CN115600695B - Fault diagnosis method for metering equipment - Google Patents
Fault diagnosis method for metering equipment Download PDFInfo
- Publication number
- CN115600695B CN115600695B CN202211085965.6A CN202211085965A CN115600695B CN 115600695 B CN115600695 B CN 115600695B CN 202211085965 A CN202211085965 A CN 202211085965A CN 115600695 B CN115600695 B CN 115600695B
- Authority
- CN
- China
- Prior art keywords
- sample
- fault
- certificate
- calibration
- subsequence
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/56—Testing of electric apparatus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Power Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a fault diagnosis method of metering equipment, and relates to the technical field of intelligent metering fault diagnosis. The specific implementation mode of the method comprises the following steps: receiving a diagnosis request of metering equipment to be diagnosed; preprocessing a history calibration certificate, and determining structural environment characteristics and project characteristics; inputting the environmental features and the project features into a pre-trained fault diagnosis model; determining a target diagnosis result of the metering equipment to be diagnosed according to the output of the fault diagnosis model; the target diagnosis result comprises a predicted fault position and a predicted fault degree of the metering equipment to be diagnosed under the target prediction time. According to the embodiment, the existing metering big data can be analyzed, so that the health condition of each metering device is monitored, the fault condition of the metering device is diagnosed and early-warned in advance, an auxiliary decision is provided for a worker, the device fault is processed in time, the safe production of the metering device is guaranteed, and the metering efficiency is improved.
Description
Technical Field
The invention belongs to the field of fault diagnosis of intelligent metering, and particularly relates to a fault diagnosis method of metering equipment.
Background
In conventional fault diagnosis of metering devices, fault devices are generally reported from each metering site, and then are diagnosed and maintained (i.e., post-maintenance) by a device maintainer reaching the site, or are periodically detected on the site by the device maintainer reaching the working site of each device to find defects or faults (i.e., planning maintenance), thereby ensuring the normal operation of the metering devices.
However, in the existing fault diagnosis mode, on one hand, with the proliferation of metering equipment, the workload of the manual diagnosis mode is extremely high, equipment maintenance personnel cannot deal with the fault diagnosis mode, so that the labor cost consumed by the existing fault diagnosis is extremely high, and the shutdown of the metering equipment and the stop of a production site cannot be timely processed; on the other hand, the efficiency of the manual diagnosis mode is too low, the metering equipment cannot be judged in real time, the early warning capability is poor, and the possible hidden trouble of the equipment cannot be predicted in advance and eliminated in time, so that the equipment failure rate is increased or even deteriorated; on the other hand, the increase of metering devices is accompanied by the exponential increase of device usage data, while the white space occupies the storage space and is not fully utilized, the usage rate of the metering data is low, and the potential value for providing reference for fault diagnosis is not fully mined.
Disclosure of Invention
In view of the above, the invention provides a fault diagnosis method and device for metering equipment, which can analyze the existing metering big data, so as to monitor the health condition of each metering equipment, diagnose and early warn the fault condition of the metering equipment in advance, thereby providing auxiliary decision for staff, timely processing equipment faults, guaranteeing the safe production of the metering equipment and improving the metering efficiency.
The technical scheme for realizing the invention is as follows:
a fault diagnosis method of a metering device, comprising:
receiving a diagnosis request of metering equipment to be diagnosed; wherein the diagnostic request includes a target predicted time and a historical calibration certificate of the metering device to be diagnosed;
preprocessing the historical calibration certificate, and determining structural environmental characteristics and project characteristics;
inputting the environmental features and the project features into a pre-trained fault diagnosis model;
determining a target diagnosis result of the metering equipment to be diagnosed according to the output of the fault diagnosis model; the target diagnosis result comprises a predicted fault position and a predicted fault degree of the metering equipment to be diagnosed under the target prediction time.
Optionally, the method further comprises:
acquiring a sample calibration certificate and a sample verification certificate of each sample metering device;
preprocessing the sample calibration certificate and the sample verification certificate to obtain structural sample structural characteristics, sample environment characteristics, sample item characteristics and sample fault characteristics;
decomposing the sample environment characteristics, the sample item characteristics and the sample fault characteristics into a sample environment subsequence, a sample item subsequence and a sample fault subsequence respectively by using empirical mode decomposition;
reconstructing the sample environment subsequence, the sample item subsequence and the sample fault subsequence, and determining a target environment variable subsequence, a target item variable subsequence and a target fault parameter subsequence;
taking the target environment variable subsequence and the target project variable subsequence as inputs, taking the target fault parameter subsequence as output, and performing iterative training on a fault diagnosis model;
and generating a final fault diagnosis model according to the training result.
Optionally, the preprocessing the sample calibration certificate and the sample verification certificate to obtain a structured sample structure feature, a sample environment feature, a sample item feature and a sample fault feature, including:
and extracting sample structural features, sample environmental features, sample item features and sample fault features of the sample verification certificate from the sample calibration certificate by using a pre-constructed certificate entity dictionary.
Optionally, the extracting the sample structural feature, the sample environmental feature, the sample item feature, and the sample fault feature of the sample verification certificate in the sample calibration certificate includes:
and determining the sample environment characteristics of the corresponding sequences including the sample environment variables and the sample calibration time, the sample item characteristics of the corresponding sequences including the sample item variables and the sample calibration time, and the sample fault characteristics of the corresponding sequences including the sample fault parameters and the sample calibration time according to the sample calibration time of the sample calibration certificate.
Optionally, constructing the certificate entity dictionary includes:
acquiring a plurality of historical calibration certificates and historical verification certificates of each historical metering device in a historical verification process; the historical calibration certificate and the historical verification certificate are in a Word document format.
Converting Word document data of a plurality of the historical calibration certificates and the historical verification certificates into calibration certificate semi-structured data and verification certificate semi-structured data in an XML format;
extracting the mapping relation between XML labels and the label values of the XML labels in the calibration certificate semi-structured data and the verification certificate semi-structured data;
and constructing a certificate entity dictionary according to the mapping relation between the XML tag and the tag value of the XML tag.
Optionally, the sample environment variables include sample temperature, sample humidity, sample air pressure, etc., the sample item variables include sample current, sample voltage, sample resistance, sample noise, etc., and the sample fault parameters include sample fault location and sample fault extent.
Optionally, before the preprocessing the historical calibration certificate, the method further includes:
determining a structured structural feature of the historical calibration certificate;
and judging whether the structural features meet the specified data form, and if so, executing the structural environmental features and project features.
The beneficial effects are that:
(1) The workload of fault diagnosis of the metering equipment is greatly reduced, the consumption of cost is reduced, the equipment fault can be diagnosed in time, and the normal operation and the normal production of the metering equipment are ensured;
(2) The efficiency of fault diagnosis of the metering equipment is improved, the real-time judgment and early warning of the metering equipment can be realized, the possible fault hidden trouble of the metering equipment is eliminated in advance, the safety of the class length metering equipment is eliminated in time, and the service life of the metering equipment is prolonged;
(3) Metering data of metering equipment is fully utilized and mined, and references are provided for fault diagnosis of the metering equipment while the utilization rate of the metering data is improved;
(4) Based on structural characteristics, environment variables, project variables and fault parameters in the past verification process of the metering equipment, the state of the metering equipment is analyzed and monitored by using a fault diagnosis model, the future health condition of the metering equipment is predicted, and the problems of 'insufficient maintenance' and 'excessive maintenance' existing in post-repair and rigidified planned maintenance are prevented by means of targeted prevention and maintenance, so that the service life of the metering equipment can be effectively prolonged.
Drawings
Fig. 1 is a schematic diagram of the main flow of a fault diagnosis method of a metering device according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a main flow of a method for generating a fault diagnosis model according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a main flow of a method for constructing a certificate entity dictionary according to an embodiment of the present invention.
Detailed Description
The invention will now be described in detail by way of example with reference to the accompanying drawings.
EMD: empirical Mode Decomposition, i.e. empirical mode decomposition, refers to signal decomposition based on the time scale characteristics of the data itself, and can be applied to decomposition of any type of signal in theory, including linear, stationary signal sequence numbers and nonlinear, non-stationary signal sequences, without presetting any basis functions.
IMF: intrinsic Mode Functions, i.e. the connotation modal component, or the natural modal function, the eigenmode function, refers to the signal component or single component signal of each layer obtained after the original signal is decomposed by EMD.
The invention provides a fault diagnosis method of metering equipment, as shown in figure 1, comprising the following steps:
step 11, receiving a diagnosis request of the metering equipment to be diagnosed; wherein the diagnostic request includes a target predicted time and a historical calibration certificate of the metering device to be diagnosed.
In the embodiment of the invention, the calibration certificate comprises a certificate unique number, a calibration place, a calibration time, a technical specification file according to which the calibration is based, a metering equipment name, a metering equipment number, a certificate page number, a consigner name, an auditor, a calibration environment variable, a calibration item, a measurement result of the calibration item and an uncertainty (or called measurement uncertainty) of the measurement result of the calibration item.
And step 12, preprocessing the historical calibration certificate to determine structural environment characteristics and project characteristics.
In an embodiment of the present invention, before the preprocessing the historical calibration certificate, the method further includes:
determining a structured structural feature of the historical calibration certificate;
judging whether the structural features meet a specified data form or not, and if so, executing the structural environmental features and project features;
if not, rejecting the diagnosis request, and sending out reminding information of the data form that the history calibration certificate does not accord with the regulation.
In the embodiment of the invention, the structural characteristics are extracted according to the structural characteristics in the calibration certificate, the structural characteristics refer to the data form of the calibration certificate, including forms such as a list, characters, a signature (picture) and the like, and can be used for judging whether the calibration certificate accords with the specified data form, and the calibration certificate which does not accord with the specified data form is directly excluded without judgment; the extraction of the environmental and project features is performed only on calibration certificates that meet the specified dataform.
Further, before preprocessing the calibration certificate, irrelevant diagnostic data in the calibration certificate can be removed, wherein the irrelevant diagnostic data comprises a unique certificate number, a calibration place, a technical specification file of a standard basis, the number of pages of the certificate, a commissioner name, an auditor and the like.
And 13, inputting the environmental characteristics and the project characteristics into a pre-trained fault diagnosis model.
In the embodiment of the invention, the fault diagnosis model can predict the future health condition of the metering equipment according to the input environmental characteristics and project characteristics, including possible faults, fault degree and position, trend of fault development, residual service life and the like, so as to determine whether the task execution of the metering equipment is influenced.
The invention provides a method for generating a fault diagnosis model, as shown in fig. 2, comprising the following steps:
step 21, obtaining a sample calibration certificate and a sample verification certificate of each sample metering device.
In an embodiment of the invention, the sample database stores a sample calibration certificate and a sample verification certificate of each sample metering device in the process of performing verification.
In an embodiment of the invention, the certification certificate is a conclusion of whether the metering device is qualified or not, which is determined according to the calibration certificate.
And step 22, preprocessing the sample calibration certificate and the sample verification certificate to obtain structural sample structural features, sample environment features, sample item features and sample fault features.
In the embodiment of the invention, a pre-constructed certificate entity dictionary is utilized to extract sample structure feature values, sample environment features, sample item features and sample fault features of a sample verification certificate in the sample calibration certificate; wherein:
in the embodiment of the present invention, as shown in fig. 3, the method for constructing a certificate entity dictionary of the present invention includes the following steps:
step 31, obtaining a plurality of historical calibration certificates and historical verification certificates of each historical metering device in a historical verification process; the historical calibration certificate and the historical verification certificate are in a Word document format.
And step 32, converting Word document data of the plurality of historical calibration certificates and historical verification certificates into calibration certificate semi-structured data and verification certificate semi-structured data in an XML format.
And step 33, extracting the mapping relation between the XML label and the label value of the XML label in the calibration certificate semi-structured data and the verification certificate semi-structured data.
And step 34, constructing a certificate entity dictionary according to the mapping relation between the XML tag and the tag value of the XML tag.
In the embodiment of the invention, the certificate entity dictionary extracted from the plurality of historical calibration certificates and the historical verification certificates is utilized, so that the certificate data of each calibration certificate and verification certificate, including the label values of each entity of the calibration certificate and verification certificate, can be extracted based on the certificate entity dictionary in the subsequent use process.
In an embodiment of the present invention, the sample environmental characteristic including the respective sample environmental variable and the corresponding sequence of the sample calibration time, the sample item characteristic of the respective sample item variable and the corresponding sequence of the sample calibration time, and the sample fault characteristic of the respective sample fault parameter and the corresponding sequence of the sample calibration time are determined according to the sample calibration time of the sample calibration certificate.
Further, the sample environment variables include sample temperature, sample humidity, sample air pressure, etc., the sample item variables include sample current, sample voltage, sample resistance, sample noise, etc., and the sample fault parameters include sample fault location and sample fault extent.
And step 23, decomposing the sample environment characteristics, the sample item characteristics and the sample fault characteristics into a sample environment subsequence, a sample item subsequence and a sample fault subsequence respectively by using empirical mode decomposition.
In an embodiment of the present invention, the EMD decomposes the corresponding sequence of each sample environment variable and sample calibration time into a plurality of sample environment subsequences, e.g., the sample environment variable is a sample temperature, and the EMD decomposes the corresponding sequence of each sample temperature and sample calibration time into a plurality of sample temperature subsequences.
The EMD decomposes the corresponding sequence of each sample item variable and sample calibration time into a plurality of sub-sequences of sample items, e.g., sample item variable is sample current, and the EMD decomposes the corresponding sequence of each sample current and sample calibration time into a plurality of sub-sequences of sample current.
The EMD decomposes the corresponding sequence of each sample fault parameter and sample calibration time into a plurality of sample fault sub-sequences, e.g., the sample fault parameter is the sample fault location, and the EMD decomposes the corresponding sequence of each sample fault location and sample calibration time into a plurality of sample fault location sub-sequences.
Further, after the EMD decomposes each sequence, trend terms for each sub-sequence (i.e., trend of change for each sequence) can be obtained.
And step 24, reconstructing the sample environment subsequence, the sample item subsequence and the sample fault subsequence, and determining a target environment variable subsequence, a target item variable subsequence and a target fault parameter subsequence.
In the embodiment of the invention, the EMD can decompose the data sequence into the intrinsic mode function subsequence IMF and the trend item, and when the IMF is obtained, the EMD automatically identifies and sequentially extracts the sequences from high frequency to low frequency, so that the obtained IMF is a sequence with average value approaching zero and no obvious rising or falling trend, and the requirement of the time sequence on stability is met. The sample environment sub-sequence, sample item sub-sequence and sample fault sub-sequence of each sample metering device are reconstructed to determine therefrom a diagnostic sequence (i.e., a target environment variable sub-sequence, a target item variable sub-sequence and a target fault parameter sub-sequence, or high frequency sequence) useful for the sample metering device, e.g., air pressure is not valuable for fault diagnosis of the engine, and temperature is valuable for fault diagnosis of the engine, so that the target environment variable sub-sequence of the engine includes a sample temperature sequence and does not include a sample air pressure sequence.
Further, reconstruction refers to the determination of converting each sample sub-sequence into a linear graph by filtering.
In the embodiment of the invention, taking an engine as an example, when the engine normally operates, signal values corresponding to the temperature of an engine environment variable and the noise of a project variable are in a normal range, once the temperature signal value and the noise signal value collected in a certain period seriously exceed the range of the normal signal value, the engine is likely to be in fault, and the EMD finds that the sequence of the temperature signal value and the noise signal value exceeds the normal signal value for a plurality of times through analyzing a sample temperature subsequence and a sample noise subsequence, and the sequence corresponding to the temperature signal value and the noise signal value is a high-frequency sequence.
In the embodiment of the invention, after the sample environment subsequence, the sample item subsequence and the sample failure subsequence are subjected to EMD processing, the sample environment subsequence, the sample item subsequence and the sample failure subsequence are decomposed into a series of relatively stable components, but each component cannot describe the characteristics of the original sequence independently, and the original sequence can be described relatively accurately only by integrating the characteristics of each component, so that the reconstructed sequence characteristic information can relatively comprehensively reflect various characteristics of corresponding sample metering equipment by utilizing the reconstruction thought, thereby providing reliable analysis for equipment performance prediction and reliable analysis and prediction for the health condition of the metering equipment.
And step 25, taking the target environment variable subsequence and the target project variable subsequence as inputs, taking the target fault parameter subsequence as an output, and performing iterative training on a fault diagnosis model.
In the embodiment of the invention, the fault diagnosis model adopts a neural network algorithm, the training of the fault diagnosis model of the neural network algorithm adopts a gradient descent and back propagation algorithm, the error of a network output node is minimized through a back learning process, the weight and the threshold of each parameter of an initial assumed neural network are trained, and the correction is carried out along the negative gradient rapid descent direction of an error function in the training process until the weight of each parameter of a final neural network is determined. In neural networks, the nonlinear learning process is accomplished by the interaction of hidden and output layers. When the output of the fault diagnosis model is inconsistent with the expected value given by the target fault parameter subsequence, an error signal of the fault diagnosis model is reversely transmitted back from the output end, and the weight is continuously corrected in the process of transmission.
And step 26, generating a final fault diagnosis model according to the training result.
In the embodiment of the invention, the training set and the testing set can be divided in the training process of the fault diagnosis model so as to further improve the accuracy of the fault diagnosis model.
Step 14, determining a target diagnosis result of the metering equipment to be diagnosed according to the output of the fault diagnosis model; the target diagnosis result comprises a predicted fault position and a predicted fault degree of the metering equipment to be diagnosed under the target prediction time.
In the embodiment of the invention, the neural network of the fault diagnosis model can forward calculate the input environmental characteristics and project characteristics and obtain the target diagnosis result, and the metering equipment to be diagnosed can carry out fault prediction, so that predictive maintenance can be provided when the fault does not occur, measures can be taken in time to solve the fault, and the fault cause can be traced back to avoid unnecessary faults. By analyzing various data of the metering equipment in the past verification process and applying EMD to carry out sequence decomposition according to time sequence analysis, a reasonable, simple and practical fault diagnosis model is built, the accuracy of fault prediction is improved, and the safety production of the equipment is ensured.
In summary, the above embodiments are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (3)
1. A fault diagnosis method of a metering device, characterized by comprising:
step one, receiving a diagnosis request of metering equipment to be diagnosed; the diagnosis request comprises target prediction time and historical calibration certificates of the metering equipment to be diagnosed, and sample calibration certificates and sample verification certificates of all sample metering equipment are obtained;
preprocessing the history calibration certificate to determine structural environment characteristics and project characteristics;
inputting the environmental characteristics and the project characteristics into a pre-trained fault diagnosis model;
the generating of the fault-oriented model comprises the following steps:
preprocessing the sample calibration certificate and the sample verification certificate to obtain structural sample structural characteristics, sample environment characteristics, sample item characteristics and sample fault characteristics; decomposing the sample environment characteristics, the sample item characteristics and the sample fault characteristics into a sample environment subsequence, a sample item subsequence and a sample fault subsequence respectively by using empirical mode decomposition;
reconstructing the sample environment subsequence, the sample item subsequence and the sample fault subsequence, and determining a target environment variable subsequence, a target item variable subsequence and a target fault parameter subsequence;
taking the target environment variable subsequence and the target project variable subsequence as inputs, taking the target fault parameter subsequence as output, and performing iterative training on a fault diagnosis model;
generating a final fault diagnosis model according to the training result;
determining a target diagnosis result of the metering equipment to be diagnosed according to the output of the fault diagnosis model; the target diagnosis result comprises a predicted fault position and a predicted fault degree of the metering equipment to be diagnosed under the target prediction time;
the preprocessing of the sample calibration certificate and the sample verification certificate to obtain a structured sample structure feature, a sample environment feature, a sample item feature and a sample fault feature comprises:
extracting sample structural features, sample environmental features, sample item features and sample fault features of the sample verification certificate from the sample calibration certificate by using a pre-constructed certificate entity dictionary;
the extracting the sample structure feature, the sample environment feature, the sample item feature and the sample fault feature of the sample verification certificate in the sample calibration certificate comprises the following steps:
determining the sample environment characteristics of the corresponding sequences including the sample environment variables and the sample calibration time, the sample item characteristics of the corresponding sequences including the sample item variables and the sample calibration time, and the sample fault characteristics of the corresponding sequences including the sample fault parameters and the sample calibration time according to the sample calibration time of the sample calibration certificate;
constructing the certificate entity dictionary, including:
acquiring a plurality of historical calibration certificates and historical verification certificates of each historical metering device in a historical verification process; the history calibration certificate and the history verification certificate are in a Word document format;
converting Word document data of a plurality of the historical calibration certificates and the historical verification certificates into calibration certificate semi-structured data and verification certificate semi-structured data in an XML format;
extracting the mapping relation between XML labels and the label values of the XML labels in the calibration certificate semi-structured data and the verification certificate semi-structured data;
and constructing a certificate entity dictionary according to the mapping relation between the XML tag and the tag value of the XML tag.
2. The method of claim 1, wherein the sample environment variables comprise sample temperature, sample humidity, and sample air pressure, the sample item variables comprise sample current, sample voltage, sample resistance, and sample noise, and the sample fault parameters comprise sample fault location and sample fault extent.
3. The method of claim 1, further comprising, prior to said preprocessing the historical calibration certificate:
determining a structured structural feature of the historical calibration certificate;
and judging whether the structural features meet the specified data form, and if so, executing the structural environmental features and project features.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211085965.6A CN115600695B (en) | 2022-09-06 | 2022-09-06 | Fault diagnosis method for metering equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211085965.6A CN115600695B (en) | 2022-09-06 | 2022-09-06 | Fault diagnosis method for metering equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115600695A CN115600695A (en) | 2023-01-13 |
| CN115600695B true CN115600695B (en) | 2023-10-17 |
Family
ID=84843432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211085965.6A Active CN115600695B (en) | 2022-09-06 | 2022-09-06 | Fault diagnosis method for metering equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115600695B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116330041B (en) * | 2023-05-26 | 2023-08-08 | 中科航迈数控软件(深圳)有限公司 | Fault detection method, device, equipment and medium for numerical control machining transmission device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108732528A (en) * | 2018-05-28 | 2018-11-02 | 国网福建省电力有限公司电力科学研究院 | A kind of digitalized electrical energy meter method for diagnosing faults based on depth confidence network |
| CN109492783A (en) * | 2018-11-14 | 2019-03-19 | 中国电力科学研究院有限公司 | A kind of Application of Power Metering Instruments failure risk prediction technique based on GBDT |
| CN110222991A (en) * | 2019-06-10 | 2019-09-10 | 国网江苏省电力有限公司常州供电分公司 | Metering device method for diagnosing faults based on RF-GBDT |
| CN112508053A (en) * | 2020-11-10 | 2021-03-16 | 泽恩科技有限公司 | Intelligent diagnosis method, device, equipment and medium based on integrated learning framework |
| CN113469231A (en) * | 2021-06-21 | 2021-10-01 | 中国原子能科学研究院 | Fault diagnosis method, fault diagnosis system, computer device, and storage medium |
| CN113642244A (en) * | 2021-08-23 | 2021-11-12 | 广东电网有限责任公司 | Power metering equipment fault prediction method based on artificial intelligence |
| CN114638384A (en) * | 2022-05-17 | 2022-06-17 | 四川观想科技股份有限公司 | Fault diagnosis method and system based on machine learning |
| CN114760339A (en) * | 2022-04-24 | 2022-07-15 | 中国工商银行股份有限公司 | Fault prediction method, apparatus, device, medium, and product |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109933881A (en) * | 2019-03-06 | 2019-06-25 | 武汉大学 | A kind of Fault Diagnosis of Power Electronic Circuits method based on optimization deepness belief network |
-
2022
- 2022-09-06 CN CN202211085965.6A patent/CN115600695B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108732528A (en) * | 2018-05-28 | 2018-11-02 | 国网福建省电力有限公司电力科学研究院 | A kind of digitalized electrical energy meter method for diagnosing faults based on depth confidence network |
| CN109492783A (en) * | 2018-11-14 | 2019-03-19 | 中国电力科学研究院有限公司 | A kind of Application of Power Metering Instruments failure risk prediction technique based on GBDT |
| CN110222991A (en) * | 2019-06-10 | 2019-09-10 | 国网江苏省电力有限公司常州供电分公司 | Metering device method for diagnosing faults based on RF-GBDT |
| CN112508053A (en) * | 2020-11-10 | 2021-03-16 | 泽恩科技有限公司 | Intelligent diagnosis method, device, equipment and medium based on integrated learning framework |
| CN113469231A (en) * | 2021-06-21 | 2021-10-01 | 中国原子能科学研究院 | Fault diagnosis method, fault diagnosis system, computer device, and storage medium |
| CN113642244A (en) * | 2021-08-23 | 2021-11-12 | 广东电网有限责任公司 | Power metering equipment fault prediction method based on artificial intelligence |
| CN114760339A (en) * | 2022-04-24 | 2022-07-15 | 中国工商银行股份有限公司 | Fault prediction method, apparatus, device, medium, and product |
| CN114638384A (en) * | 2022-05-17 | 2022-06-17 | 四川观想科技股份有限公司 | Fault diagnosis method and system based on machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115600695A (en) | 2023-01-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109472110B (en) | Method for predicting residual service life of aeroengine based on LSTM network and ARIMA model | |
| CN109543210A (en) | A kind of Wind turbines failure prediction system based on machine learning algorithm platform | |
| CN113469060A (en) | Multi-sensor fusion convolution neural network aeroengine bearing fault diagnosis method | |
| CN106777814B (en) | Reliability prediction method based on multi-source hierarchical information updating and failure physics | |
| CN109583520B (en) | State evaluation method of cloud model and genetic algorithm optimization support vector machine | |
| BahooToroody et al. | A condition monitoring based signal filtering approach for dynamic time dependent safety assessment of natural gas distribution process | |
| CN114723285B (en) | Power grid equipment safety evaluation prediction method | |
| CN105003453A (en) | Online monitoring and fault diagnosis system of mine fan | |
| CN112083244B (en) | Integrated intelligent diagnosis system for faults of avionic equipment | |
| CN104390657A (en) | Generator set operating parameter measuring sensor fault diagnosis method and system | |
| CN110175324B (en) | Power grid operation instruction verification method and system based on data mining | |
| CN114021932A (en) | Energy efficiency evaluation and diagnosis method, system and medium for wind turbine generator | |
| CN116308304B (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
| CN110852509A (en) | Fault prediction method and device of IGBT module and storage medium | |
| CN111382494A (en) | System and method for detecting anomalies in sensory data of industrial machines | |
| CN114519923A (en) | Intelligent diagnosis and early warning method and system for power plant | |
| CN115600695B (en) | Fault diagnosis method for metering equipment | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| Li et al. | Application of Big Data Technology in Evaluation of Operating State of High-Pressure Hydrogenation Heat Exchanger | |
| CN115406483A (en) | Hydroelectric generating set fault identification method, device, equipment and readable storage medium | |
| CN113313365A (en) | Degradation early warning method and device for primary air fan | |
| KR20220089853A (en) | Method for Failure prediction and prognostics and health management of renewable energy generation facilities using machine learning technology | |
| Bond et al. | A hybrid learning approach to prognostics and health management applied to military ground vehicles using time-series and maintenance event data | |
| CN114320773B (en) | Wind turbine generator system fault early warning method based on power curve analysis and neural network | |
| Zeng et al. | Research on indexes and verification technology of airborne PHM system |
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 |