CN117493787A - Hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis - Google Patents
Hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis Download PDFInfo
- Publication number
- CN117493787A CN117493787A CN202410001162.0A CN202410001162A CN117493787A CN 117493787 A CN117493787 A CN 117493787A CN 202410001162 A CN202410001162 A CN 202410001162A CN 117493787 A CN117493787 A CN 117493787A
- Authority
- CN
- China
- Prior art keywords
- sampling time
- time point
- value
- normalization
- unsynchronized
- 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 35
- 230000005856 abnormality Effects 0.000 title claims abstract description 15
- 238000010219 correlation analysis Methods 0.000 title claims abstract description 15
- 238000005070 sampling Methods 0.000 claims abstract description 325
- 238000010606 normalization Methods 0.000 claims abstract description 222
- 238000011156 evaluation Methods 0.000 claims abstract description 40
- 230000002159 abnormal effect Effects 0.000 claims abstract description 29
- 230000008569 process Effects 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 10
- 230000004044 response Effects 0.000 claims description 43
- 230000008859 change Effects 0.000 claims description 34
- 230000001052 transient effect Effects 0.000 claims description 16
- 238000009826 distribution Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000003111 delayed effect Effects 0.000 claims description 6
- 230000000875 corresponding effect Effects 0.000 description 64
- 238000004364 calculation method Methods 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/20—Hydro energy
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Measuring Fluid Pressure (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis, which comprises the steps of obtaining a pressure normalization time sequence and a flow normalization time sequence in a preset time period in the operation process of a hydraulic valve; according to the asynchronous evaluation index of each sampling time point in the preset period, at least one asynchronous sampling time point is obtained, all the asynchronous sampling time points are classified, weight is adaptively distributed to each data in the pressure normalization time sequence and the flow normalization time sequence, the pearson correlation coefficient between the pressure normalization time sequence and the flow normalization time sequence is obtained according to the weight, abnormal early warning of the operation data of the hydraulic valve is carried out according to the pearson correlation coefficient, the accuracy of correlation analysis between the pressure and the flow of the hydraulic valve is improved, and abnormal operation early warning of the hydraulic valve is reduced.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis.
Background
The hydraulic valve is one of key components in the hydraulic system, and the abnormal operation data of the hydraulic valve can cause the fault of the whole system, so that potential fault signs can be found early by continuously monitoring the operation data of the hydraulic valve, and maintenance or replacement measures can be taken in advance, thereby being beneficial to avoiding the downtime and production interruption of the hydraulic system and reducing the maintenance cost and loss. The monitoring of the operation data index of the common hydraulic valve is mainly that the pressure value and the flow value inside the hydraulic valve are corresponding, the abnormal early warning of the operation data of the hydraulic valve is generally carried out by using a pressure sensor and a flow sensor, the traditional monitoring mode is that a normal numerical value interval is set, when the pressure data or the flow data exceeds the set normal numerical value interval, an alarm system is triggered to realize abnormal prompt, but the mode has a certain limitation on the condition of changeable data characteristics.
In the operation process of the hydraulic valve, the time sequence change trend of the pressure value and the flow value is usually in a synchronous state, namely, the time sequence change trend has strong linear correlation, the increase of the pressure can bring about the increase of the flow, therefore, in the prior art, the abnormal operation early warning of the hydraulic valve is carried out according to the correlation coefficient by analyzing the correlation coefficient between the pressure and the flow of the hydraulic valve, the lower the correlation coefficient is, the abnormal operation of the hydraulic valve is, but the pressure and the flow of the hydraulic valve can be subjected to the normal change trend of asynchronous or unbalanced data caused by the change of the operation requirement or the extension of the hydraulic cylinder (the process that the piston rod of the hydraulic cylinder moves outwards due to the action of the hydraulic pressure), and the analysis of the correlation coefficient between the pressure and the flow can be influenced inaccurately at the moment, so that the abnormal early warning is biased.
Therefore, how to improve the accuracy of the correlation analysis between the pressure and the flow rate of the hydraulic valve to reduce the error of the abnormal operation early warning of the hydraulic valve is a problem to be solved.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis, so as to solve the problem of how to improve the accuracy of correlation analysis between the pressure and the flow of the hydraulic valve and reduce the error of early warning the abnormal operation of the hydraulic valve.
The embodiment of the invention provides a hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis, which comprises the following steps:
in the operation process of the hydraulic valve, respectively acquiring a pressure normalization value and a flow normalization value of each sampling time point to obtain a pressure normalization time sequence and a flow normalization time sequence in a preset period;
for any sampling time point in the preset period, respectively acquiring a pressure normalization value and a flow normalization value of the sampling time point in the pressure normalization time sequence and the flow normalization time sequence, and acquiring an unsynchronized evaluation index of the sampling time point according to the difference between the pressure normalization value and the flow normalization value;
According to the asynchronous evaluation index of each sampling time point in the preset period, at least one asynchronous sampling time point is obtained, and instantaneous and response delay degree analysis is carried out on each asynchronous sampling time point so as to classify all asynchronous sampling time points and obtain a time point classification result;
and respectively carrying out self-adaptive weight distribution on each data in the pressure normalization time sequence and the flow normalization time sequence according to the time point classification result, acquiring a pearson correlation coefficient between the pressure normalization time sequence and the flow normalization time sequence according to the weight, and carrying out abnormal early warning on the operation data of the hydraulic valve according to the pearson correlation coefficient.
Further, the obtaining the unsynchronized evaluation index of the sampling time point according to the difference between the pressure normalized value and the flow normalized value includes:
constructing a first change curve of the pressure normalization time sequence and a second change curve of the flow normalization time sequence, respectively acquiring a first slope value of a pressure normalization value corresponding to each sampling time point in the preset period according to the first change curve to obtain a first slope value average value, and respectively acquiring a second slope value of a flow normalization value corresponding to each sampling time point in the preset period according to the second change curve to obtain a second slope value average value;
Calculating a first difference absolute value between the first slope value average value and the second slope value average value, and calculating a second difference absolute value between the first slope value of the pressure normalization value corresponding to the sampling time point and the second slope value of the corresponding flow normalization value;
and carrying out normalization processing on the absolute value of the difference between the first absolute value of the difference and the second absolute value of the difference, and taking the corresponding obtained normalized value as an unsynchronized evaluation index of the sampling time point.
Further, the obtaining at least one unsynchronized sampling time point according to the unsynchronized evaluation index of each sampling time point in the preset period includes:
acquiring a preset asynchronous evaluation index threshold, and determining that the sampling time point is an asynchronous sampling time point if the asynchronous evaluation index of any sampling time point in the preset period is greater than or equal to the asynchronous evaluation index threshold.
Further, the analyzing the instantaneous and response delay degree of each asynchronous sampling time point to classify all asynchronous sampling time points to obtain a time point classification result includes:
for any unsynchronized sampling time point, according to the number of unsynchronized sampling time points existing in the local range of the unsynchronized sampling time point, acquiring a transient index of the unsynchronized sampling time point, and according to a first slope value difference of a corresponding pressure normalization value and a second slope value difference of a corresponding flow normalization value between the unsynchronized sampling time point and an adjacent sampling time point, acquiring a response delay degree of the unsynchronized sampling time point;
And classifying all the unsynchronized sampling time points according to the instantaneous index and the response delay degree of each unsynchronized sampling time point to obtain a time point classification result.
Further, the obtaining, according to the number of the unsynchronized sampling time points existing in the local range of the unsynchronized sampling time points, the instantaneous index of the unsynchronized sampling time point includes:
forming a local range of the asynchronous sampling time points by a preset number of sampling time points adjacent to each other before and after the asynchronous sampling time points, counting the total number of the sampling time points contained in the local range and the first number of the asynchronous sampling time points, and calculating the ratio between the total number and the first number;
and carrying out normalization processing on the difference value between the constant 1 and the ratio, and taking the normalization result obtained correspondingly as the instantaneous index of the asynchronous sampling time point.
Further, the obtaining the response delay degree of the unsynchronized sampling time point according to the first slope value difference of the pressure normalized value corresponding to the unsynchronized sampling time point and the adjacent sampling time point and the second slope value difference of the flow normalized value corresponding to the unsynchronized sampling time point includes:
Wherein,represents the response delay degree of the jth unsynchronized sampling time point, +.>Representing an exponential function based on a natural constant e, < ->Representing the difference value operation,/->Representing the number of delayed sampling time points of the jth unsynchronized sampling time point, +.>A j-th asynchronous sampling time point>Delay sampling timeFirst slope value of pressure normalization value corresponding to point,/->Represents the j + th>Sample time Point +.>Second slope value of flow normalization value corresponding to each delay sampling time point,/for each delay sampling time point>Represents the delay interval value, N represents the number of sampling time points within a preset period, +.>A first slope value representing a pressure normalization value corresponding to an xth sampling time point, +.>A second slope value representing a flow normalization value corresponding to an xth sampling time point, |represents an absolute value sign, ++>Representing a minimum function;
wherein the delayed sampling time point of the jth asynchronous sampling time point refers to the adjacent sampling time point after the jth asynchronous sampling time pointSampling time points.
Further, the classifying, according to the instantaneous index and the response delay degree of each unsynchronized sampling time point, all unsynchronized sampling time points to obtain a time point classification result includes:
Respectively acquiring a transient index threshold and a response delay degree threshold, and dividing an asynchronous sampling time point into a second type of time point if the transient index of the asynchronous sampling time point is smaller than the transient index threshold and the response delay degree of the asynchronous sampling time point is smaller than the response delay degree threshold aiming at any asynchronous sampling time point;
and if the instantaneous index of the asynchronous sampling time point is greater than or equal to the instantaneous index threshold, or the response delay degree of the asynchronous sampling time point is greater than or equal to the response delay degree threshold, dividing the asynchronous sampling time point into a first type of time point.
Further, the adaptively assigning weights to the data in the pressure normalization timing sequence and the flow normalization timing sequence according to the time point classification result includes:
for any unsynchronized sampling time point in the first type of time points, setting weights of a pressure normalization value and a flow normalization value corresponding to the unsynchronized sampling time point in the pressure normalization time sequence and the flow normalization time sequence as a first preset value;
For any unsynchronized sampling time point in the second class of time points, setting weights of a pressure normalization value and a flow normalization value corresponding to the unsynchronized sampling time point in the pressure normalization time sequence and the flow normalization time sequence as a second preset value;
and setting weights of the pressure normalization value and the flow normalization value corresponding to the sampling time points in the pressure normalization time sequence and the flow normalization time sequence as a constant 1 for any sampling time point of the non-first type time points and the non-second type time points in the preset time period.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
in the operation process of the hydraulic valve, the pressure normalization value and the flow normalization value of each sampling time point are respectively obtained, and a pressure normalization time sequence and a flow normalization time sequence in a preset period are obtained; for any sampling time point in the preset period, respectively acquiring a pressure normalization value and a flow normalization value of the sampling time point in the pressure normalization time sequence and the flow normalization time sequence, and acquiring an unsynchronized evaluation index of the sampling time point according to the difference between the pressure normalization value and the flow normalization value; according to the asynchronous evaluation index of each sampling time point in the preset period, at least one asynchronous sampling time point is obtained, and instantaneous and response delay degree analysis is carried out on each asynchronous sampling time point so as to classify all asynchronous sampling time points and obtain a time point classification result; and respectively carrying out self-adaptive weight distribution on each data in the pressure normalization time sequence and the flow normalization time sequence according to the time point classification result, acquiring a pearson correlation coefficient between the pressure normalization time sequence and the flow normalization time sequence according to the weight, and carrying out abnormal early warning on the operation data of the hydraulic valve according to the pearson correlation coefficient. According to the variation difference in the pressure normalization time sequence and the flow normalization time sequence, sampling time points corresponding to the unsynchronized pressure variation and the unsynchronized flow variation are obtained, and the characteristic classification is carried out on the pressure data and the flow data corresponding to the unsynchronized sampling time points, so that the weight value in the process of calculating the self-adaptive distribution correlation is reduced, the pressure data and the flow data with lower early warning necessity are reduced, the acquisition of the pearson correlation coefficient between the pressure normalization time sequence and the flow normalization time sequence is more practical, and the error of carrying out abnormal operation early warning on the hydraulic valve is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for early warning of abnormal operation data of a hydraulic valve based on pressure-flow correlation analysis according to an embodiment of the present invention.
Detailed Description
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present disclosure and are not to be construed as limiting the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with aspects of the present disclosure.
The data acquisition, storage, use, processing and the like in the technical scheme meet the relevant regulations of national laws and regulations. In order to illustrate the technical scheme of the invention, the following description is made by specific examples.
Referring to fig. 1, a method flowchart of a hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis according to an embodiment of the present invention is shown in fig. 1, where the hydraulic valve operation data abnormality early warning method may include:
step S101, respectively acquiring a pressure normalization value and a flow normalization value of each sampling time point in the operation process of the hydraulic valve, and obtaining a pressure normalization time sequence and a flow normalization time sequence in a preset period.
Specifically, corresponding sensors (pressure sensor and flow sensor) are used for adjusting the same acquisition frequency to acquire pressure data and flow data related to the hydraulic valve in the hydraulic system, and the pressure data and the flow data are recorded, so that the pressure and the flow acquired at each sampling time point can be acquired in the operation process of the hydraulic valve, one sampling time point corresponds to one pressure and one flow, and further a pressure time sequence and a flow time sequence in a preset period are obtained. It is worth to be noted that the invention does not limit the acquisition frequency and the preset time period, and the implementer can set the device according to the implementation scene. Preferably, the acquisition frequency in the embodiment of the invention is 1 second, and the preset time period is 1 hour.
After the pressure time sequence and the flow time sequence are obtained, preprocessing is respectively carried out on the two sequences, wherein the preprocessing comprises data cleaning, noise removal and the like, so that the quality and the accuracy of acquired data are ensured. After preprocessing the pressure time sequence and the flow time sequence, respectively carrying out normalization processing on the pressure time sequence and the flow time sequence, thereby obtaining a pressure normalization value and a flow normalization value of each sampling time point, further forming the pressure normalization value of each sampling time point into a pressure normalization time sequence in a preset period, and similarly forming the flow normalization value of each sampling time point into a flow normalization time sequence in the preset period.
Step S102, for any sampling time point in a preset period, respectively obtaining a pressure normalization value and a flow normalization value of the sampling time point in a pressure normalization time sequence and a flow normalization time sequence, and obtaining an unsynchronized evaluation index of the sampling time point according to the difference between the pressure normalization value and the flow normalization value.
Specifically, considering that the time sequence changes of the pressure data and the flow data of the hydraulic valve are linearly related, that is, as the pressure increases or decreases, the flow will also increase or decrease accordingly, if there is no good synchronism between the pressure and the flow, for example, the pressure fluctuation is large and the flow does not change correspondingly, or the pressure fluctuation is small and the flow does not change correspondingly, it means that there is abnormality in the hydraulic valve, that is, the phenomenon that there is inconsistency or imbalance between the pressure and the flow of the hydraulic valve is also means that there is abnormality in the current hydraulic valve, and attention needs to be paid.
During actual operation of the hydraulic valve, however, it may also be normal for the change between the pressure and the flow of the hydraulic valve to be unsynchronized or offset, for example: when the hydraulic system is started or stopped, because the oil in the hydraulic system needs to be adapted and balanced to achieve a stable running state, a transient out-of-sync or out-of-sync phenomenon may occur due to a large rate of change of pressure and flow, or a transient out-of-sync or out-of-sync between pressure and flow may occur due to a change of working conditions (e.g., load change, temperature change). However, as long as such an asynchronization or imbalance is temporary and returns to a normal state after the hydraulic system is stabilized, such a change is not considered to be abnormal, and the necessity of warning is low. Meanwhile, when the hydraulic valve receives a control signal, an actuating mechanism may need a certain time to adjust and respond, in the process, certain delay and asynchronism may occur between pressure and flow, as long as the delay and the asynchronism are within an acceptable range and can be restored to a normal state after adjustment is completed, the change is not considered to be abnormal, and the early warning necessity is low.
Preferably, the step of obtaining the unsynchronized evaluation index of the sampling time point according to the difference between the pressure normalized value and the flow normalized value includes:
constructing a first change curve of the pressure normalization time sequence and a second change curve of the flow normalization time sequence, respectively acquiring a first slope value of a pressure normalization value corresponding to each sampling time point in the preset period according to the first change curve to obtain a first slope value average value, and respectively acquiring a second slope value of a flow normalization value corresponding to each sampling time point in the preset period according to the second change curve to obtain a second slope value average value;
calculating a first difference absolute value between the first slope value average value and the second slope value average value, and calculating a second difference absolute value between the first slope value of the pressure normalization value corresponding to the sampling time point and the second slope value of the corresponding flow normalization value;
and carrying out normalization processing on the absolute value of the difference between the first absolute value of the difference and the second absolute value of the difference, and taking the corresponding obtained normalized value as an unsynchronized evaluation index of the sampling time point.
In an embodiment, the pressure normalization time sequence and the flow normalization time sequence are mapped in the same two-dimensional feature space, wherein a horizontal axis of the two-dimensional feature space is a sampling time point, a vertical axis of the two-dimensional feature space is data in the pressure normalization time sequence or the flow normalization time sequence, and then a first change curve of the pressure normalization time sequence and a second change curve of the flow normalization time sequence are constructed in the two-dimensional feature space. And carrying out first-order derivation on the first change curve to obtain a first slope value of the pressure normalization value corresponding to each sampling time point on the first change curve, and similarly carrying out first-order derivation on the second change curve to obtain a second slope value of the flow normalization value corresponding to each sampling time point on the second change curve, so that the first slope value of the pressure normalization value corresponding to each sampling time point and the second slope value of the corresponding flow normalization value can be obtained. Taking the ith sampling time point in the preset period as an example, according to the first slope value of the pressure normalization value corresponding to the ith sampling time point and the second slope value of the corresponding flow normalization value, acquiring an unsynchronized evaluation index of the ith sampling time point, and then calculating the unsynchronized evaluation index of the ith sampling time point to obtain the calculation expression of the unsynchronized evaluation index of the ith sampling time point:
Wherein,an unsynchronized evaluation index representing the ith sampling time point,>representing normalization functions，A first slope value representing a pressure normalization value corresponding to an ith sampling time point, +.>A second slope value representing a flow normalization value corresponding to the ith sampling time point, +.>A first slope value mean value representing pressure normalization values corresponding to all sampling time points within a preset period,/>A second slope value mean value of flow normalization values corresponding to all sampling time points in a preset period, wherein N represents the number of sampling time points in the preset period, +.>A first slope value representing a pressure normalization value corresponding to a jth sampling time point, +.>And a second slope value representing a flow normalization value corresponding to the j-th sampling time point, and I represents an absolute value sign.
The absolute value of the difference between the first slope value of the pressure normalized value corresponding to the i-th sampling time point and the second slope value of the flow normalized value corresponding to the i-th sampling time point is calculatedFor representing synchronous difference between pressure and flow of the ith sampling time point, calculating first difference absolute value +_x between first slope value average of pressure normalization values corresponding to all sampling time points in a preset period and second slope value average of flow normalization values corresponding to all sampling time points in the preset period >For characterizing a reference synchronization difference between the pressure and the flow in a preset period, therefore, by calculating the absolute value of the difference between the synchronization difference at the i-th sampling time point and the reference synchronization difference in the preset period ∈ ->For characterizing the unsynchronized difference characteristic of the ith sampling time point, +.>The larger the value of (c) is, the more the pressure and the flow corresponding to the ith sampling time point are not synchronous, the more obvious the characteristics of the asynchronous change are, and the larger the asynchronous evaluation index corresponding to the ith sampling time point is.
Step S103, according to the unsynchronized evaluation index of each sampling time point in the preset period, at least one unsynchronized sampling time point is obtained, and the instantaneous and response delay degree analysis is carried out on each unsynchronized sampling time point so as to classify all the unsynchronized sampling time points and obtain a time point classification result.
Specifically, according to the method of step S102, an unsynchronized evaluation index of each sampling time point in the preset period can be obtained, and then at least one unsynchronized sampling time point is obtained according to the unsynchronized evaluation index of each sampling time point in the preset period, that is, a sampling time point with obvious unsynchronized variation characteristics between pressure and flow is obtained by screening, and then at least one unsynchronized sampling time point is obtained according to the unsynchronized evaluation index of each sampling time point in the preset period, including:
Acquiring a preset asynchronous evaluation index threshold, and determining that the sampling time point is an asynchronous sampling time point if the asynchronous evaluation index of any sampling time point in the preset period is greater than or equal to the asynchronous evaluation index threshold.
In an embodiment, the threshold of the unsynchronized evaluation index is set to 0.7, if the unsynchronized evaluation index of any sampling time point in the preset period is greater than or equal to 0.7, the sampling time point is determined to be an unsynchronized sampling time point, otherwise, the unsynchronized sampling time point belongs to a synchronous sampling time point. In the embodiment of the invention, the setting of the asynchronous evaluation index threshold is not limited, and the asynchronous evaluation index threshold can be adaptively set according to the implementation scene.
Further, after determining the asynchronous sampling time points with obvious asynchronous change characteristics between the pressure and the flow in the preset period, performing feature analysis of instantaneity and response delay degree on each asynchronous sampling time point to classify the asynchronous sampling time points into a category with lower abnormality early warning necessity and a category with higher abnormality early warning necessity, and performing transient and response delay degree analysis on each asynchronous sampling time point to classify all the asynchronous sampling time points to obtain a time point classification result, wherein the specific classification process is as follows:
(1) For any unsynchronized sampling time point, according to the number of unsynchronized sampling time points existing in the local range of the unsynchronized sampling time point, acquiring a transient index of the unsynchronized sampling time point, and according to a first slope value difference of a corresponding pressure normalization value and a second slope value difference of a corresponding flow normalization value between the unsynchronized sampling time point and an adjacent sampling time point, acquiring a response delay degree of the unsynchronized sampling time point.
Wherein, according to the number of the asynchronous sampling time points existing in the local range of the asynchronous sampling time points, acquiring the instantaneous index of the asynchronous sampling time points comprises:
forming a local range of the asynchronous sampling time points by a preset number of sampling time points adjacent to each other before and after the asynchronous sampling time points, counting the total number of the sampling time points contained in the local range and the first number of the asynchronous sampling time points, and calculating the ratio between the total number and the first number;
and carrying out normalization processing on the difference value between the constant 1 and the ratio, and taking the normalization result obtained correspondingly as the instantaneous index of the asynchronous sampling time point.
In one embodiment, taking the jth asynchronous sampling time point as an example, the sampling time point is within a preset periodSelecting adjacent front and back of the jth unsynchronized sampling time point by taking the jth unsynchronized sampling time point as the centerThe sampling time points form the local range of the j-th unsynchronized sampling time point, namely the front adjacent of the j-th unsynchronized sampling time point +.>Sampling time points and post-neighbors->The sampling time points form the local range of the j asynchronous sampling time points, and preferably, the embodiment of the invention setsAcquiring the instantaneous index of the jth unsynchronized sampling time point according to the number of the unsynchronized sampling time points existing in the local range of the jth unsynchronized sampling time point, wherein the calculation expression of the instantaneous index of the jth unsynchronized sampling time point is as follows:
wherein,transient index indicating the jth unsynchronized sampling time point,/for the sampling time point>Represents a normalization function, 1 represents a constant, +.>Representing the number of asynchronous sample time points present within the local range of the jth asynchronous sample time point,representing the total number of sampling time points contained within the local range of the jth unsynchronized sampling time point。
The more the number of asynchronous sampling time points existing in the local range of the jth asynchronous sampling time point, the more the frequency of the asynchronous sampling time points is shown, the more the jth asynchronous sampling time point is shown to be not in instantaneous occurrence, and the lower the instantaneous index corresponding to the jth asynchronous sampling time point is shown to be.
The method comprises the steps of obtaining a response delay degree of an unsynchronized sampling time point according to a first slope value difference of a pressure normalization value corresponding to the unsynchronized sampling time point and an adjacent sampling time point and a second slope value difference of a corresponding flow normalization value, wherein the response delay degree of the unsynchronized sampling time point is specifically: taking the jth asynchronous sampling time point as an example, the jth asynchronous sampling time point is followed by an adjacent asynchronous sampling time pointAs the delay sampling time point, preferably +.>At the same time set the delay interval value +.>And let->The j-th asynchronous sampling time point>Obtaining the +.>First slope value of pressure normalization value corresponding to each delay sampling time point +.>And j +>Sample time Point +.>Second slope value of flow normalization value corresponding to each delay sampling time point +.>Obtaining the absolute value of the difference between the first slope value and the second slope value +.>Each delay sampling time point of the jth unsynchronized sampling time point and the jth +.>The mean absolute value of the difference between each of the delayed sampling time points of the sampling time points +.>Calculating the absolute value mean of the difference value->Absolute value of difference from first >The absolute value of the difference between them, in the same way, in the delay interval value +.>Obtaining the absolute value of the difference corresponding to each delay interval value, taking the absolute value of the minimum difference, carrying out negative mapping on the absolute value of the minimum difference, and taking the corresponding obtained mapping value as the response delay degree of the jth unsynchronized sampling time point, wherein the calculation expression of the response delay degree of the jth unsynchronized sampling time point is as follows:
wherein,represents the response delay degree of the jth unsynchronized sampling time point, +.>Representing an exponential function based on a natural constant e, < ->Representing the difference value operation,/->Representing the number of delayed sampling time points of the jth unsynchronized sampling time point, +.>A j-th asynchronous sampling time point>First slope value of pressure normalization value corresponding to each delay sampling time point,/for>Represents the j + th>Sample time Point +.>Second slope value of flow normalization value corresponding to each delay sampling time point,/for each delay sampling time point>Represents the delay interval value, N represents the number of sampling time points within a preset period, +.>A first slope value representing a pressure normalization value corresponding to an xth sampling time point, +.>A second slope value representing a flow normalization value corresponding to an xth sampling time point, |represents an absolute value sign, ++ >Representing taking the minimum functionA number.
By calculation ofFor characterizing the pressure data of the jth unsynchronized sampling time point with its neighboring sampling time points (jth->Slope difference between flow data at sampling time points) from the first absolute difference value +.>The smaller the difference, the j-th asynchronous sampling time point and the j-th asynchronous sampling time point are described>The sampling time points have delay, and the greater the corresponding response delay degree is, if the difference is greater, the j-th unsynchronized sampling time point and the j-th unsynchronized sampling time point are described>There is no delay between the sampling time points, which belongs to the normal variation difference of the data fluctuation.
(2) And classifying all the unsynchronized sampling time points according to the instantaneous index and the response delay degree of each unsynchronized sampling time point to obtain a time point classification result.
Specifically, a transient index threshold and a response delay degree threshold are respectively obtained, and for any unsynchronized sampling time point, if the transient index of the unsynchronized sampling time point is smaller than the transient index threshold and the response delay degree of the unsynchronized sampling time point is smaller than the response delay degree threshold, the unsynchronized sampling time point is divided into a second type of time point;
And if the instantaneous index of the asynchronous sampling time point is greater than or equal to the instantaneous index threshold, or the response delay degree of the asynchronous sampling time point is greater than or equal to the response delay degree threshold, dividing the asynchronous sampling time point into a first type of time point.
In one embodiment, the instantaneous index threshold and the response delay degree threshold are set to be 0.8, and the conditions for classifying all asynchronous sampling time points are as follows:
wherein,representing a first type of time point,/->Representing a second class of points in time.
It should be noted that, the first time point refers to a sampling time point with a larger influence on the correlation between the pressure normalization time sequence and the flow normalization time sequence calculated later, that is, a category with higher abnormality early warning necessity; the second time point is a sampling time point with smaller influence on the correlation between the pressure normalization time sequence and the flow normalization time sequence calculated later, namely, a category with lower abnormality early warning necessity.
And step S104, respectively carrying out self-adaptive weight distribution on each data in the pressure normalization time sequence and the flow normalization time sequence according to the time point classification result, acquiring a Pearson correlation coefficient between the pressure normalization time sequence and the flow normalization time sequence according to the weight, and carrying out abnormal early warning on the operation data of the hydraulic valve according to the Pearson correlation coefficient.
After classifying all the unsynchronized sampling time points in the preset period, respectively carrying out self-adaptive weight distribution on each data in the pressure normalization time sequence and the flow normalization time sequence according to the time point classification result so as to reduce the influence degree of the pressure normalization value and the flow normalization value corresponding to the unsynchronized sampling time point with lower abnormal early warning necessity on the subsequent correlation analysis, wherein the specific process of weight distribution is as follows:
for any unsynchronized sampling time point in the first type of time points, setting weights of a pressure normalization value and a flow normalization value corresponding to the unsynchronized sampling time point in the pressure normalization time sequence and the flow normalization time sequence as a first preset value;
for any unsynchronized sampling time point in the second class of time points, setting weights of a pressure normalization value and a flow normalization value corresponding to the unsynchronized sampling time point in the pressure normalization time sequence and the flow normalization time sequence as a second preset value;
and setting weights of the pressure normalization value and the flow normalization value corresponding to the sampling time points in the pressure normalization time sequence and the flow normalization time sequence as a constant 1 for any sampling time point of the non-first type time points and the non-second type time points in the preset time period.
Further, after weighting each of the pressure normalization timing sequence and the flow normalization timing sequence, a weighted correlation analysis is performed on the pressure normalization timing sequence and the flow normalization timing sequence. Specifically, since the weights of the pressure normalization value and the flow normalization value corresponding to each sampling time point in the preset period are the same and the weights of different sampling time points are different, when the pearson correlation coefficient is calculated, the pearson correlation coefficient weighted by the data in the pressure normalization time sequence and the data in the flow normalization time sequence is obtained as a final correlation analysis result between the pressure normalization time sequence and the flow normalization time sequence.
It should be noted that, the pearson correlation coefficient belongs to the prior art, and is not described herein in detail.
After the pearson correlation coefficient between the pressure normalization time sequence and the flow normalization time sequence is determined, comparing the pearson correlation coefficient with a preset correlation threshold, if the pearson correlation coefficient is smaller than or equal to the preset correlation threshold, indicating that no good synchronism exists between the pressure and the flow of the hydraulic valve in a preset period, determining that the hydraulic valve is abnormal, otherwise, if the pearson correlation coefficient is larger than the preset correlation threshold, indicating that the time sequence change between the pressure and the flow of the hydraulic valve in the preset period is linearly correlated, and determining that the hydraulic valve is in a normal running state.
In summary, in the operation process of the hydraulic valve, the pressure normalization value and the flow normalization value of each sampling time point are respectively obtained, so as to obtain a pressure normalization time sequence and a flow normalization time sequence in a preset period; for any sampling time point in a preset period, respectively acquiring a pressure normalization value and a flow normalization value of the sampling time point in a pressure normalization time sequence and a flow normalization time sequence, and acquiring an unsynchronized evaluation index of the sampling time point according to the difference between the pressure normalization value and the flow normalization value; according to the asynchronous evaluation index of each sampling time point in the preset period, at least one asynchronous sampling time point is obtained, and instantaneous and response delay degree analysis is carried out on each asynchronous sampling time point so as to classify all the asynchronous sampling time points and obtain a time point classification result; and respectively carrying out self-adaptive weight distribution on each data in the pressure normalization time sequence and the flow normalization time sequence according to the time point classification result, acquiring a pearson correlation coefficient between the pressure normalization time sequence and the flow normalization time sequence according to the weight, and carrying out abnormal early warning on the operation data of the hydraulic valve according to the pearson correlation coefficient. According to the variation difference in the pressure normalization time sequence and the flow normalization time sequence, sampling time points corresponding to the unsynchronized pressure variation and the unsynchronized flow variation are obtained, and the characteristic classification is carried out on the pressure data and the flow data corresponding to the unsynchronized sampling time points, so that the weight value in the process of calculating the self-adaptive distribution correlation is reduced, the pressure data and the flow data with lower early warning necessity are reduced, the acquisition of the pearson correlation coefficient between the pressure normalization time sequence and the flow normalization time sequence is more practical, and the error of carrying out abnormal operation early warning on the hydraulic valve is reduced.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the 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 scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (8)
1. The hydraulic valve operation data abnormality early warning method based on the pressure flow correlation analysis is characterized by comprising the following steps of:
in the operation process of the hydraulic valve, respectively acquiring a pressure normalization value and a flow normalization value of each sampling time point to obtain a pressure normalization time sequence and a flow normalization time sequence in a preset period;
for any sampling time point in the preset period, respectively acquiring a pressure normalization value and a flow normalization value of the sampling time point in the pressure normalization time sequence and the flow normalization time sequence, and acquiring an unsynchronized evaluation index of the sampling time point according to the difference between the pressure normalization value and the flow normalization value;
According to the asynchronous evaluation index of each sampling time point in the preset period, at least one asynchronous sampling time point is obtained, and instantaneous and response delay degree analysis is carried out on each asynchronous sampling time point so as to classify all asynchronous sampling time points and obtain a time point classification result;
and respectively carrying out self-adaptive weight distribution on each data in the pressure normalization time sequence and the flow normalization time sequence according to the time point classification result, acquiring a pearson correlation coefficient between the pressure normalization time sequence and the flow normalization time sequence according to the weight, and carrying out abnormal early warning on the operation data of the hydraulic valve according to the pearson correlation coefficient.
2. The method for early warning of abnormal operation data of a hydraulic valve according to claim 1, wherein the step of obtaining the unsynchronized evaluation index of the sampling time point according to the difference between the pressure normalized value and the flow normalized value includes:
constructing a first change curve of the pressure normalization time sequence and a second change curve of the flow normalization time sequence, respectively acquiring a first slope value of a pressure normalization value corresponding to each sampling time point in the preset period according to the first change curve to obtain a first slope value average value, and respectively acquiring a second slope value of a flow normalization value corresponding to each sampling time point in the preset period according to the second change curve to obtain a second slope value average value;
Calculating a first difference absolute value between the first slope value average value and the second slope value average value, and calculating a second difference absolute value between the first slope value of the pressure normalization value corresponding to the sampling time point and the second slope value of the corresponding flow normalization value;
and carrying out normalization processing on the absolute value of the difference between the first absolute value of the difference and the second absolute value of the difference, and taking the corresponding obtained normalized value as an unsynchronized evaluation index of the sampling time point.
3. The method for warning of abnormal operation data of a hydraulic valve according to claim 1, wherein the obtaining at least one unsynchronized sampling time point according to the unsynchronized evaluation index of each sampling time point in the preset period comprises:
acquiring a preset asynchronous evaluation index threshold, and determining that the sampling time point is an asynchronous sampling time point if the asynchronous evaluation index of any sampling time point in the preset period is greater than or equal to the asynchronous evaluation index threshold.
4. The method for warning of abnormal operation data of a hydraulic valve according to claim 2, wherein the analyzing the instantaneous and response delay degree of each unsynchronized sampling time point to classify all unsynchronized sampling time points to obtain a time point classification result comprises:
For any unsynchronized sampling time point, according to the number of unsynchronized sampling time points existing in the local range of the unsynchronized sampling time point, acquiring a transient index of the unsynchronized sampling time point, and according to a first slope value difference of a corresponding pressure normalization value and a second slope value difference of a corresponding flow normalization value between the unsynchronized sampling time point and an adjacent sampling time point, acquiring a response delay degree of the unsynchronized sampling time point;
and classifying all the unsynchronized sampling time points according to the instantaneous index and the response delay degree of each unsynchronized sampling time point to obtain a time point classification result.
5. The method for warning of abnormal operation data of a hydraulic valve according to claim 4, wherein the obtaining the instantaneous index of the unsynchronized sampling time point according to the number of unsynchronized sampling time points existing in the local range of the unsynchronized sampling time point includes:
forming a local range of the asynchronous sampling time points by a preset number of sampling time points adjacent to each other before and after the asynchronous sampling time points, counting the total number of the sampling time points contained in the local range and the first number of the asynchronous sampling time points, and calculating the ratio between the total number and the first number;
And carrying out normalization processing on the difference value between the constant 1 and the ratio, and taking the normalization result obtained correspondingly as the instantaneous index of the asynchronous sampling time point.
6. The method for warning of abnormal operation data of a hydraulic valve according to claim 4, wherein the obtaining the response delay degree of the unsynchronized sampling time point according to the first slope value difference of the corresponding pressure normalized value and the second slope value difference of the corresponding flow normalized value between the unsynchronized sampling time point and the adjacent sampling time point comprises:
wherein,represents the response delay degree of the jth unsynchronized sampling time point, +.>Representing an exponential function based on a natural constant e, < ->Representing the difference value operation,/->Representing the number of delayed sampling time points of the jth unsynchronized sampling time point, +.>A j-th asynchronous sampling time point>First slope value of pressure normalization value corresponding to each delay sampling time point,/for>Represents the j + th>Sample time Point +.>Second slope value of flow normalization value corresponding to each delay sampling time point,/for each delay sampling time point>Represents a delay interval value, N represents a preset time periodIs >A first slope value representing a pressure normalization value corresponding to an xth sampling time point, +.>A second slope value representing a flow normalization value corresponding to an xth sampling time point, |represents an absolute value sign, ++>Representing a minimum function;
wherein the delayed sampling time point of the jth asynchronous sampling time point refers to the adjacent sampling time point after the jth asynchronous sampling time pointSampling time points.
7. The method for warning of abnormal operation data of a hydraulic valve according to claim 4, wherein the classifying all the unsynchronized sampling time points according to the instantaneous index and the response delay degree of each unsynchronized sampling time point to obtain a time point classification result comprises:
respectively acquiring a transient index threshold and a response delay degree threshold, and dividing an asynchronous sampling time point into a second type of time point if the transient index of the asynchronous sampling time point is smaller than the transient index threshold and the response delay degree of the asynchronous sampling time point is smaller than the response delay degree threshold aiming at any asynchronous sampling time point;
and if the instantaneous index of the asynchronous sampling time point is greater than or equal to the instantaneous index threshold, or the response delay degree of the asynchronous sampling time point is greater than or equal to the response delay degree threshold, dividing the asynchronous sampling time point into a first type of time point.
8. The method for warning of abnormal operation data of a hydraulic valve according to claim 7, wherein the adaptively assigning weights to the data in the pressure normalization timing sequence and the flow normalization timing sequence according to the time point classification result, respectively, comprises:
for any unsynchronized sampling time point in the first type of time points, setting weights of a pressure normalization value and a flow normalization value corresponding to the unsynchronized sampling time point in the pressure normalization time sequence and the flow normalization time sequence as a first preset value;
for any unsynchronized sampling time point in the second class of time points, setting weights of a pressure normalization value and a flow normalization value corresponding to the unsynchronized sampling time point in the pressure normalization time sequence and the flow normalization time sequence as a second preset value;
and setting weights of the pressure normalization value and the flow normalization value corresponding to the sampling time points in the pressure normalization time sequence and the flow normalization time sequence as a constant 1 for any sampling time point of the non-first type time points and the non-second type time points in the preset time period.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410001162.0A CN117493787B (en) | 2024-01-02 | 2024-01-02 | Hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410001162.0A CN117493787B (en) | 2024-01-02 | 2024-01-02 | Hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117493787A true CN117493787A (en) | 2024-02-02 |
| CN117493787B CN117493787B (en) | 2024-03-15 |
Family
ID=89671210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410001162.0A Active CN117493787B (en) | 2024-01-02 | 2024-01-02 | Hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117493787B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118066183A (en) * | 2024-04-19 | 2024-05-24 | 浙江威星电子系统软件股份有限公司 | Pressure control valve tightness detection method |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005002808A (en) * | 2003-06-10 | 2005-01-06 | Hitachi Unisia Automotive Ltd | Leakage diagnosis device for evaporated fuel processing device |
| WO2020052147A1 (en) * | 2018-09-11 | 2020-03-19 | 清华大学合肥公共安全研究院 | Monitoring device fault detection method and apparatus |
| US20220137611A1 (en) * | 2020-11-05 | 2022-05-05 | Kabushiki Kaisha Toshiba | Abnormality determination apparatus, learning apparatus and abnormality determination method |
| CN115796408A (en) * | 2023-02-13 | 2023-03-14 | 成都秦川物联网科技股份有限公司 | Gas transmission loss prediction method for smart gas and Internet of things system |
| US20230211515A1 (en) * | 2020-06-24 | 2023-07-06 | Edgewell Personal Care Brands, Llc | Machine learning for a personal care device |
| CN116414076A (en) * | 2023-06-12 | 2023-07-11 | 济宁长兴塑料助剂有限公司 | Intelligent monitoring system for recovered alcohol production data |
| CN116611674A (en) * | 2023-07-20 | 2023-08-18 | 中建五局第三建设有限公司 | Intelligent dispatching operation method for building supply water |
| CN116702473A (en) * | 2023-06-08 | 2023-09-05 | 江苏国电南自海吉科技有限公司 | Clustering algorithm-based transformer temperature abnormality early warning method and system |
| CN116908619A (en) * | 2023-07-23 | 2023-10-20 | 哈尔滨理工大学 | Harmonic source positioning method based on space-time diagram attention convolution network |
| CN117078490A (en) * | 2023-10-17 | 2023-11-17 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Urban small micro water body risk assessment method based on synchronous analysis of multiple factors |
| CN117268743A (en) * | 2023-11-22 | 2023-12-22 | 山东力威液压技术有限公司 | Fault diagnosis method for proportional flow valve |
| CN117278314A (en) * | 2023-10-24 | 2023-12-22 | 中南林业科技大学 | DDoS attack detection method |
-
2024
- 2024-01-02 CN CN202410001162.0A patent/CN117493787B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005002808A (en) * | 2003-06-10 | 2005-01-06 | Hitachi Unisia Automotive Ltd | Leakage diagnosis device for evaporated fuel processing device |
| WO2020052147A1 (en) * | 2018-09-11 | 2020-03-19 | 清华大学合肥公共安全研究院 | Monitoring device fault detection method and apparatus |
| US20230211515A1 (en) * | 2020-06-24 | 2023-07-06 | Edgewell Personal Care Brands, Llc | Machine learning for a personal care device |
| US20220137611A1 (en) * | 2020-11-05 | 2022-05-05 | Kabushiki Kaisha Toshiba | Abnormality determination apparatus, learning apparatus and abnormality determination method |
| CN115796408A (en) * | 2023-02-13 | 2023-03-14 | 成都秦川物联网科技股份有限公司 | Gas transmission loss prediction method for smart gas and Internet of things system |
| CN116702473A (en) * | 2023-06-08 | 2023-09-05 | 江苏国电南自海吉科技有限公司 | Clustering algorithm-based transformer temperature abnormality early warning method and system |
| CN116414076A (en) * | 2023-06-12 | 2023-07-11 | 济宁长兴塑料助剂有限公司 | Intelligent monitoring system for recovered alcohol production data |
| CN116611674A (en) * | 2023-07-20 | 2023-08-18 | 中建五局第三建设有限公司 | Intelligent dispatching operation method for building supply water |
| CN116908619A (en) * | 2023-07-23 | 2023-10-20 | 哈尔滨理工大学 | Harmonic source positioning method based on space-time diagram attention convolution network |
| CN117078490A (en) * | 2023-10-17 | 2023-11-17 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Urban small micro water body risk assessment method based on synchronous analysis of multiple factors |
| CN117278314A (en) * | 2023-10-24 | 2023-12-22 | 中南林业科技大学 | DDoS attack detection method |
| CN117268743A (en) * | 2023-11-22 | 2023-12-22 | 山东力威液压技术有限公司 | Fault diagnosis method for proportional flow valve |
Non-Patent Citations (2)
| Title |
|---|
| 董深;吕谋;盛泽斌;李璞;: "基于遗传算法的供水管网反问题漏失定位", 哈尔滨工业大学学报, no. 02, 28 February 2013 (2013-02-28), pages 112 - 116 * |
| 陈刚;: "时间序列相关性分析研究", 现代信息科技, no. 13, 10 July 2020 (2020-07-10), pages 13 - 16 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118066183A (en) * | 2024-04-19 | 2024-05-24 | 浙江威星电子系统软件股份有限公司 | Pressure control valve tightness detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117493787B (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117493787B (en) | Hydraulic valve operation data abnormality early warning method based on pressure flow correlation analysis | |
| CN107908835B (en) | Method for analyzing landslide dynamic response condition under multiple influence factors | |
| CN113518011B (en) | Abnormality detection method and apparatus, electronic device, and computer-readable storage medium | |
| CN117407700B (en) | Method for monitoring working environment in live working process | |
| CN104181883A (en) | Method for processing abnormal data of real-time data acquisition system in real time | |
| CN107172128B (en) | Cloud-assisted manufacturing equipment big data acquisition method | |
| CN111179591B (en) | Road network traffic time sequence characteristic data quality diagnosis and restoration method | |
| CN110175353B (en) | Trend analysis method for elevator operation index | |
| CN109615126A (en) | A kind of bearing residual life prediction technique | |
| CN108680798B (en) | Lightning monitoring and early warning method and system | |
| CN117195137B (en) | Rotor die casting error detecting system based on data analysis | |
| CN113219910A (en) | Full-flow production self-diagnosis and optimization system | |
| CN116881673B (en) | Shield tunneling machine operation and maintenance method based on big data analysis | |
| CN117113263B (en) | Real-time monitoring method for bridge pushing structure | |
| CN114978956A (en) | Method and device for detecting abnormal performance mutation points of network equipment in smart city | |
| CN114548311B (en) | Hydraulic equipment intelligent control system based on artificial intelligence | |
| CN117807550A (en) | Intelligent quantitative detection method and system for building fire-fighting facilities | |
| CN117150244B (en) | Intelligent power distribution cabinet state monitoring method and system based on electrical parameter analysis | |
| JP2000509178A (en) | Automatic control loop monitoring and diagnostics | |
| CN113032239A (en) | Risk prompting method and device, electronic equipment and storage medium | |
| CN112749035B (en) | Abnormality detection method, abnormality detection device, and computer-readable medium | |
| CN117591964A (en) | Electric power intelligent analysis method based on artificial intelligence | |
| CN111339155B (en) | Correlation analysis system | |
| CN113758627B (en) | Water supply network transient flow event detection method | |
| CN114662058A (en) | Wireless station 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 |