CN117592383B - Method, system, equipment and medium for predicting equipment health life - Google Patents
Method, system, equipment and medium for predicting equipment health life Download PDFInfo
- Publication number
- CN117592383B CN117592383B CN202410078181.3A CN202410078181A CN117592383B CN 117592383 B CN117592383 B CN 117592383B CN 202410078181 A CN202410078181 A CN 202410078181A CN 117592383 B CN117592383 B CN 117592383B
- Authority
- CN
- China
- Prior art keywords
- equipment
- index weight
- value
- weight
- corrosion
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000036541 health Effects 0.000 title claims abstract description 52
- 238000005260 corrosion Methods 0.000 claims abstract description 70
- 230000007797 corrosion Effects 0.000 claims abstract description 70
- 238000013528 artificial neural network Methods 0.000 claims abstract description 40
- 230000002285 radioactive effect Effects 0.000 claims abstract description 31
- 238000004458 analytical method Methods 0.000 claims abstract description 22
- 210000002569 neuron Anatomy 0.000 claims description 42
- 239000013598 vector Substances 0.000 claims description 40
- 238000012549 training Methods 0.000 claims description 20
- 238000003860 storage Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000005855 radiation Effects 0.000 description 16
- 239000000463 material Substances 0.000 description 10
- 239000011159 matrix material Substances 0.000 description 10
- 230000002378 acidificating effect Effects 0.000 description 8
- 229910000975 Carbon steel Inorganic materials 0.000 description 6
- 239000010962 carbon steel Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 239000007788 liquid Substances 0.000 description 5
- 230000001052 transient effect Effects 0.000 description 5
- 238000011282 treatment Methods 0.000 description 5
- 239000002699 waste material Substances 0.000 description 5
- VEXZGXHMUGYJMC-UHFFFAOYSA-N Hydrochloric acid Chemical compound Cl VEXZGXHMUGYJMC-UHFFFAOYSA-N 0.000 description 4
- QAOWNCQODCNURD-UHFFFAOYSA-N Sulfuric acid Chemical compound OS(O)(=O)=O QAOWNCQODCNURD-UHFFFAOYSA-N 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 229910052751 metal Inorganic materials 0.000 description 4
- 239000002184 metal Substances 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- HEMHJVSKTPXQMS-UHFFFAOYSA-M Sodium hydroxide Chemical compound [OH-].[Na+] HEMHJVSKTPXQMS-UHFFFAOYSA-M 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 229910052739 hydrogen Inorganic materials 0.000 description 2
- 239000001257 hydrogen Substances 0.000 description 2
- -1 hydrogen ions Chemical class 0.000 description 2
- 150000002500 ions Chemical class 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 229910021645 metal ion Inorganic materials 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 239000002901 radioactive waste Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 229910000976 Electrical steel Inorganic materials 0.000 description 1
- 229910001069 Ti alloy Inorganic materials 0.000 description 1
- RTAQQCXQSZGOHL-UHFFFAOYSA-N Titanium Chemical compound [Ti] RTAQQCXQSZGOHL-UHFFFAOYSA-N 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 229910021529 ammonia Inorganic materials 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000002927 high level radioactive waste Substances 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
- 239000010936 titanium Substances 0.000 description 1
- 229910052719 titanium Inorganic materials 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
Abstract
The invention discloses a method, a system, equipment and a medium for predicting the health life of equipment, which relate to the field of equipment health life prediction and have the technical scheme that: acquiring real-time operation data of the equipment, wherein the real-time operation data comprise service time, pH value, temperature, humidity, pressure and radioactive dose; inputting real-time operation data into a pre-constructed corrosion index weight model for analysis to obtain respective first index weights of service time, pH value, temperature, humidity, pressure and radioactive dose; and inputting the first index weight into the self-organizing map neural network which is trained in advance to obtain a prediction result of the equipment health life. The invention predicts the healthy service life of the equipment under different running conditions more accurately.
Description
Technical Field
The present invention relates to the field of equipment health life prediction, and more particularly, to an equipment health life prediction method, system, equipment and medium.
Background
The health service life of the equipment is mainly influenced by the following factors, in particular: material quality: the material of the equipment determines the durability and corrosion resistance of the equipment, and the service life of different materials in different medium environments can be different. Medium: factors such as medium type, concentration, temperature and the like in the equipment have great influence on corrosion and abrasion degree of the equipment; the service lives of different media in different devices are also different; for example, acidic media (e.g., sulfuric acid, hydrochloric acid, etc.) typically cause acidic corrosion of the equipment. Under an acidic environment, hydrogen ions (H+) in an acidic medium react with the metal surface to cause the metal ions to dissolve and release electrons; this can lead to corrosion pits or layers on the device surface, thereby reducing its mechanical strength and corrosion resistance. Some neutral media (such as water) have less corrosive effect on the equipment; however, the presence of certain conditions, such as high oxygen levels, the presence of other ions or organics in the water, etc., may still cause corrosion of the equipment. Environment: the operation state and the maintenance quality are also factors directly influencing the service life of the equipment, and links such as vibration, temperature, pressure, humidity and the like are changed. Length of service: in general, as the length of service increases, the length of service ages slowly and its storage capacity slowly decreases. Radiation dose: irradiation accelerates the corrosion rate of nuclear waste equipment in deep geological treatments, which is related to the ability of y-ray radiation to alter the properties of the electrode process while at the same time destroying its dynamic balance, and irradiation damage in the crystal lattice is also one of its factors.
The above-mentioned influencing factors, such as materials, media, environment, service time, radioactive dose, etc., can cause corrosion of the equipment to different extents, but the corrosion extents of the equipment made of different materials may be correspondingly changed under different service environments, so that the service life of the equipment is changed, and the influence of the influencing factors under different running conditions on the health service life of the equipment is not considered in the prior art, so that the prediction of the health service life of the equipment is not accurate enough.
Therefore, how to predict the health life of equipment under different operating conditions more accurately is a problem that needs to be solved at present.
Disclosure of Invention
The invention aims to provide a method, a system, equipment and a medium for predicting the health life of equipment, which can accurately predict the health life of equipment under different running conditions.
The technical aim of the invention is realized by the following technical scheme:
in a first aspect of the present invention, there is provided a method for predicting the health life of a device, the method comprising:
acquiring real-time operation data of the equipment, wherein the real-time operation data comprise service time, pH value, temperature, humidity, pressure and radioactive dose;
inputting real-time operation data into a pre-constructed corrosion index weight model for analysis to obtain respective first index weights of service time, pH value, temperature, humidity, pressure and radioactive dose;
and inputting the first index weight into the self-organizing map neural network which is trained in advance to obtain a prediction result of the equipment health life.
In one implementation, the pre-constructed corrosion index weight model is specifically constructed by: and establishing a corrosion index weight model comprising a target layer, a criterion layer and a scheme layer from top to bottom, wherein the target layer is a weight factor influencing the corrosion degree of equipment, the criterion layer is an influence factor type influencing the corrosion degree of the equipment, and the scheme layer comprises an influence factor influencing the factor type.
In one implementation, the impact factor types include device factors and service environment factors; wherein the influencing factors of the equipment factors comprise the service time, pH value, pressure and radioactive dose of the equipment, and the influencing factors of the service environment factors comprise the temperature and humidity of the service environment of the equipment.
In one implementation, a training process for a self-organizing map neural network includes:
determining the number of neurons of an input layer of the self-organizing map neural network according to the dimension of the second index weight, determining the number of neurons of an output layer according to the number of samples of the second index weight, and initializing network parameters of the self-organizing map neural network; wherein the network parameters comprise weight vectors, learning rates and domain functions of neurons;
the second index weight and the factor value of the historical operation data are weighted and summed to obtain a comprehensive index weight, the comprehensive index weight is used as a training sample, the Euclidean distance between the neuron of the output layer and the comprehensive index weight is calculated, and the winning neuron is determined according to the Euclidean distance;
updating the weight vectors of the neurons of the input layer and the output layer according to the winning neurons and the optimal field, updating the learning rate and the field function according to the updating result of the weight vectors of the neurons until the iteration number reaches the preset iteration number, and storing the network parameters under the current iteration number to obtain the self-organizing map neural network after training is completed.
In one implementation, the factor value of the historical operating data is specifically: the pH value is linearly and incrementally distributed according to the difference value of 7; the service time is linearly and incrementally distributed to take value according to the design service life; at a temperature of 60 DEG C o C-80 o C is the outward decreasing distribution value of the peak value interval; the pressure is linearly and incrementally distributed to take value from the empty state of the equipment to the rated capacity; humidity takes a value in a linear stage distribution.
In one implementation, historical operating data of the device is input to a corrosion indicator weight model for analysis to obtain a second indicator weight.
In one implementation, before the historical operating data of the device is input into the corrosion indicator weight model for analysis to obtain the second indicator weight, the method further includes: and processing the historical operation data by adopting the local abnormal factors, and removing abnormal data points.
In a second aspect of the present invention, there is provided a device health lifetime prediction system, the system comprising:
the data acquisition module is used for acquiring real-time operation data of the equipment, wherein the real-time operation data comprise service time, pH value, temperature, humidity, pressure and radioactive dose;
the analysis module is used for inputting the real-time operation data into a pre-constructed corrosion index weight model for analysis to obtain respective first index weights of service time, pH value, temperature, humidity, pressure and radioactive dose;
and the prediction module is used for inputting the first index weight into the pre-trained self-organizing map neural network to obtain a prediction result of the equipment health life.
In a third aspect of the present invention, there is provided an electronic device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor implements the steps of a device health lifetime prediction method as provided in the first aspect of the present invention.
In a fourth aspect of the present invention, there is provided a computer readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of a device health lifetime prediction method as provided in the first aspect of the present invention.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a method for predicting the health life of equipment, which comprises the steps of acquiring real-time operation data of the equipment, wherein the real-time operation data comprise service time, pH value, temperature, humidity, pressure and radioactive dose; inputting real-time operation data into a pre-constructed corrosion index weight model for analysis to obtain respective first index weights of service time, pH value, temperature, humidity, pressure and radioactive dose; and inputting the first index weight into the self-organizing map neural network which is trained in advance to obtain a prediction result of the equipment health life. According to the method, the influence of different service time, pH value, temperature, humidity, pressure and radioactive dose on the corrosion degree of the equipment is considered, the first index weight of the corrosion degree of the equipment, which is influenced by real-time operation data, is analyzed, and the first index weight is input into the self-organizing map neural network trained in advance, so that the healthy service life of the equipment can be accurately predicted.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention. In the drawings:
fig. 1 shows a schematic flow chart of a method for predicting the health life of equipment according to an embodiment of the present invention;
FIG. 2 illustrates a functional block diagram of a device health life prediction system provided by an embodiment of the present invention;
fig. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention.
In the drawings, the reference numerals and corresponding part names:
210. a data acquisition module, 220 and an analysis module; 230. a prediction module; 310. a processor; 320. a memory; 321. one or more programs; 330. a communication interface.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention.
It is noted that the terms "comprises" or "comprising" when utilized in various embodiments of the present application are indicative of the existence of, and do not limit the addition of, one or more functions, operations or elements of the subject application. Furthermore, as used in various embodiments of the present application, the terms "comprises," "comprising," and their cognate terms are intended to refer to a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be interpreted as first excluding the existence of or increasing likelihood of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing.
It should be appreciated that terms such as "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
The device of the embodiment of the application refers to a device for storing radioactive waste liquid, namely a nuclear waste liquid treatment device, and comprises a liquid pumping device, a pipeline, a storage tank and a transit metal device. The health service life of the equipment is mainly influenced by the following factors, in particular: material quality: the material of the equipment determines the durability and corrosion resistance of the equipment, and different materials have different service lives in different medium environments, for example, nuclear waste liquid treatment equipment manufactured by silicon steel is used for placing low radioactive doses, and the carbon steel has higher corrosion rate, so the equipment is suitable for manufacturing medium-low radioactive waste storage tanks. As another example, a nuclear waste liquid treatment apparatus made of titanium alloy is an apparatus for placing a high radioactive dose, since titanium and its alloys are suitable for disposal of high level waste due to good long-term corrosion resistance. Medium: factors such as medium type, concentration, temperature and the like in the equipment have great influence on corrosion and abrasion degree of the equipment; the service lives of different media in different devices are also different; acidic media (e.g., sulfuric acid, hydrochloric acid, etc.) typically cause acidic corrosion of carbon steel. Under an acidic environment, hydrogen ions (H+) in an acidic medium react with the metal surface to cause the metal ions to dissolve and release electrons; this can lead to corrosion pits or layers on the surface of the carbon steel, thereby reducing its mechanical strength and corrosion resistance; the corrosion of carbon steel by alkaline media (such as sodium hydroxide, ammonia, etc.) is relatively small. Some neutral media (such as water) have less corrosion to carbon steel; however, corrosion of carbon steel may still be caused under certain conditions, such as high oxygen content, the presence of other ions or organics in the water, etc. Environment: the operation state and the maintenance quality are also factors directly influencing the service life of the equipment, and links such as vibration, temperature, pressure, humidity and the like are changed. Length of service: in general, as the length of service increases, the length of service ages slowly and its storage capacity slowly decreases. Radiation dose: irradiation accelerates the corrosion rate of nuclear waste equipment in deep geological treatments, which is related to the ability of y-ray radiation to alter the properties of the electrode process while at the same time destroying its dynamic balance, and irradiation damage in the crystal lattice is also one of its factors.
The above-mentioned influencing factors, such as materials, media, environment, service time, radioactive dose, etc., can cause corrosion of the equipment to different extents, but the corrosion extents of the equipment made of different materials may be correspondingly changed under different service environments, so that the service life of the equipment is changed, and the influence of different influencing factors on the health service life of the equipment under the operation condition is not considered in the prior art, so that the prediction of the health service life of the equipment is not accurate enough.
Based on the shortcomings of the prior art described above, embodiments of the present invention provide a method, system, device, and medium for predicting the health life of a device by obtaining real-time operational data of the device, wherein the real-time operational data includes time of service, pH, temperature, humidity, pressure, and radiation dose; inputting real-time operation data into a pre-constructed corrosion index weight model for analysis to obtain respective first index weights of service time, pH value, temperature, humidity, pressure and radioactive dose; and inputting the first index weight into the self-organizing map neural network which is trained in advance to obtain a prediction result of the equipment health life. According to the method, the influence of different service time, pH value, temperature, humidity, pressure and radioactive dose on the corrosion degree of the equipment is considered, the first index weight of the corrosion degree of the equipment, which is influenced by real-time operation data, is analyzed, and the first index weight is input into the self-organizing map neural network trained in advance, so that the healthy service life of the equipment can be accurately predicted.
In the embodiment of the present application, the method for predicting the health life of the device is applicable to an electronic device or a server, such as a computer, etc., where an operating system of the electronic device may include, but is not limited to, an Android operating system, an IOS operating system, a Synbian (saiban) operating system, a BlackBerry operating system, a windows phone8 operating system, etc. In an embodiment of the application, an electronic device may be provided with a user interface (UserInterface, UI), an interface module and a processor (CPU).
Referring to fig. 1, fig. 1 is a schematic flow chart of a method for predicting the health life of an apparatus according to an embodiment of the present application, and as shown in fig. 1, the method includes the following steps:
s110, acquiring real-time operation data of the equipment, wherein the real-time operation data comprise service time, pH value, temperature, humidity, pressure and radioactive dose.
In this embodiment, the real-time operating data includes time of service, pH, temperature, humidity, pressure, and radiation dose, all of which may contribute to the increased corrosion level of the equipment.
It is to be appreciated that the real-time operational data obtained by the present embodiments may include any combination of one or more of time of service, pH, temperature, humidity, pressure, and radiation dose, for example, the real-time operational data includes time of service, pH, temperature, humidity, and pressure, and for example, the real-time operational data includes time of service, pH, temperature, pressure, and radiation dose.
S120, inputting the real-time operation data into a pre-constructed corrosion index weight model for analysis, and obtaining the respective first index weights of service time, pH value, temperature, humidity, pressure and radioactive dose.
In this embodiment, the construction process of the pre-constructed corrosion index weight model specifically includes: and establishing a corrosion index weight model comprising a target layer, a criterion layer and a scheme layer from top to bottom, wherein the target layer is a weight factor influencing the corrosion degree of equipment, the criterion layer is an influence factor type influencing the corrosion degree of the equipment, and the scheme layer comprises an influence factor influencing the factor type. Wherein, the influence factor type comprises equipment factors and service environment factors; wherein the influencing factors of the equipment factors comprise the service time, pH value, pressure and radioactive dose of the equipment, and the influencing factors of the service environment factors comprise the temperature and humidity of the service environment of the equipment.
Specifically, an effective corrosion index weight model is established, and various criteria or factors influencing corrosion conditions, such as the environmental humidity, metal type, radioactive dose, working temperature and the like of equipment are listed; constructing a hierarchy structure of the targets, the criteria and the schemes according to the hierarchy relation to form a criterion layer and a scheme layer of the hierarchy analysis, wherein the criterion layer comprises the targets and the criteria, and the scheme layer comprises the sub-criteria; the elements in each layer are compared pairwise, and expert judgment or data analysis is used for obtaining the relative importance between the elements, so that a pairwise comparison matrix is obtained; and obtaining the weight of each hierarchical internal element by calculating the eigenvectors of the pairwise comparison matrix. Then, the weights are transferred to a higher level, and finally the weight of a target layer, namely the relative importance of each criterion to the target, is calculated; consistency test is carried out to ensure consistency of the comparison matrixes, and if the consistency requirement is not met, the comparison matrixes are required to be readjusted until the consistency requirement is met; and comprehensively calculating to obtain a final corrosion index weight model according to the relative importance of each criterion to the target.
For the judgment matrix: the data indexes are compared in pairs, the numbers from 1 to 9 and the reciprocal thereof are used as comparison standards, then the evaluation indexes are scored and arranged, and the judgment matrix is established on the basis.
The process of calculating the comprehensive weight in this embodiment is: the weight is obtained through an arithmetic average method, the weight is obtained through a geometric average method, the weight is obtained through a characteristic value method, the sum of the three weights is integrated, and then average value taking is carried out.
Arithmetic mean method: normalizing the judgment matrix according to the columns; adding the normalized columns (summing by row); and dividing each element in the vector obtained after the addition by n to obtain a weight vector. Specifically, the pH value is 0.39253251, the service time is 0.0655761, the pressure is 0.16241862, the temperature is 0.23104683, the humidity is 0.09185212, and the radiation dose is 0.05657382.
The geometric mean method is to multiply the elements of the matrix according to the rows to obtain a new column vector, and then open each component of the new vector to the power of n; and normalizing the column vector to obtain a weight vector. Specifically, the values of the weight vectors of the parameters calculated based on the geometric mean method are specifically: the weight vector for pH was 0.39595652, the weight vector for service time was 0.06159627, the weight vector for pressure was 0.16240932, the weight vector for temperature was 0.23423477, the weight vector for humidity was 0.09213488, and the weight vector for radiation dose was 0.05366825.
The eigenvalue method is to calculate the maximum eigenvalue of the matrix and the corresponding eigenvector, and normalize the calculated eigenvector to obtain the weight vector. Specifically, the values of the weight vectors of the parameters calculated based on the eigenvalue method are specifically: the weight vector for pH was 0.39652712, the weight vector for service time was 0.06330336, the weight vector for pressure was 0.16262187, the weight vector for temperature was 0.23132833, the humidity was 0.09097733, and the radiation dose was 0.05524199.
The comprehensive average weight is obtained by comprehensively averaging the weights obtained by the three methods. Specifically, the weight vector for pH is 0.39500538, the weight vector for service time is 0.06349191, the weight vector for pressure is 0.16248327, the weight vector for temperature is 0.23220331, the weight vector for humidity is 0.09165478, and the weight vector for radiation dose is 0.05516135.
Consistency test: calculating a characteristic value and a characteristic vector; the CI formula is calculated as (lambda max-n)/(n-1), wherein lambda max is the maximum eigenvalue, and n is the dimension of the judgment matrix; searching a corresponding random consistency index RI according to the dimension of the judgment matrix; the formula for calculating CR is CI/RI; if CR is less than or equal to 0.1, the judgment matrix is considered to have reasonable consistency. For this example, the calculated cr= 0.03533290454342794 had reasonable consistency.
S130, inputting the first index weight into the pre-trained self-organizing map neural network to obtain a prediction result of the equipment health life.
In this embodiment, the training process of the self-organizing map neural network includes: determining the number of neurons of an input layer of the self-organizing map neural network according to the dimension of the second index weight, determining the number of neurons of an output layer according to the number of samples of the second index weight, and initializing network parameters of the self-organizing map neural network; wherein the network parameters comprise weight vectors, learning rates and domain functions of neurons; the second index weight and the factor value of the historical operation data are weighted and summed to obtain a comprehensive index weight, the comprehensive index weight is used as a training sample, the Euclidean distance between the neuron of the output layer and the comprehensive index weight is calculated, and the winning neuron is determined according to the Euclidean distance; updating the weight vectors of the neurons of the input layer and the output layer according to the winning neurons and the optimal field, updating the learning rate and the field function according to the updating result of the weight vectors of the neurons until the iteration number reaches the preset iteration number, and storing the network parameters under the current iteration number to obtain the self-organizing map neural network after training is completed.
In one embodiment, historical operating data of the device is input to a corrosion indicator weight model for analysis to obtain a second indicator weight.
Specifically, a Self-Organizing Map (SOM) is mainly divided into two parts, i.e., an input layer and an output layer. Wherein the number n of neurons of the input layer is equal to the dimension of the input data, i.e. each neuron corresponds to a feature of the input data. The distinction between different self-organizing map neural networks is mainly represented by the output layer, also called the competing layer. For the purpose of visualizing data, the output layer of the self-organizing map neural network is typically a one-dimensional or two-dimensional array, and a high-dimensional array is rarely used. Two-dimensional arrays of self-organizing map neural networks have two main structures: rectangular or hexagonal. All of the output layer neurons are connected by side inhibition. In general, the number of output layer neurons determines the number of classifications and the network size of the ad hoc mapping neural network for the input data, which will directly affect the trained ad hocAccuracy and generalization ability of the weave map neural network. Therefore, careful consideration is needed when selecting the proper number of neurons of the output layer for designing the self-organizing map neural network. For this example, the index weight contains 6 dimensions in total, namely, pH, time of service, pressure, temperature, humidity, and radiation dose, so the number of neurons in the input layer is 6. For the output layer neuron number, the present embodiment determines the output layer neuron number,Irepresenting the number of training samples.
Because the training process of the self-organizing map neural network is realized based on the historical operation data of the equipment, the historical operation data of the equipment is typical event data and mainly comprises event related attribute data and event occurrence time, and the state conditions of the equipment at different moments are recorded. Meanwhile, the change of the running condition of the equipment can be reflected through the historical running data, namely the running state of the equipment usually has a certain transient state. Therefore, in order to solve the problem of transient state of the operation state of the equipment, the factor value (pH value, service time, pressure, temperature, humidity, radiation dose) and the corresponding weight (pH value 0.39500538, service time 0.06349191, pressure 0.16248327, temperature 0.23220331, humidity 0.09165478, radiation dose 0.05516135) of a single piece of historical operation data are used for weighted summation, namely, the second index weight and the factor value of the historical operation data are weighted summation, so that the comprehensive index weight is obtained, and the problem of transient state of the operation state of the training sample equipment is solved. In a further embodiment, the factor value of the historical operating data is specifically: the pH value is linearly and incrementally distributed according to the difference value of 7; the service time is linearly and incrementally distributed to take value according to the design service life; at a temperature of 60 DEG C o C-80 o C is the outward decreasing distribution value of the peak value interval; the pressure is linearly and incrementally distributed to take value from the empty state of the equipment to the rated capacity; humidity takes a value in a linear stage distribution.
Second, a random number generator may be used to generate a random vector within a certain range as an initial value for the weight vector of the neuron. The learning rate is set to a large value during the initial training period so that neurons can quickly make adjustments to the input data. As training proceeds, the learning rate gradually decreases. The domain function initial value is typically a larger value. The network parameters provided above are known techniques for training the self-organizing map neural network, and the training process of the self-organizing map neural network is not explained in detail in this embodiment.
The embodiment considers that in the prior art, the historical operation data of the equipment is used as a training sample for life prediction by adopting the self-organizing map neural network pair, but the method cannot learn the specific influence degree of parameters, so that the life prediction is inaccurate. Therefore, in this embodiment, the weight proportion of the influence of the plurality of parameters on the corrosion degree of the device is firstly analyzed through a corrosion index weight model, so as to determine the influence of each parameter on the corrosion degree of the device, and on the basis, the running state of the device is considered to have a certain transient property generally, so that the comprehensive index weight is formed by carrying out weighted summation on the index weight and the factor value of the parameter, thereby solving the problem that the running state of the device has a certain transient property generally.
In summary, it can be seen that, according to the method for predicting the health life of equipment provided by the embodiment of the present invention, the influence of different service times, pH values, temperatures, humidity, pressures and radioactive doses on the corrosion degree of equipment is considered, the first index weight of the corrosion degree of the equipment affected by real-time operation data is analyzed, and the first index weight is input into a pre-trained self-organizing map neural network, so that the health life of the equipment can be predicted more accurately.
In some embodiments, before inputting the historical operating data of the device into the corrosion indicator weight model for analysis to obtain the second indicator weight, further comprising: and processing the historical operation data by adopting the local abnormal factors, and removing abnormal data points.
In this embodiment, it is proposed to use a density-based abnormal data detection method to remove abnormal data in historical operation data, and make the data with higher density into a normal operation data set of the device, where local abnormal factors are relatively common data abnormal detection in the field of data preprocessing, so that redundant description is not made in this embodiment.
The invention also provides a device health life prediction system which can be used for executing the device health life prediction method described in the embodiment of the invention.
Referring to fig. 2, fig. 2 shows a schematic block diagram of a device health lifetime prediction system according to an embodiment of the present invention, where the system includes:
a data acquisition module 210 for acquiring real-time operational data of the apparatus, wherein the real-time operational data includes time of service, pH, temperature, humidity, pressure, and radiation dose;
the analysis module 220 is configured to input real-time operation data into a pre-constructed corrosion index weight model for analysis, so as to obtain respective first index weights of service time, pH value, temperature, humidity, pressure and radioactive dose;
the prediction module 230 is configured to input the first index weight into the pre-trained ad hoc mapping neural network, and obtain a prediction result of the equipment health lifetime.
An embodiment of an equipment health life prediction system according to the present application and an equipment health life prediction method shown in fig. 1 are based on the invention under the same concept, and by the above detailed description of an equipment health life prediction method, a person skilled in the art can clearly understand the implementation process of an equipment health life prediction system according to the present application, so that, for brevity of description, a detailed description is omitted herein.
Correspondingly, according to the equipment health life prediction system provided by the embodiment of the invention, the influence of different service time, pH value, temperature, humidity, pressure and radioactive dose on the corrosion degree of the equipment is considered, the first index weight of the corrosion degree of the equipment influenced by real-time operation data is analyzed, and the first index weight is input into the self-organizing map neural network trained in advance, so that the health service life of the equipment can be predicted more accurately.
In still another embodiment of the present invention, an electronic device is further provided, and referring to fig. 3, fig. 3 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application. The electronic device includes a processor 310, a memory 320, a communication interface 330, and at least one communication bus for connecting the processor 310, the memory 320, the communication interface 330. Memory 320 includes, but is not limited to, random Access Memory (RAM), read Only Memory (ROM), erasable Programmable Read Only Memory (PROM), or portable read only memory (CD-ROM), and memory 320 is used for associated instructions and data.
The communication interface 330 is used to receive and transmit data. The processor 310 may be one or more CPUs, and in the case where the processor 310 is one CPU, the CPU may be a single core CPU or a multi-core CPU. The processor 310 in the electronic device is configured to read one or more programs 321 stored in the memory 320, and perform the following operations: acquiring real-time operation data of the equipment, wherein the real-time operation data comprise service time, pH value, temperature, humidity, pressure and radioactive dose; inputting real-time operation data into a pre-constructed corrosion index weight model for analysis to obtain respective first index weights of service time, pH value, temperature, humidity, pressure and radioactive dose; and inputting the first index weight into the self-organizing map neural network which is trained in advance to obtain a prediction result of the equipment health life.
It should be noted that, the specific implementation of each operation may be described in the foregoing corresponding description of the method embodiment shown in fig. 1, and the electronic device may be used to execute the device health lifetime prediction method of the foregoing method embodiment of the present application, which is not described herein in detail.
In yet another embodiment of the present invention, there is also provided a computer-readable storage medium that is a memory device in a computer device for storing a program and data. It is understood that the computer readable storage medium herein may include both built-in storage media in a computer device and extended storage media supported by the computer device. The computer-readable storage medium provides a storage space storing an operating system of the terminal. Also stored in the memory space are one or more instructions, which may be one or more computer programs (including program code), adapted to be loaded and executed by the processor. The computer readable storage medium herein may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. One or more instructions stored in a computer-readable storage medium may be loaded and executed by a processor to implement the corresponding steps of the method for predicting device health life in the above embodiments. It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (6)
1. A method for predicting the health life of a device, the method comprising:
acquiring real-time operation data of the equipment, wherein the real-time operation data comprise service time, pH value, temperature, humidity, pressure and radioactive dose;
inputting real-time operation data into a pre-constructed corrosion index weight model for analysis to obtain respective first index weights of service time, pH value, temperature, humidity, pressure and radioactive dose; the construction process of the pre-constructed corrosion index weight model specifically comprises the following steps: establishing a corrosion index weight model comprising a target layer, a criterion layer and a scheme layer from top to bottom, wherein the target layer is a weight factor for influencing the corrosion degree of equipment, the criterion layer is an influence factor type for influencing the corrosion degree of the equipment, and the scheme layer comprises an influence factor for influencing the factor type; wherein, the influence factor type comprises equipment factors and service environment factors; wherein, the influencing factors of the equipment factors comprise the service time, pH value, pressure and radioactive dose of the equipment, and the influencing factors of the service environment factors comprise the temperature and humidity of the service environment of the equipment;
inputting the first index weight into a pre-trained self-organizing map neural network to obtain a prediction result of the health life of the equipment; the training process of the self-organizing map neural network comprises the following steps: determining the number of neurons of an input layer of the self-organizing map neural network according to the dimension of the second index weight, determining the number of neurons of an output layer according to the number of samples of the second index weight, and initializing network parameters of the self-organizing map neural network; wherein the network parameters comprise weight vectors, learning rates and domain functions of neurons; the second index weight and the factor value of the historical operation data are weighted and summed to obtain a comprehensive index weight, the comprehensive index weight is used as a training sample, the Euclidean distance between the neuron of the output layer and the comprehensive index weight is calculated, and the winning neuron is determined according to the Euclidean distance; updating the weight vectors of the neurons of the input layer and the output layer according to the winning neurons and the optimal field, updating the learning rate and the field function according to the updating result of the weight vectors of the neurons until the iteration times reach the preset iteration times, and storing the network parameters under the current iteration times to obtain the self-organizing map neural network after training is completed; and the historical operation data of the equipment is input into a corrosion index weight model for analysis to obtain a second index weight.
2. The method for predicting the health life of a device according to claim 1, wherein the factor values of the historical operating data are specifically: the pH value was linearly varied by 7Increasing the distribution value; the service time is linearly and incrementally distributed to take value according to the design service life; at a temperature of 60 DEG C o C-80 o C is the outward decreasing distribution value of the peak value interval; the pressure is linearly and incrementally distributed to take value from the empty state of the equipment to the rated capacity; humidity takes a value in a linear stage distribution.
3. The method of claim 1, wherein before inputting the historical operating data of the device into the corrosion indicator weight model for analysis to obtain the second indicator weight, further comprising: and processing the historical operation data by adopting the local abnormal factors, and removing abnormal data points.
4. A device health life prediction system, the system comprising:
the data acquisition module is used for acquiring real-time operation data of the equipment, wherein the real-time operation data comprise service time, pH value, temperature, humidity, pressure and radioactive dose;
the analysis module is used for inputting the real-time operation data into a pre-constructed corrosion index weight model for analysis to obtain respective first index weights of service time, pH value, temperature, humidity, pressure and radioactive dose; the construction process of the pre-constructed corrosion index weight model specifically comprises the following steps: establishing a corrosion index weight model comprising a target layer, a criterion layer and a scheme layer from top to bottom, wherein the target layer is a weight factor for influencing the corrosion degree of equipment, the criterion layer is an influence factor type for influencing the corrosion degree of the equipment, and the scheme layer comprises an influence factor for influencing the factor type; wherein, the influence factor type comprises equipment factors and service environment factors; wherein, the influencing factors of the equipment factors comprise the service time, pH value, pressure and radioactive dose of the equipment, and the influencing factors of the service environment factors comprise the temperature and humidity of the service environment of the equipment;
the prediction module is used for inputting the first index weight into the self-organizing map neural network which is trained in advance to obtain a prediction result of the healthy life of the equipment; the training process of the self-organizing map neural network comprises the following steps: determining the number of neurons of an input layer of the self-organizing map neural network according to the dimension of the second index weight, determining the number of neurons of an output layer according to the number of samples of the second index weight, and initializing network parameters of the self-organizing map neural network; wherein the network parameters comprise weight vectors, learning rates and domain functions of neurons; the second index weight and the factor value of the historical operation data are weighted and summed to obtain a comprehensive index weight, the comprehensive index weight is used as a training sample, the Euclidean distance between the neuron of the output layer and the comprehensive index weight is calculated, and the winning neuron is determined according to the Euclidean distance; updating the weight vectors of the neurons of the input layer and the output layer according to the winning neurons and the optimal field, updating the learning rate and the field function according to the updating result of the weight vectors of the neurons until the iteration times reach the preset iteration times, and storing the network parameters under the current iteration times to obtain the self-organizing map neural network after training is completed; and the historical operation data of the equipment is input into a corrosion index weight model for analysis to obtain a second index weight.
5. An electronic device comprising a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program when executed by the processor implements the steps of a device health lifetime prediction method as claimed in any one of claims 1 to 3.
6. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of a device health lifetime prediction method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410078181.3A CN117592383B (en) | 2024-01-19 | 2024-01-19 | Method, system, equipment and medium for predicting equipment health life |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410078181.3A CN117592383B (en) | 2024-01-19 | 2024-01-19 | Method, system, equipment and medium for predicting equipment health life |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117592383A CN117592383A (en) | 2024-02-23 |
| CN117592383B true CN117592383B (en) | 2024-03-26 |
Family
ID=89920540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410078181.3A Active CN117592383B (en) | 2024-01-19 | 2024-01-19 | Method, system, equipment and medium for predicting equipment health life |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117592383B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108776855A (en) * | 2018-04-17 | 2018-11-09 | 中国电力科学研究院有限公司 | A kind of smart machine health status evaluation method and system |
| CN112200327A (en) * | 2020-10-14 | 2021-01-08 | 北京理工大学 | MES equipment maintenance early warning method and system |
| CN112816884A (en) * | 2021-03-01 | 2021-05-18 | 中国人民解放军国防科技大学 | Method, device and equipment for monitoring health state of satellite lithium ion battery |
| CN112834841A (en) * | 2020-12-30 | 2021-05-25 | 北京爱康宜诚医疗器材有限公司 | Method and device for detecting service life of infrared camera and processor |
| CN114444972A (en) * | 2022-02-24 | 2022-05-06 | 湖南大学 | Power transformer health state assessment method based on graph neural network |
| CN114638164A (en) * | 2022-03-21 | 2022-06-17 | 西安热工研究院有限公司 | Method for predicting high-temperature creep life of pressure pipeline of power station |
| CN115271238A (en) * | 2022-08-10 | 2022-11-01 | 广东电网有限责任公司 | Method and device for predicting service life of transformer |
| CN115470717A (en) * | 2022-10-31 | 2022-12-13 | 四川工程职业技术学院 | Method, device, equipment and storage medium for predicting remaining life of robot |
| CN115587527A (en) * | 2022-08-31 | 2023-01-10 | 广东邦普循环科技有限公司 | Battery life prediction method, system, terminal device and computer readable medium |
| CN116087670A (en) * | 2023-03-28 | 2023-05-09 | 上海擎测机电工程技术有限公司 | Method and system for analyzing equipment state by AR equipment connection Wen Zhen sensor |
| CN116124460A (en) * | 2022-12-26 | 2023-05-16 | 江西理工大学 | Bearing life prediction method and system based on health index construction |
| CN116796617A (en) * | 2022-03-14 | 2023-09-22 | 中国科学院沈阳自动化研究所 | Rolling bearing equipment residual life prediction method and system based on data identification |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2024003643A (en) * | 2022-06-27 | 2024-01-15 | 日本電気株式会社 | Method of learning neural network, computer program, and remaining life prediction system |
-
2024
- 2024-01-19 CN CN202410078181.3A patent/CN117592383B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108776855A (en) * | 2018-04-17 | 2018-11-09 | 中国电力科学研究院有限公司 | A kind of smart machine health status evaluation method and system |
| CN112200327A (en) * | 2020-10-14 | 2021-01-08 | 北京理工大学 | MES equipment maintenance early warning method and system |
| CN112834841A (en) * | 2020-12-30 | 2021-05-25 | 北京爱康宜诚医疗器材有限公司 | Method and device for detecting service life of infrared camera and processor |
| CN112816884A (en) * | 2021-03-01 | 2021-05-18 | 中国人民解放军国防科技大学 | Method, device and equipment for monitoring health state of satellite lithium ion battery |
| CN114444972A (en) * | 2022-02-24 | 2022-05-06 | 湖南大学 | Power transformer health state assessment method based on graph neural network |
| CN116796617A (en) * | 2022-03-14 | 2023-09-22 | 中国科学院沈阳自动化研究所 | Rolling bearing equipment residual life prediction method and system based on data identification |
| CN114638164A (en) * | 2022-03-21 | 2022-06-17 | 西安热工研究院有限公司 | Method for predicting high-temperature creep life of pressure pipeline of power station |
| CN115271238A (en) * | 2022-08-10 | 2022-11-01 | 广东电网有限责任公司 | Method and device for predicting service life of transformer |
| CN115587527A (en) * | 2022-08-31 | 2023-01-10 | 广东邦普循环科技有限公司 | Battery life prediction method, system, terminal device and computer readable medium |
| CN115470717A (en) * | 2022-10-31 | 2022-12-13 | 四川工程职业技术学院 | Method, device, equipment and storage medium for predicting remaining life of robot |
| CN116124460A (en) * | 2022-12-26 | 2023-05-16 | 江西理工大学 | Bearing life prediction method and system based on health index construction |
| CN116087670A (en) * | 2023-03-28 | 2023-05-09 | 上海擎测机电工程技术有限公司 | Method and system for analyzing equipment state by AR equipment connection Wen Zhen sensor |
Non-Patent Citations (5)
| Title |
|---|
| A Reliability-Optimized Maximum Power Point Tracking Algorithm Utilizing Neural Networks for Long-Term Lifetime Prediction for Photovoltaic Power Converters;Mahmoud Shahbazi等;《Energies》;20230801;第16卷(第16期);1-24 * |
| Remaining Useful Life Prediction of Lithium-Ion Batteries by Using a Denoising Transformer-Based Neural Network;Yunlong Han等;《Energies》;20230901;第16卷(第17期);1-16 * |
| 基于AGA-GRNN神经网络的刀具寿命预测研究;李浩平等;《三峡大学学报(自然科学版)》;20181113;第40卷(第06期);84-87 * |
| 基于神经网络和专家系统的城镇煤气管道漏损分析与寿命预测;郭佳;《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑) 》;20080915;C038-565 * |
| 滚动轴承的退化状态划分与剩余寿命预测;隋文涛等;《机械设计与制造》;20221208(第12期);301-304 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117592383A (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Su et al. | Performance improvement method of support vector machine‐based model monitoring dam safety | |
| EP3380948B1 (en) | Environmental monitoring systems, methods and media | |
| CN111784061B (en) | Training method, device and equipment for power grid engineering cost prediction model | |
| Shittu et al. | A systematic review of structural reliability methods for deformation and fatigue analysis of offshore jacket structures | |
| CN114282309B (en) | Stationary blade regulating mechanism system reliability analysis method based on multi-target agent model | |
| CN109165421B (en) | Ship shafting bearing load value prediction method based on genetic algorithm optimization BP neural network | |
| CN112989621B (en) | Model performance evaluation method, device, equipment and storage medium | |
| Ren et al. | A new interval prediction method for displacement behavior of concrete dams based on gradient boosted quantile regression | |
| Jiménez‐Come et al. | Characterization of pitting corrosion of stainless steel using artificial neural networks | |
| CN111044926A (en) | Method for predicting service life of proton exchange membrane fuel cell | |
| CN111639722A (en) | Transformer fault diagnosis method based on principal component analysis and twin support vector machine | |
| CN117592383B (en) | Method, system, equipment and medium for predicting equipment health life | |
| CN116094068A (en) | Power grid dispatching method, equipment and medium based on carbon emission prediction mechanism | |
| CN112488399B (en) | Power load prediction method and device | |
| Lin et al. | An explainable probabilistic model for health monitoring of concrete dam via optimized sparse bayesian learning and sensitivity analysis | |
| Peters et al. | Does the scientific underpinning of regulatory tools to estimate bioavailability of nickel in freshwaters matter? The European‐wide environmental quality standard for nickel | |
| Li et al. | A Deformation Prediction Model of High Arch Dams in the Initial Operation Period Based on PSR‐SVM‐IGWO | |
| CN116562120A (en) | RVE-based turbine engine system health condition assessment method and RVE-based turbine engine system health condition assessment device | |
| CN115101136A (en) | Large-scale aluminum electrolysis cell global anode effect prediction method | |
| Ilupeju | Modelling South Africa's market risk using the APARCH model and heavy-tailed distributions. | |
| CN113537753B (en) | Intelligent component environment adaptability assessment method | |
| Shittu et al. | A Systematic Review of Structural Reliability Methods for Deformation and Fatigue Analysis of Offshore Jacket Structures. Metals 2021, 11, 50 | |
| Yin et al. | A new state‐of‐health estimation method for Li‐ion batteries based on interpretable belief rule base with expert knowledge credibility | |
| CN116452070B (en) | Large-scale equipment health assessment method and device under multi-identification framework | |
| CN111784010B (en) | Method and system for predicting residual service life of electric gate valve |
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 |