning mode;
if the access time of the cooling system is between the preset time lower limit value and the preset time upper limit value or the access time of the cooling system is higher than the time lower limit value and the running data of the cooling system equipment lacks a few fields, selecting a transition early warning mode;
and if the access duration of the cooling system is higher than the upper limit threshold of the duration, selecting a dynamic early warning mode.
When the selected fault early warning mode is the cold start early warning mode, the second processing module 430 is specifically configured to:
acquiring cooling water temperature data of a cooling system in a preset time period;
and judging whether the highest value of the cooling water temperature in the cooling water temperature data is higher than a preset unified water temperature threshold and the time length of the cooling water temperature in the cooling water temperature data which is higher than the unified water temperature threshold exceeds a preset over-limit time length threshold, if so, judging that the cooling water temperature is abnormal and carrying out fault early warning.
When the selected failure early warning mode is the transition early warning mode, the second processing module 430 is specifically configured to:
acquiring cooling water temperature data and historical water temperature data of a cooling system in a preset time period;
and judging whether the highest value of the cooling water temperature in the cooling water temperature data is higher than the highest water temperature threshold in the historical water temperature data and the time length of the highest water temperature threshold in the historical water temperature data exceeds a preset time-exceeding threshold, if so, judging that the cooling water temperature is abnormal and carrying out fault early warning.
When the selected failure early warning mode is the dynamic early warning mode, the second processing module 430 is specifically configured to:
acquiring actual operation data of carrier equipment corresponding to a cooling system in a preset time period;
obtaining characteristic data and a cooling water temperature measured value of the cooling system based on the actual operation data;
inputting the characteristic data into a cooling water temperature prediction model to obtain a cooling water temperature prediction value output by the cooling water temperature prediction model; the cooling water temperature prediction model is obtained by training and testing a nonlinear regression model based on sample characteristic data and sample label data of a cooling system;
the measured value of the cooling water temperature is differed with the predicted value of the cooling water temperature to obtain a water temperature difference value statistic value;
and comparing the water temperature difference value statistic value with a preset water temperature difference value statistic value threshold, and if the water temperature difference value statistic value is larger than the water temperature difference value statistic value threshold, judging that the cooling water temperature is abnormal and carrying out fault early warning.
In an exemplary embodiment, the cooling system fault early warning apparatus further includes a model training module, which is specifically configured to:
acquiring original sample data of a cooling system;
extracting sample characteristic data and sample label data from original sample data; the sample characteristic data comprises one or more of an environment temperature statistic value, a hydraulic oil temperature statistic value and an engine rotating speed statistic value, and the sample label data comprises a cooling water temperature statistic value;
and training and testing the nonlinear regression model based on the sample characteristic data and the sample label data to obtain a cooling water temperature prediction model.
Therefore, the cooling system fault early warning device provided by the embodiment of the invention can select the corresponding fault early warning mode according to the access time of the cooling system, can pertinently realize the fault early warning function according to the actual condition, has more perfect functions, and has higher accuracy and reliability in the fault early warning process.
In addition, the embodiment of the invention also provides a cooling system, and the cooling system can perform timely and reliable early warning on the abnormal fault of the cooling water temperature of the cooling system by using the fault early warning method of the cooling system.
The working machine comprises the cooling system, the cooling system can be understood as a heat dissipation system on the working machine, abnormal faults of cooling water temperature can be found in time and early warning can be carried out in time in the working process through the cooling system, and the working process is safer.
In an actual application process, the operation machine can be a pile machine, such as a rotary drilling rig, when the time length of the cooling system is determined, the time length can be achieved by using the time length data of the whole operation machine, and then the abnormal cooling water temperature of the pile machine is detected and early warned in a parallel mode of multiple fault early warning modes.
Fig. 5 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 5: a processor (processor)510, a communication Interface (Communications Interface)520, a memory (memory)530 and a communication bus 540, wherein the processor 510, the communication Interface 520 and the memory 530 communicate with each other via the communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform a cooling system fault warning method comprising: acquiring working condition information of carrier equipment corresponding to a cooling system; selecting a corresponding fault early warning mode according to the working condition information of the carrier equipment corresponding to the cooling system; the fault early warning mode comprises a cold start early warning mode, a transition early warning mode and a dynamic early warning mode; and based on the selected fault early warning mode, carrying out fault early warning on the abnormal cooling water temperature in the cooling system.
Furthermore, the logic instructions in the memory 530 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, which when executed by a computer, enable the computer to perform the cooling system fault pre-warning method provided by the above methods, the method comprising: acquiring working condition information of carrier equipment corresponding to a cooling system; selecting a corresponding fault early warning mode according to the working condition information of the carrier equipment corresponding to the cooling system; the fault early warning mode comprises a cold start early warning mode, a transition early warning mode and a dynamic early warning mode; and based on the selected fault early warning mode, carrying out fault early warning on the abnormal cooling water temperature in the cooling system.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor is implemented to perform the cooling system fault warning method provided above, the method comprising: acquiring working condition information of carrier equipment corresponding to a cooling system; selecting a corresponding fault early warning mode according to the working condition information of the carrier equipment corresponding to the cooling system; the fault early warning mode comprises a cold start early warning mode, a transition early warning mode and a dynamic early warning mode; and based on the selected fault early warning mode, carrying out fault early warning on the abnormal cooling water temperature in the cooling system.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A cooling system fault early warning method is characterized by comprising the following steps:
acquiring working condition information of carrier equipment corresponding to a cooling system;
selecting a corresponding fault early warning mode according to the working condition information of the carrier equipment corresponding to the cooling system; the fault early warning mode comprises a cold start early warning mode, a transition early warning mode and a dynamic early warning mode;
and carrying out fault early warning on the abnormal cooling water temperature in the cooling system based on the selected fault early warning mode.
2. The cooling system fault early warning method according to claim 1, wherein the operating condition information of the carrier device corresponding to the cooling system comprises access duration of the cooling system and device operation data.
3. The method for early warning of the fault of the cooling system as claimed in claim 2, wherein selecting the corresponding fault early warning mode according to the working condition information of the carrier device corresponding to the cooling system comprises:
judging whether the access duration of the cooling system is lower than a preset duration lower limit value or not, and if the access duration of the cooling system is lower than the duration lower limit value, selecting a cold start early warning mode;
if the access time length of the cooling system is between a preset time length lower limit value and a preset time length upper limit value or the access time length of the cooling system is higher than the time length lower limit value and a small number of fields of equipment operation data are omitted, selecting a transition early warning mode;
and if the access time of the cooling system is higher than the upper limit threshold of the time, selecting a dynamic early warning mode.
4. The cooling system fault early warning method according to claim 3, wherein when the selected fault early warning mode is a cold start early warning mode, fault early warning is performed on abnormal cooling water temperature in the cooling system based on the selected fault early warning mode, and the method comprises the following steps:
acquiring cooling water temperature data of the cooling system in a preset time period;
and judging whether the highest value of the cooling water temperature in the cooling water temperature data is higher than a preset unified water temperature threshold and the time length of the cooling water temperature in the cooling water temperature data which is higher than the unified water temperature threshold exceeds a preset over-limit time length threshold, if so, judging that the cooling water temperature is abnormal and carrying out fault early warning.
5. The method for early warning the fault of the cooling system according to claim 3, wherein when the selected fault early warning mode is a transition early warning mode, the fault early warning for the abnormal cooling water temperature in the cooling system based on the selected fault early warning mode comprises:
acquiring cooling water temperature data and historical water temperature data of the cooling system in a preset time period;
and judging whether the maximum value of the cooling water temperature in the cooling water temperature data is higher than the maximum water temperature threshold in the historical water temperature data and the time length of the maximum water temperature in the historical water temperature data exceeds a preset time-exceeding threshold, and if so, judging that the cooling water temperature is abnormal and carrying out fault early warning.
6. The cooling system fault early warning method according to claim 3, wherein when the selected fault early warning mode is a dynamic early warning mode, fault early warning is performed on abnormal cooling water temperature in the cooling system based on the selected fault early warning mode, and the method comprises the following steps:
acquiring actual operation data of carrier equipment corresponding to the cooling system in a preset time period;
obtaining characteristic data and a cooling water temperature measured value of the cooling system based on the actual operation data;
inputting the characteristic data into a cooling water temperature prediction model to obtain a cooling water temperature prediction value output by the cooling water temperature prediction model; the cooling water temperature prediction model is obtained by training and testing a nonlinear regression model based on sample characteristic data and sample label data of the cooling system;
the measured value of the cooling water temperature is differed with the predicted value of the cooling water temperature to obtain a water temperature difference value statistic value;
and comparing the water temperature difference value statistic value with a preset water temperature difference value statistic value threshold, and if the water temperature difference value statistic value is larger than the water temperature difference value statistic value threshold, judging that the cooling water temperature is abnormal and carrying out fault early warning.
7. The cooling system fault early warning method according to claim 6, wherein the training process of the cooling water temperature prediction model comprises the following steps:
acquiring original sample data of a cooling system;
extracting sample characteristic data and sample label data from the original sample data; the sample characteristic data comprises one or more of an environment temperature statistic value, a hydraulic oil temperature statistic value and an engine rotating speed statistic value, and the sample label data comprises a cooling water temperature statistic value;
and training and testing a nonlinear regression model based on the sample characteristic data and the sample label data to obtain a cooling water temperature prediction model.
8. A cooling system fault early warning device, comprising:
the acquisition module is used for acquiring the working condition information of the carrier equipment corresponding to the cooling system;
the first processing module is used for selecting a corresponding fault early warning mode according to the working condition information of the carrier equipment corresponding to the cooling system; the fault early warning mode comprises a cold start early warning mode, a transition early warning mode and a dynamic early warning mode;
and the second processing module is used for carrying out fault early warning on the abnormal cooling water temperature in the cooling system based on the selected fault early warning mode.
9. A cooling system using a cooling system malfunction early warning method according to any one of claims 1 to 7.
10. A work machine comprising a cooling system as claimed in claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111659422.6A CN114322446B (en) | 2021-12-30 | 2021-12-30 | Cooling system fault early warning method and device, cooling system and working machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111659422.6A CN114322446B (en) | 2021-12-30 | 2021-12-30 | Cooling system fault early warning method and device, cooling system and working machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114322446A true CN114322446A (en) | 2022-04-12 |
| CN114322446B CN114322446B (en) | 2023-10-24 |
Family
ID=81018813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111659422.6A Active CN114322446B (en) | 2021-12-30 | 2021-12-30 | Cooling system fault early warning method and device, cooling system and working machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114322446B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115933841A (en) * | 2022-12-23 | 2023-04-07 | 南方电网大数据服务有限公司 | Liquid cooling CDU prediction system based on historical information analysis |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108506171A (en) * | 2018-03-20 | 2018-09-07 | 明阳智慧能源集团股份公司 | A kind of large-scale half direct-drive unit cooling system for gear box fault early warning method |
| CN112924205A (en) * | 2021-01-27 | 2021-06-08 | 上海三一重机股份有限公司 | Method and device for diagnosing faults of working machine, working machine and electronic equipment |
| DE202020005497U1 (en) * | 2020-12-17 | 2021-07-13 | Secop Gmbh | Portable cooling unit |
| CN113327341A (en) * | 2021-04-29 | 2021-08-31 | 平顶山聚新网络科技有限公司 | Equipment early warning system, method and storage medium based on network technology |
| CN113516200A (en) * | 2021-07-30 | 2021-10-19 | 盛景智能科技(嘉兴)有限公司 | Method and device for generating model training scheme, electronic equipment and storage medium |
| CN113606833A (en) * | 2021-08-17 | 2021-11-05 | 四川虹美智能科技有限公司 | Refrigerator fault prediction system based on LSTM recurrent neural network |
| CN113685260A (en) * | 2021-09-07 | 2021-11-23 | 上海华兴数字科技有限公司 | Cooling system fault diagnosis method and device and working machine |
| CN113762391A (en) * | 2021-09-08 | 2021-12-07 | 中国南方电网有限责任公司超高压输电公司昆明局 | State detection method and device of cooling system, computer equipment and storage medium |
-
2021
- 2021-12-30 CN CN202111659422.6A patent/CN114322446B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108506171A (en) * | 2018-03-20 | 2018-09-07 | 明阳智慧能源集团股份公司 | A kind of large-scale half direct-drive unit cooling system for gear box fault early warning method |
| DE202020005497U1 (en) * | 2020-12-17 | 2021-07-13 | Secop Gmbh | Portable cooling unit |
| CN112924205A (en) * | 2021-01-27 | 2021-06-08 | 上海三一重机股份有限公司 | Method and device for diagnosing faults of working machine, working machine and electronic equipment |
| CN113327341A (en) * | 2021-04-29 | 2021-08-31 | 平顶山聚新网络科技有限公司 | Equipment early warning system, method and storage medium based on network technology |
| CN113516200A (en) * | 2021-07-30 | 2021-10-19 | 盛景智能科技(嘉兴)有限公司 | Method and device for generating model training scheme, electronic equipment and storage medium |
| CN113606833A (en) * | 2021-08-17 | 2021-11-05 | 四川虹美智能科技有限公司 | Refrigerator fault prediction system based on LSTM recurrent neural network |
| CN113685260A (en) * | 2021-09-07 | 2021-11-23 | 上海华兴数字科技有限公司 | Cooling system fault diagnosis method and device and working machine |
| CN113762391A (en) * | 2021-09-08 | 2021-12-07 | 中国南方电网有限责任公司超高压输电公司昆明局 | State detection method and device of cooling system, computer equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115933841A (en) * | 2022-12-23 | 2023-04-07 | 南方电网大数据服务有限公司 | Liquid cooling CDU prediction system based on historical information analysis |
| CN115933841B (en) * | 2022-12-23 | 2023-11-07 | 南方电网大数据服务有限公司 | Liquid cooling CDU prediction system based on historical information analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114322446B (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111637924B (en) | Detection method and detection device for abnormality of excavator and readable storage medium | |
| CN112272763B (en) | Abnormality detection device, abnormality detection method, and computer-readable storage medium | |
| CN112254972B (en) | Excavator oil temperature early warning method and device, server and excavator | |
| CN109725220B (en) | Detection method, system and device for transformer oil cooling loop | |
| CN115454778A (en) | Intelligent monitoring system for abnormal time sequence indexes in large-scale cloud network environment | |
| CN114155692A (en) | Equipment fault reporting method, device and storage medium | |
| CN116415126A (en) | Method, device and computing equipment for anomaly detection of doctor blades of paper machine | |
| CN114322446A (en) | Cooling system fault early warning method and device, cooling system and operation machine | |
| CN116000131A (en) | Intelligent operation and maintenance method and system for extruder equipment based on data driving | |
| CN114285612B (en) | Method, system, device, equipment and medium for detecting abnormal data | |
| CN114548280A (en) | Fault diagnosis model training method, fault diagnosis method and electronic equipment | |
| CN112100037B (en) | Alarm level identification method, device, electronic equipment and storage medium | |
| CN112524077A (en) | Method, device and system for detecting fan fault | |
| CN113101734A (en) | Health assessment method, device and system of filter element and mechanical equipment | |
| CN112380759B (en) | Smart electric meter service life prediction method based on deep learning and CoxPH model | |
| CN117435883A (en) | Method and system for predicting equipment faults based on digital twinning | |
| CN117149565A (en) | State detection method, device, equipment and medium for key performance indexes of cloud platform | |
| CN110598680A (en) | Method and system for evaluating health state of mechanical equipment and readable storage medium | |
| KR101982235B1 (en) | Method and device for similar equipment clustering using feature extraction method based on survival function | |
| CN113642123B (en) | Health assessment method and device for heat dissipation system of working machine and working machine | |
| CN113986659A (en) | Fault analysis method, device, equipment and computer storage medium | |
| CN114881112A (en) | System anomaly detection method, device, equipment and medium | |
| CN116412087A (en) | Abnormality detection method and related device for wind generating set | |
| CN112398706B (en) | Data evaluation standard determining method and device, storage medium and electronic equipment | |
| CN114022305A (en) | Underground water dynamic monitoring method and device |
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 |