CN117932322B - Flour equipment fault diagnosis method and system - Google Patents
Flour equipment fault diagnosis method and system Download PDFInfo
- Publication number
- CN117932322B CN117932322B CN202410330010.5A CN202410330010A CN117932322B CN 117932322 B CN117932322 B CN 117932322B CN 202410330010 A CN202410330010 A CN 202410330010A CN 117932322 B CN117932322 B CN 117932322B
- Authority
- CN
- China
- Prior art keywords
- fault
- equipment
- data
- interaction
- flour
- 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.)
- Active
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 62
- 235000013312 flour Nutrition 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000007613 environmental effect Effects 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 44
- 230000003993 interaction Effects 0.000 claims abstract description 41
- 238000012423 maintenance Methods 0.000 claims abstract description 28
- 230000002159 abnormal effect Effects 0.000 claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 17
- 230000000694 effects Effects 0.000 claims abstract description 16
- 238000012482 interaction analysis Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims description 32
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000012544 monitoring process Methods 0.000 claims description 20
- 238000012706 support-vector machine Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 12
- 230000003068 static effect Effects 0.000 claims description 12
- 238000004140 cleaning Methods 0.000 claims description 11
- 239000000428 dust Substances 0.000 claims description 9
- 238000011161 development Methods 0.000 claims description 7
- 238000012300 Sequence Analysis Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 6
- 230000008901 benefit Effects 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000000556 factor analysis Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000003449 preventive effect Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 230000007257 malfunction Effects 0.000 claims 9
- 239000002131 composite material Substances 0.000 abstract 1
- 238000004519 manufacturing process Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008846 dynamic interplay Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of flour equipment, in particular to a flour equipment fault diagnosis method and system, which comprises the following steps: s1, collecting comprehensive environment and equipment operation data: collecting data related to the flour processing environment and the operation of the equipment in real time by using various sensors; s2, data preprocessing and anomaly detection: identifying an abnormal signal in the data; s3, device interaction analysis: identifying a device interaction pattern that results in a fault signal; s4, comprehensively analyzing the fault mode and the environmental factors: analyzing the fault cause; s5, fault diagnosis and prediction: diagnosing the current fault and predicting the future fault of the equipment; s6, feeding back and optimizing maintenance effects: and feeding back the maintained equipment performance data. The invention can effectively identify and solve the faults caused by the interaction among the equipment and the composite action of environmental factors, and remarkably improve the operation efficiency and stability of flour processing equipment.
Description
Technical Field
The invention relates to the technical field of flour equipment, in particular to a flour equipment fault diagnosis method and system.
Background
In the flour processing industry, timely diagnosis and prevention of equipment faults plays a vital role in guaranteeing production efficiency and product quality, traditional fault diagnosis methods often depend on experience of equipment operators or simple sensor monitoring, and when complex equipment interaction and changeable environmental factors are processed, the methods often look out of mind, and especially on modern flour processing production lines, the interdependence among equipment and the influence of environmental factors such as temperature and humidity, dust and the like on equipment performance make fault diagnosis a complex and changeable challenge.
With the development of information technology and automation technology, although it is easier to collect operation data of devices, how to accurately extract information related to faults from massive data, identify fault modes, predict future potential faults, and evaluate influence of environmental factors is still a problem to be solved urgently, and in addition, complex interactions between devices often cause rapid propagation of faults, which brings additional difficulty to accurate diagnosis and timely response.
Disclosure of Invention
Based on the above purpose, the invention provides a flour equipment fault diagnosis method and system.
A flour machine fault diagnosis method comprising the steps of:
S1, collecting comprehensive environment and equipment operation data: collecting data related to the flour processing environment and the operation of the equipment in real time by using various sensors;
S2, data preprocessing and anomaly detection: cleaning and preprocessing the collected data by a data processing technology, and identifying abnormal signals in the data;
s3, device interaction analysis: analyzing interaction and dependency relationship among devices, and identifying a device interaction mode causing a fault signal;
S4, comprehensively analyzing the fault mode and the environmental factors: using a dynamic PCA algorithm, comprehensively considering the influences of a fault mode, equipment interaction and environmental factors, and analyzing fault reasons;
s5, fault diagnosis and prediction: based on the comprehensive analysis result, diagnosing the current fault and predicting the future fault of the equipment;
s6, feeding back and optimizing maintenance effects: and feeding back the maintained equipment performance data, and optimizing the accuracy of fault diagnosis.
Further, the plurality of sensors specifically includes:
Temperature sensor: the method is used for monitoring the temperatures of equipment and a processing environment and identifying overheat or temperature abnormality;
humidity sensor: the device is used for monitoring the humidity level of the processing environment and preventing the quality of flour and the normal operation of equipment from being influenced by the excessively high or excessively low humidity;
Vibration sensor: the method is used for monitoring the vibration frequency and amplitude of equipment and identifying abnormal operation states of the equipment, including unbalance, dislocation or bearing faults;
a current sensor: the method comprises the steps of monitoring the current use condition of equipment and identifying an electrical fault or equipment overload condition;
Dust particle size and concentration sensor: monitoring the granularity and concentration of dust in the air aiming at the flour processing environment, and evaluating the air quality and the equipment blockage risk;
A sound sensor: the method is used for capturing sounds generated during the running of the device and identifying the abnormal state of the device.
Further, the data preprocessing and anomaly detection in S2 includes:
S21, data cleaning: cleaning the collected data, including removing invalid data, correcting erroneous data points and filling missing values;
S22, data standardization: carrying out standardization treatment on the cleaned data, wherein the standardization treatment comprises normalization, standard deviation standardization or minimum-maximum scaling;
s23, feature extraction: extracting features from the normalized data;
s24, abnormal signal identification: performing anomaly detection on the extracted features based on a preset threshold;
S25, recording and reporting abnormal events: recording the identified abnormal signals, and generating an abnormal event report including the time, the position, the intensity and the fault type of the abnormality.
Further, the device interaction analysis in S3 includes:
S31, constructing a device interaction graph model (DIG): constructing an equipment interaction graph model, wherein nodes represent flour processing equipment, edges represent interaction among the equipment, and each edge is endowed with a dynamic dependency index DDI for quantifying the interaction degree among the equipment;
S32, calculating a dynamic dependency index DDI: for each pair of devices i and j in the model, calculating a dynamic dependence index DDI ij (t) of the device i on the device j at a time t by combining the static priority index and the dynamic performance influence index, wherein the calculation formula is as follows:
DDIij(t)＝λ·SPIij+(1-λ)·DPIij(t)；
Wherein SPI ij is the static priority index, DPI ij (t) is the dynamic performance impact index, λ is the adjustment parameter;
S33, identifying a fault propagation path: based on the calculated DDI value, adopting Dijkstra algorithm to identify a fault propagation path;
s34, analyzing the interaction mode of the equipment: and analyzing the specific device interaction mode which leads to the fault signal by comprehensively considering DDI values and fault propagation paths among the devices.
Further, the dynamic performance impact index DPI ij (t) is based on a correlation coefficient and a covariance of a correlation operation parameter between a parameter X of the device i and a parameter Y of the device j, and a calculation formula is as follows:
Wherein ρ (X i(t),Yj (t)) represents the correlation coefficient of the parameter X of the device i and the parameter Y of the device j at time t, The covariance of X i and Y j at time t is shown for quantifying trend dependence between the two parameters.
Further, the Dijkstra algorithm is used for searching the shortest path, for flour equipment fault diagnosis, the dependency relationship between equipment and the fault influence are dynamically changed, the Dijkstra algorithm reflects the dynamics by introducing a time and state dependent weight adjustment mechanism, the DDI value of each side (u, v) is dynamically adjusted, and the equipment state and the fault propagation probability are considered, wherein the calculation formula is as follows:
DDIuv′(t,s)＝DDIuv(t)·(1+α·Ps+β·ΔTuv(s))；
Where DDI uv' (T, s) represents a dynamic DDI value after considering a device state and a fault propagation probability at time T and state s, DDI uv (T) is an original DDI value calculated based on static and dynamic factors, P s represents a probability of fault propagation from device u to device v at state s, Δt uv(s) represents an influence delay of device u on device v, i.e., a time difference required for fault propagation from u to v, and α and β are adjustment parameters for balancing the fault propagation probability and influence delay in the dynamic DDI value.
Further, the comprehensive analysis of the fault mode and the environmental factor in S4 includes:
S41, extracting data features: extracting data features by using a dynamic PCA algorithm to identify variables related to faults;
S42, fault mode identification: matching the extracted data characteristics with known fault modes, and identifying the fault type corresponding to the current equipment state;
S43, environmental factor analysis: the effect of the environmental data changes on the identified failure modes and device interactions is analyzed to determine the effect of environmental factors in the failure development.
Further, the dynamic PCA algorithm includes:
Data normalization: and (3) carrying out standardization processing on the operation data X i (t) of the equipment i in the time window t, wherein the calculation formula is as follows:
Wherein μ (t) and σ (t) are the mean and standard deviation, respectively, of the data in the time window;
The nuclear method is transformed: mapping the standardized data to a high-dimensional space through a kernel method, wherein the calculation formula is as follows:
Where K is a Gaussian kernel function and σ is a bandwidth parameter of the kernel function;
Extracting main components: PCA is applied in a high-dimensional space, eigenvalues and eigenvectors of a covariance matrix are calculated, eigenvectors corresponding to the k largest eigenvalues are selected as main components, and a calculation formula is as follows:
PCA (C) → selecting the feature vector corresponding to the largest k feature values.
Further, the diagnosing and predicting of the fault in S5 includes:
S51, comprehensive analysis result evaluation: based on the data characteristics extracted by the dynamic PCA algorithm, the results of equipment interaction analysis, environmental factor evaluation and fault mode identification, a comprehensive analysis framework is constructed, and the comprehensive analysis framework provides comprehensive understanding of the current fault state, including the type, cause and affected equipment components of the fault;
s52, current fault diagnosis: the information in the comprehensive analysis framework is utilized, a support vector machine SVM is applied to accurately diagnose the current fault, and the calculation formula is as follows:
Where K (x i, x) represents a kernel function for handling nonlinear classification problems in SVM, α i,yi, and b is a model parameter;
S53, predicting the future faults of the equipment: based on the current fault diagnosis result and past fault history and trend analysis, a time sequence analysis prediction model is used for predicting the fault type and time point of the future occurrence of the equipment, and the model is expressed as:
wherein Y t+1 is a future failure index, Is a model parameter, Y t is the current failure index, and ε t is an error term.
A flour equipment fault diagnosis system for realizing the flour equipment fault diagnosis method, which comprises the following modules:
And a data collection module: providing a plurality of sensors for monitoring and collecting data related to the flour processing environment and the operation of the equipment in real time;
The data preprocessing and anomaly detection module: the method has the advantages that the functions of data cleaning, standardization and feature extraction are realized, so that collected data are processed and optimized, the accuracy and the integrity of the data are ensured, the extracted features are subjected to anomaly detection, anomaly signals indicating equipment faults in the data are identified, anomaly events are recorded and reported, real-time fault early warning is provided, and quick decision and response are supported;
and the equipment interaction analysis module is used for: constructing a device interaction graph model (DIG), analyzing interaction and dependency relationship among devices by calculating dynamic dependency index DDI, and identifying a fault propagation path by adopting Dijkstra algorithm to reveal a device interaction mode causing a fault signal;
failure mode and environmental factor analysis module: comprehensively considering the influences of a fault mode, equipment interaction and environmental factors by using a dynamic PCA algorithm, analyzing data characteristics, analyzing fault reasons, analyzing the relation between environmental data change and the fault mode, and determining the effect of the environmental factors in fault development;
fault diagnosis and prediction module: based on comprehensive analysis results, accurately diagnosing the current fault by using a Support Vector Machine (SVM), providing detailed information of fault type, influence degree and maintenance priority, applying a time sequence analysis prediction model, and based on fault history and trend analysis, predicting the future potential fault of the equipment and formulating a preventive maintenance strategy;
And a maintenance effect feedback and optimization module: and collecting the maintained equipment performance data, and feeding back and optimizing the fault diagnosis and prediction model.
The invention has the beneficial effects that:
According to the invention, through comprehensive environment and equipment operation data collection and combination of a dynamic PCA algorithm, the influence of a fault mode, equipment interaction and environmental factors can be comprehensively considered, so that the accuracy of fault diagnosis is improved, the root cause behind the fault including hidden problems possibly caused by complex interaction of equipment and specific environmental conditions can be revealed, and the method can effectively identify and solve the fault caused by complex interaction among equipment and complex interaction of environmental factors, thereby remarkably improving the operation efficiency and stability of flour processing equipment.
According to the invention, through the fault diagnosis method, not only the current equipment fault can be accurately diagnosed, but also the future potential fault of the equipment can be predicted based on the comprehensive analysis result, and the prediction capability enables a maintenance team to take preventive measures in advance to avoid or reduce the influence caused by the potential fault.
The invention provides powerful support for maintenance and operation management of flour processing equipment through accurate fault diagnosis and effective future fault prediction, which is not only helpful for reducing maintenance cost and production loss caused by faults, but also can significantly improve the stability and production efficiency of a production line, particularly in complex production environments, the influence of environmental factors such as dust and the like on the equipment performance is effectively monitored and managed, the continuity of the production process and the consistency of the product quality are ensured, and obvious economic benefit and social benefit are brought to the flour processing industry.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only of the invention and that other drawings can be obtained from them without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a diagnostic method according to an embodiment of the invention;
fig. 2 is a schematic diagram of a system functional module according to an embodiment of the present invention.
Detailed Description
The present invention will be further described in detail with reference to specific embodiments in order to make the objects, technical solutions and advantages of the present invention more apparent.
It is to be noted that unless otherwise defined, technical or scientific terms used herein should be taken in a general sense as understood by one of ordinary skill in the art to which the present invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
As shown in fig. 1, a flour machine failure diagnosis method includes the steps of:
S1, collecting comprehensive environment and equipment operation data: collecting data related to the flour processing environment and the operation of the equipment in real time by using various sensors;
S2, data preprocessing and anomaly detection: cleaning and preprocessing the collected data by a data processing technology, and identifying abnormal signals in the data;
S3, device interaction analysis: analyzing interactions and dependencies among devices, identifying device interaction patterns that lead to failure signals, considering how devices interact (e.g., how a failure of one device affects another device), and how these interactions affect the overall operational state of the devices;
S4, comprehensively analyzing the fault mode and the environmental factors: using a dynamic PCA algorithm, comprehensively considering the influences of a fault mode, equipment interaction and environmental factors, and analyzing fault reasons;
S5, fault diagnosis and prediction: based on the comprehensive analysis result, diagnosing the current fault and predicting the future fault of the equipment, the specific type, the influence degree and the priority of emergency maintenance of the fault can be provided, and detailed maintenance and repair suggestions are provided for maintenance teams;
S6, feeding back and optimizing maintenance effects: the maintained equipment performance data is fed back, the fault diagnosis accuracy is optimized, and the fault diagnosis system can learn and improve from each maintenance activity and adapt to the change of equipment and environmental conditions;
The fault diagnosis method not only can accurately identify and solve faults caused by complex interaction of equipment and environmental factors, but also can improve the prediction capability of potential faults in the future through continuous learning and system optimization, thereby remarkably improving the running efficiency and stability of flour equipment.
The various sensors include in particular:
Temperature sensor: the method is used for monitoring the temperatures of equipment and a processing environment and identifying overheat or temperature abnormality;
humidity sensor: the device is used for monitoring the humidity level of the processing environment and preventing the quality of flour and the normal operation of equipment from being influenced by the excessively high or excessively low humidity;
Vibration sensor: the method is used for monitoring the vibration frequency and amplitude of equipment and identifying abnormal operation states of the equipment, including unbalance, dislocation or bearing faults;
a current sensor: the method comprises the steps of monitoring the current use condition of equipment and identifying an electrical fault or equipment overload condition;
Dust particle size and concentration sensor: monitoring the granularity and concentration of dust in the air aiming at the flour processing environment, and evaluating the air quality and the equipment blockage risk;
a sound sensor: for capturing sounds generated by the device during operation, identifying abnormal conditions of the device, such as wear or internal chipping;
By utilizing the sensor, the running state of flour processing equipment and the environment thereof can be monitored and collected in real time, and support is provided for fault diagnosis and preventive maintenance.
The data preprocessing and anomaly detection in S2 includes:
S21, data cleaning: the collected data is cleaned, including invalid data removal, error data point correction and missing value filling, so that accuracy and integrity of the data are ensured, and a reliable basis is provided for subsequent analysis;
S22, data standardization: the cleaned data is subjected to standardization processing, including normalization, standard deviation standardization or minimum-maximum scaling, so as to ensure that the data of different sources and different magnitudes can be compared and analyzed on the same scale;
S23, feature extraction: extracting features from the standardized data, wherein the features aim to capture important information and modes in the data, and are important for subsequent abnormality detection and fault diagnosis;
S24, abnormal signal identification: performing anomaly detection on the data based on the extracted features by a preset threshold value, and identifying anomaly signals in the data, wherein the signals possibly indicate potential faults or abnormal operation of equipment;
S25, recording and reporting abnormal events: recording the identified abnormal signals to generate an abnormal event report, wherein the report comprises abnormal time, position, strength and fault type, and the report provides real-time fault early warning for a device operation team and supports quick decision-making and response;
The method effectively processes and analyzes a large amount of data collected from equipment and the environment, can accurately identify abnormal signals in the data, provides key information for fault prediction and maintenance of flour processing equipment, specifies how to clean and preprocess the collected data through a data processing technology, identifies the abnormal signals in the data, and provides important technical support for implementation of a flour processing equipment fault diagnosis method.
The device interaction analysis in S3 includes:
S31, constructing a device interaction graph model (DIG): constructing an equipment interaction graph model, wherein nodes represent flour processing equipment, edges represent interaction among the equipment, and each edge is endowed with a dynamic dependency index DDI for quantifying the interaction degree among the equipment;
S32, calculating a dynamic dependency index DDI: for each pair of devices i and j in the model, calculating a dynamic dependence index DDI ij (t) of the device i on the device j at a time t by combining the static priority index and the dynamic performance influence index, wherein the calculation formula is as follows:
DDIij(t)＝λ·SPIij+(1-λ)·DPIij(t)；
The SPI ij is a static priority index, the value of the SPI ij is determined when the equipment is installed based on a fixed technological process or design parameters between the equipment i and the equipment j, the value of the SPI ij is not changed with time, the DPI ij (t) is a dynamic performance influence index, the actual influence of the equipment j is dynamically evaluated according to the current running state of the equipment i, the real-time monitoring data can be used for calculating, lambda is an adjusting parameter, the weight for balancing the static priority and the dynamic performance influence is used for balancing, and the value range is [0,1];
S33, identifying a fault propagation path: based on the calculated DDI value, a Dijkstra algorithm is adopted to identify a fault propagation path, and the propagation path is helpful for determining which equipment interaction modes possibly cause occurrence of fault signals;
S34, analyzing the interaction mode of the equipment: comprehensively considering DDI values and fault propagation paths among devices, analyzing specific device interaction modes causing fault signals, wherein the analysis reveals how stability and efficiency of the whole production line are affected through complex interaction among the devices;
The method is specially designed for flour processing equipment, not only static physical or technological process connection among the equipment is fully considered, but also dynamic interaction influence based on the current running state of the equipment is fully considered, and by constructing an equipment interaction graph model (DIG) and calculating a dynamic dependency index DDI, the method can accurately analyze and identify the equipment interaction mode causing fault signals, especially in a complex production environment, the method not only enhances the understanding of interaction among the equipment, but also provides important data support for predicting, diagnosing and maintaining equipment faults, and by the deep analysis, a maintenance team can more effectively identify potential fault sources and fault propagation paths, optimize maintenance plans, reduce unexpected shutdown and improve production efficiency.
The dynamic performance impact index DPI ij (t) is based on the correlation coefficient and covariance of the relevant operating parameters between the parameter X of the device i and the parameter Y of the device j, and the calculation formula is:
Wherein ρ (X i(t),Yj (t)) represents the correlation coefficient of the parameter X of the device i and the parameter Y of the device j at time t, The covariance of X i and Y j at time t is shown for quantifying trend dependence between the two parameters.
The Dijkstra algorithm is used for searching the shortest path, for flour equipment fault diagnosis, the dependency relationship and fault influence among the equipment are dynamically changed, the Dijkstra algorithm reflects the dynamics by introducing a time and state dependent weight adjustment mechanism, the DDI value of each side (u, v) is dynamically adjusted, and the equipment state and fault propagation probability are considered, wherein the calculation formula is as follows:
DDIuv′(t,s)＝DDIuv(t)·(1+α·Ps+β·ΔTuv(s))；
Where DDI uv' (T, s) represents a dynamic DDI value after considering a device state and a fault propagation probability at time T and state s, DDI uv (T) is an original DDI value calculated based on static and dynamic factors, P s represents a probability of fault propagation from device u to device v at state s, Δt uv(s) represents an influence delay of device u on device v, i.e., a time difference required for fault propagation from u to v, and α and β are adjustment parameters for balancing the fault propagation probability and influence delay in the dynamic DDI value;
The Dijkstra algorithm enables the fault diagnosis method of the flour processing equipment to accurately identify and predict the propagation path of faults in an equipment network, and a maintenance team can better understand the dynamic property and potential influence of the faults by considering the probability and time delay of fault propagation, so that more targeted prevention and treatment measures are adopted, which has great significance for improving the flour processing efficiency and reducing unexpected shutdown, and the invention is more effective and practical in practical application.
The comprehensive analysis of the fault mode and the environmental factors in the S4 comprises the following steps:
S41, extracting data features: extracting data features by using a dynamic PCA algorithm to identify variables related to faults;
S42, fault mode identification: matching the extracted data characteristics with known fault modes, and identifying the fault type corresponding to the current equipment state;
S43, environmental factor analysis: analyzing the influence of the environmental data change on the identified fault mode and the interaction influence of equipment, and determining the effect of environmental factors in fault development;
by means of a dynamic PCA algorithm, key changes in running data of flour processing equipment can be captured, influences of environmental factors on equipment faults can be analyzed carefully, particularly dust is a very key factor in the flour processing environment, root causes of the faults can be identified more accurately by means of integrating the data and analysis results, and basis is provided for making effective maintenance strategies and preventive measures.
The application of the method makes the fault diagnosis of flour processing equipment not only depend on simple experience judgment or static data analysis, but also provides a more scientific and comprehensive diagnosis method by dynamically analyzing complex interaction of equipment data and environmental factors. Successful implementation of the method can obviously improve the equipment stability and production efficiency of the flour processing industry, and simultaneously reduce the cost loss caused by unexpected faults.
The dynamic PCA algorithm includes:
Data normalization: and (3) carrying out standardization processing on the operation data X i (t) of the equipment i in the time window t, wherein the calculation formula is as follows:
Wherein μ (t) and σ (t) are the mean and standard deviation, respectively, of the data in the time window;
The nuclear method is transformed: mapping the standardized data to a high-dimensional space through a kernel method, wherein the calculation formula is as follows:
Where K is a Gaussian kernel function and σ is a bandwidth parameter of the kernel function;
Extracting main components: PCA is applied in a high-dimensional space, eigenvalues and eigenvectors of a covariance matrix are calculated, eigenvectors corresponding to the k largest eigenvalues are selected as main components, and a calculation formula is as follows:
PCA (C) to selecting the feature vector corresponding to the k largest feature values;
by integrating the dynamic PCA algorithm into the flour plant fault diagnosis process, complex plant operational data can be more effectively processed and analyzed, particularly in terms of capturing nonlinear relationships and dynamic changes between plants.
The fault diagnosis and prediction in S5 includes:
S51, comprehensive analysis result evaluation: based on the data characteristics extracted by the dynamic PCA algorithm, the results of equipment interaction analysis, environmental factor evaluation and fault mode identification, a comprehensive analysis framework is constructed, and the comprehensive analysis framework provides comprehensive understanding of the current fault state, including the type, cause and affected equipment components of the fault;
s52, current fault diagnosis: the information in the comprehensive analysis framework is utilized, a support vector machine SVM is applied to accurately diagnose the current fault, and the calculation formula is as follows:
Where K (x i, x) represents a kernel function for handling nonlinear classification problems in SVM, α i,yi, and b is a model parameter;
S53, predicting the future faults of the equipment: based on the current fault diagnosis result and past fault history and trend analysis, a time sequence analysis prediction model is used for predicting the fault type and time point of the future occurrence of the equipment, and the model is expressed as:
wherein Y t+1 is a future failure index, Is a model parameter, Y t is the current failure index, ε t is the error term;
the method can effectively realize fault diagnosis and future fault prediction of flour processing equipment, comprehensively considers the operation data, environmental factors and interaction among the equipment, can diagnose the current equipment fault, and can predict the future fault trend based on the history and real-time data, thereby providing strong support for equipment maintenance and operation management, being beneficial to improving the equipment reliability, reducing the maintenance cost and finally improving the production efficiency and the product quality.
As shown in fig. 2, a flour equipment failure diagnosis system is used for implementing the flour equipment failure diagnosis method, and comprises the following modules:
And a data collection module: providing a plurality of sensors for monitoring and collecting data related to the flour processing environment and the operation of the equipment in real time;
The data preprocessing and anomaly detection module: the method has the advantages that the functions of data cleaning, standardization and feature extraction are realized, so that collected data are processed and optimized, the accuracy and the integrity of the data are ensured, the extracted features are subjected to anomaly detection, anomaly signals indicating equipment faults in the data are identified, anomaly events are recorded and reported, real-time fault early warning is provided, and quick decision and response are supported;
and the equipment interaction analysis module is used for: constructing a device interaction graph model (DIG), analyzing interaction and dependency relationship among devices by calculating dynamic dependency index DDI, and identifying a fault propagation path by adopting Dijkstra algorithm to reveal a device interaction mode causing a fault signal;
Failure mode and environmental factor analysis module: comprehensively considering the influences of a fault mode, equipment interaction and environmental factors by using a dynamic PCA algorithm, analyzing data characteristics, analyzing fault reasons, specifically analyzing the relation between environmental data change and the fault mode, and determining the effect of the environmental factors in fault development;
fault diagnosis and prediction module: based on comprehensive analysis results, accurately diagnosing the current fault by using a Support Vector Machine (SVM), providing detailed information of fault type, influence degree and maintenance priority, applying a time sequence analysis prediction model, and based on fault history and trend analysis, predicting the future potential fault of the equipment and formulating a preventive maintenance strategy;
And a maintenance effect feedback and optimization module: and collecting the maintained equipment performance data, and feeding back and optimizing the fault diagnosis and prediction model.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the invention is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined within the idea of the invention, the steps may be implemented in any order and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
The present invention is intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the present invention should be included in the scope of the present invention.
Claims (9)
1. A flour machine fault diagnosis method, characterized by comprising the following steps:
S1, collecting comprehensive environment and equipment operation data: collecting data related to the flour processing environment and the operation of the equipment in real time by using various sensors;
S2, data preprocessing and anomaly detection: cleaning and preprocessing the collected data by a data processing technology, and identifying abnormal signals in the data;
S3, device interaction analysis: analyzing interactions and dependencies between devices, identifying a device interaction pattern that results in a fault signal, the device interaction analysis comprising:
s31, constructing a device interaction graph model: constructing an equipment interaction graph model, wherein nodes represent flour processing equipment, edges represent interaction among the equipment, and each edge is endowed with a dynamic dependency index DDI for quantifying the interaction degree among the equipment;
S32, calculating a dynamic dependency index DDI: for each pair of devices i and j in the model, calculating a dynamic dependence index DDI ij (t) of the device i on the device j at a time t by combining the static priority index and the dynamic performance influence index, wherein the calculation formula is as follows:
DDIij(t)＝λ·SPIij+(1-λ)·DPIij(t)；
Wherein SPI ij is the static priority index, DPI ij (t) is the dynamic performance impact index, λ is the adjustment parameter;
S33, identifying a fault propagation path: based on the calculated DDI value, adopting Dijkstra algorithm to identify a fault propagation path;
s34, analyzing the interaction mode of the equipment: comprehensively considering DDI values and fault propagation paths among devices, and analyzing a specific device interaction mode of a fault signal;
S4, comprehensively analyzing the fault mode and the environmental factors: using a dynamic PCA algorithm, comprehensively considering the influences of a fault mode, equipment interaction and environmental factors, and analyzing fault reasons;
s5, fault diagnosis and prediction: based on the comprehensive analysis result, diagnosing the current fault and predicting the future fault of the equipment;
s6, feeding back and optimizing maintenance effects: and feeding back the maintained equipment performance data, and optimizing the accuracy of fault diagnosis.
2. A flour mill malfunction diagnosis method according to claim 1, wherein said plurality of sensors comprises in particular:
Temperature sensor: the method is used for monitoring the temperatures of equipment and a processing environment and identifying overheat or temperature abnormality;
humidity sensor: the device is used for monitoring the humidity level of the processing environment and preventing the quality of flour and the normal operation of equipment from being influenced by the excessively high or excessively low humidity;
Vibration sensor: the method is used for monitoring the vibration frequency and amplitude of equipment and identifying abnormal operation states of the equipment, including unbalance, dislocation or bearing faults;
a current sensor: the method comprises the steps of monitoring the current use condition of equipment and identifying an electrical fault or equipment overload condition;
Dust particle size and concentration sensor: monitoring the granularity and concentration of dust in the air aiming at the flour processing environment, and evaluating the air quality and the equipment blockage risk;
A sound sensor: the method is used for capturing sounds generated during the running of the device and identifying the abnormal state of the device.
3. A flour mill malfunction diagnosis method according to claim 2, wherein the data preprocessing and anomaly detection in S2 includes:
S21, data cleaning: cleaning the collected data, including removing invalid data, correcting erroneous data points and filling missing values;
S22, data standardization: carrying out standardization treatment on the cleaned data, wherein the standardization treatment comprises normalization, standard deviation standardization or minimum-maximum scaling;
s23, feature extraction: extracting features from the normalized data;
s24, abnormal signal identification: performing anomaly detection on the extracted features based on a preset threshold;
S25, recording and reporting abnormal events: recording the identified abnormal signals, and generating an abnormal event report including the time, the position, the intensity and the fault type of the abnormality.
4. A flour mill malfunction diagnosis method according to claim 3, wherein said dynamic performance impact index DPI ij (t) is based on the correlation coefficient and covariance of the relevant operating parameters between parameter X of apparatus i and parameter Y of apparatus j, and the calculation formula is:
Wherein ρ (X i(t),Yj (t)) represents the correlation coefficient of the parameter X of the device i and the parameter Y of the device j at time t, The covariance of X i and Y j at time t is shown for quantifying trend dependence between the two parameters.
5. The flour machine fault diagnosis method according to claim 4, wherein Dijkstra algorithm is used for finding the shortest path, for flour machine fault diagnosis, dependency relationship and fault influence between machines are dynamically changed, by introducing a time and state dependent weight adjustment mechanism, dijkstra algorithm reflects the dynamics, the DDI value of each side is dynamically adjusted, and the machine state and fault propagation probability are considered, and the calculation formula is:
DDIuv′(t,s)＝DDIuv(t)·(1+α·Ps+β·ΔTuv(s))；
Where DDI uv' (T, s) represents a dynamic DDI value after considering a device state and a fault propagation probability at time T and state s, DDI uv (T) is an original DDI value calculated based on static and dynamic factors, P s represents a probability of fault propagation from device u to device v at state s, Δt uv(s) represents an influence delay of device u on device v, i.e., a time difference required for fault propagation from u to v, and α and β are adjustment parameters for balancing the fault propagation probability and influence delay in the dynamic DDI value.
6. The flour mill malfunction diagnosis method according to claim 5, wherein the comprehensive analysis of the malfunction mode and the environmental factor in S4 includes:
S41, extracting data features: extracting data features by using a dynamic PCA algorithm to identify variables related to faults;
S42, fault mode identification: matching the extracted data characteristics with known fault modes, and identifying the fault type corresponding to the current equipment state;
S43, environmental factor analysis: the effect of the environmental data changes on the identified failure modes and device interactions is analyzed to determine the effect of environmental factors in the failure development.
7. A flour machine fault diagnosis method according to claim 6, wherein the dynamic PCA algorithm comprises:
Data normalization: and (3) carrying out standardization processing on the operation data X i (t) of the equipment i in the time window t, wherein the calculation formula is as follows:
Wherein μ (t) and σ (t) are the mean and standard deviation, respectively, of the data in the time window;
The nuclear method is transformed: mapping the standardized data to a high-dimensional space through a kernel method, wherein the calculation formula is as follows:
Where K is a Gaussian kernel function and σ is a bandwidth parameter of the kernel function;
Extracting main components: PCA is applied in a high-dimensional space, eigenvalues and eigenvectors of a covariance matrix are calculated, eigenvectors corresponding to the k largest eigenvalues are selected as main components, and a calculation formula is as follows:
PCA (C) → selecting the feature vector corresponding to the largest k feature values.
8. A flour mill malfunction diagnosis method according to claim 7, wherein the malfunction diagnosis and prediction in S5 includes:
S51, comprehensive analysis result evaluation: based on the data characteristics extracted by the dynamic PCA algorithm, the results of equipment interaction analysis, environmental factor evaluation and fault mode identification, a comprehensive analysis framework is constructed, and the comprehensive analysis framework provides comprehensive understanding of the current fault state, including the type, cause and affected equipment components of the fault;
s52, current fault diagnosis: the information in the comprehensive analysis framework is utilized, a support vector machine SVM is applied to accurately diagnose the current fault, and the calculation formula is as follows:
Where K (x i, x) represents a kernel function for handling nonlinear classification problems in SVM, α i,yi, and b is a model parameter;
S53, predicting the future faults of the equipment: based on the current fault diagnosis result and past fault history and trend analysis, a time sequence analysis prediction model is used for predicting the fault type and time point of the future occurrence of the equipment, and the model is expressed as:
wherein Y t+1 is a future failure index, Is a model parameter, Y t is the current failure index, and ε t is an error term.
9. A flour mill malfunction diagnosis system for implementing a flour mill malfunction diagnosis method according to any one of claims 1 to 8, comprising the following modules:
And a data collection module: providing a plurality of sensors for monitoring and collecting data related to the flour processing environment and the operation of the equipment in real time;
The data preprocessing and anomaly detection module: the method has the advantages that the functions of data cleaning, standardization and feature extraction are realized, so that collected data are processed and optimized, the accuracy and the integrity of the data are ensured, the extracted features are subjected to anomaly detection, anomaly signals indicating equipment faults in the data are identified, anomaly events are recorded and reported, real-time fault early warning is provided, and quick decision and response are supported;
And the equipment interaction analysis module is used for: constructing a device interaction graph model, analyzing interaction and dependency relationship among devices by calculating dynamic dependency index DDI, identifying a fault propagation path by adopting Dijkstra algorithm, and revealing a device interaction mode causing a fault signal;
failure mode and environmental factor analysis module: comprehensively considering the influences of a fault mode, equipment interaction and environmental factors by using a dynamic PCA algorithm, analyzing data characteristics, analyzing fault reasons, analyzing the relation between environmental data change and the fault mode, and determining the effect of the environmental factors in fault development;
fault diagnosis and prediction module: based on comprehensive analysis results, accurately diagnosing the current fault by using a Support Vector Machine (SVM), providing detailed information of fault type, influence degree and maintenance priority, applying a time sequence analysis prediction model, and based on fault history and trend analysis, predicting the future potential fault of the equipment and formulating a preventive maintenance strategy;
And a maintenance effect feedback and optimization module: and collecting the maintained equipment performance data, and feeding back and optimizing the fault diagnosis and prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410330010.5A CN117932322B (en) | 2024-03-22 | 2024-03-22 | Flour equipment fault diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410330010.5A CN117932322B (en) | 2024-03-22 | 2024-03-22 | Flour equipment fault diagnosis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117932322A CN117932322A (en) | 2024-04-26 |
| CN117932322B true CN117932322B (en) | 2024-06-04 |
Family
ID=90766820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410330010.5A Active CN117932322B (en) | 2024-03-22 | 2024-03-22 | Flour equipment fault diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117932322B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118128742B (en) * | 2024-05-10 | 2024-07-16 | 杭州涵锐科技有限公司 | Intelligent monitoring method and system for air compressor |
| CN118154174B (en) * | 2024-05-11 | 2024-08-20 | 青岛研博数据信息技术有限公司 | Intelligent operation and maintenance cloud platform for industrial equipment |
| CN118423907B (en) * | 2024-07-03 | 2024-09-24 | 无锡冠亚恒温制冷技术有限公司 | Intelligent monitoring alarm system and method for heating refrigeration circulator |
| CN118469554A (en) * | 2024-07-15 | 2024-08-09 | 深圳市威诺达工业技术有限公司 | Regulation and control optimization method and system based on fault diagnosis of electric submersible pump |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590506A (en) * | 2017-08-17 | 2018-01-16 | 北京航空航天大学 | A kind of complex device method for diagnosing faults of feature based processing |
| CN114707551A (en) * | 2022-04-06 | 2022-07-05 | 西北大学 | Multi-mode data fusion method for industrial internet equipment fault diagnosis |
| CN116244617A (en) * | 2022-12-19 | 2023-06-09 | 国网安徽省电力有限公司电力科学研究院 | Intelligent high-voltage switch cabinet fault diagnosis method and system based on heterogeneous graph structure learning |
| CN117150414A (en) * | 2023-10-17 | 2023-12-01 | 广东迅扬科技股份有限公司 | Fault diagnosis method |
| CN117142009A (en) * | 2023-10-30 | 2023-12-01 | 山西海诚智能制造有限公司 | Scraper conveyor health state assessment method based on graph rolling network |
| CN117472036A (en) * | 2023-12-28 | 2024-01-30 | 国网山东省电力公司营销服务中心(计量中心) | Detection system and method of HPLC fault diagnosis equipment |
-
2024
- 2024-03-22 CN CN202410330010.5A patent/CN117932322B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590506A (en) * | 2017-08-17 | 2018-01-16 | 北京航空航天大学 | A kind of complex device method for diagnosing faults of feature based processing |
| CN114707551A (en) * | 2022-04-06 | 2022-07-05 | 西北大学 | Multi-mode data fusion method for industrial internet equipment fault diagnosis |
| CN116244617A (en) * | 2022-12-19 | 2023-06-09 | 国网安徽省电力有限公司电力科学研究院 | Intelligent high-voltage switch cabinet fault diagnosis method and system based on heterogeneous graph structure learning |
| CN117150414A (en) * | 2023-10-17 | 2023-12-01 | 广东迅扬科技股份有限公司 | Fault diagnosis method |
| CN117142009A (en) * | 2023-10-30 | 2023-12-01 | 山西海诚智能制造有限公司 | Scraper conveyor health state assessment method based on graph rolling network |
| CN117472036A (en) * | 2023-12-28 | 2024-01-30 | 国网山东省电力公司营销服务中心(计量中心) | Detection system and method of HPLC fault diagnosis equipment |
Non-Patent Citations (5)
| Title |
|---|
| Composite-Graph-Based Sparse Subspace Clustering for Machine Fault Diagnosis;Chuang Sun et al.;《IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT》;20190619;第69卷(第5期);第1850-1859页 * |
| Fault detection and diagnosis of nonlinear dynamical processes through correlation dimension and fractal analysis based dynamic kernel PCA;Wahiba Bounoua et al.;《Chemical Engineering Science》;20200906;第1-14页 * |
| 基于 PCA 和 IGWO-SVM 的水泥回转窑故障诊断研究;金星等;《中国测试》;20171031;第43卷(第10期);第92-96页 * |
| 基于主成分分析—支持向量机优化模型的断路器故障诊断 方法研究;樊浩等;《高压电器》;20200616;第56卷(第6期);第143-151页 * |
| 基于改进 联合 的 电厂设备故障诊断方法;刘兴彦等;《计算机技术与自动化》;20230930;第42卷(第3期);第27-31页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117932322A (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117932322B (en) | Flour equipment fault diagnosis method and system | |
| US9483049B2 (en) | Anomaly detection and diagnosis/prognosis method, anomaly detection and diagnosis/prognosis system, and anomaly detection and diagnosis/prognosis program | |
| CN109186813A (en) | A kind of temperature sensor self-checking unit and method | |
| CN118194150B (en) | Remote monitoring and fault prediction system for water chiller | |
| CN112173636B (en) | Method for detecting faults of belt conveyor carrier roller by inspection robot | |
| CN113196311A (en) | System and method for identifying and predicting abnormal sensing behavior patterns of a machine | |
| CN109141625B (en) | Online state monitoring method for ball screw pair | |
| CN118154174B (en) | Intelligent operation and maintenance cloud platform for industrial equipment | |
| CN118226825B (en) | Quality control data processing method based on MES system | |
| CN112733446A (en) | Data-driven self-adaptive anomaly detection method | |
| CN118030409A (en) | Method and system for detecting abnormal operation performance of fan unit | |
| CN118051822A (en) | Equipment running state abnormality detection method based on voiceprint recognition technology | |
| CN118035814A (en) | State fault early warning method and system based on digital twin field data analysis equipment | |
| CN117672255B (en) | Abnormal equipment identification method and system based on artificial intelligence and equipment operation sound | |
| CN110336860A (en) | Key node data guard method based on multidimensional data processing in industrial Internet of Things | |
| CN117435908A (en) | Multi-fault feature extraction method for rotary machine | |
| KR102108975B1 (en) | Apparatus and method for condition based maintenance support of naval ship equipment | |
| Ceschini et al. | Detection and Classification of Sensor Anomalies in Gas Turbine Field Data | |
| Raj | An Improved Accuracy and Efficiency Based Defect Detection Method for Industrial Signal Processing | |
| CN118566701B (en) | Fault diagnosis system and method applied to integrated circuit of industrial robot | |
| Ahmed et al. | Detection of Cracks in the Industrial System Using Adaptive Principal Component Analysis and Wavelet Denoising | |
| Soller et al. | Evaluation and adaption of maintenance prediction methods in mixed production line setups based on anomaly detection | |
| CN118625791B (en) | Fault-tolerant control system and method for conveying equipment abnormality | |
| CN118224156B (en) | Hydraulic system abnormality monitoring method and system | |
| Rigamonti et al. | AN ADVANCED EARLY FAULT DETECTION TOOL FOR PREDICTIVE MAINTENANCE OF A FLEET OF INDUSTRIAL GAS TURBINES |
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 |