CN117422258A - Economical life calculation method and device for power equipment - Google Patents
Economical life calculation method and device for power equipment Download PDFInfo
- Publication number
- CN117422258A CN117422258A CN202311426403.8A CN202311426403A CN117422258A CN 117422258 A CN117422258 A CN 117422258A CN 202311426403 A CN202311426403 A CN 202311426403A CN 117422258 A CN117422258 A CN 117422258A
- Authority
- CN
- China
- Prior art keywords
- cost
- period
- predicted
- power equipment
- stage
- 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.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 44
- 230000000630 rising effect Effects 0.000 claims description 46
- 239000013598 vector Substances 0.000 claims description 43
- 230000009467 reduction Effects 0.000 claims description 30
- 238000003062 neural network model Methods 0.000 claims description 25
- 238000005315 distribution function Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 15
- 238000003064 k means clustering Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 description 36
- 238000012423 maintenance Methods 0.000 description 22
- 238000004422 calculation algorithm Methods 0.000 description 12
- 230000008859 change Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 241000282461 Canis lupus Species 0.000 description 7
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 230000015654 memory Effects 0.000 description 3
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000007787 long-term memory Effects 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
- 238000005457 optimization Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides an economic life calculation method and device for power equipment, and belongs to the technical field of power. The method comprises the following steps: acquiring historical operation data of all the electric devices of the target type, and acquiring actual annual average period cost corresponding to each operation period of each electric device based on the historical operation data, wherein the actual annual average period cost is a value obtained by dividing the current total operation cost of the electric device by the current operation period; dividing the total operational life of each power device into a plurality of phases; based on the actual annual average period cost of each power equipment in each stage, establishing a period cost model of each stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted according to the period cost model of each stage; and calculating the economic life of the power equipment to be predicted based on the predicted annual average period cost. The invention can accurately calculate the economic life of the power equipment.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to an economic life calculation method and device of electric power equipment.
Background
With the expansion of the physical asset scale of the power grid, the maintenance, overhaul and technical improvement tasks of each power equipment in the power grid are also increasingly severe, and how to ensure the safety of the assets in the power grid and efficiently manage the equipment is a key problem to be solved urgently by power grid enterprises.
In the prior art, the retirement of the power equipment is based on the design life marked by the manufacturer, but the mode can raise the maintenance cost of the equipment, the input is not in direct proportion to the output, and a certain degree of fund waste is caused; the other is to determine the retired life of the power equipment according to the total life cycle cost and the economic life of the power equipment, but the method is to directly predict and calculate the whole life cycle, so that the accuracy of the obtained total life cycle cost is difficult to ensure, and the economic life of the power equipment cannot be accurately calculated.
Therefore, a method capable of accurately calculating the economic life of the power equipment is needed.
Disclosure of Invention
The embodiment of the invention provides a method and a device for calculating the economic life of power equipment, which are used for solving the problem that the economic life of power grid equipment cannot be accurately calculated in the prior art.
In a first aspect, an embodiment of the present invention provides a method for calculating an economic lifetime of an electrical device, including:
Acquiring historical operation data of all the electric devices of the target type, and acquiring actual annual average period cost corresponding to each operation period of each electric device based on the historical operation data, wherein the actual annual average period cost is a value obtained by dividing the current total operation cost of the electric device by the current operation period;
dividing the total operational life of each power device into a plurality of phases;
based on the actual annual average period cost of each power equipment in each stage, establishing a period cost model of each stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted according to the period cost model of each stage;
and calculating the economic life of the power equipment to be predicted based on the predicted annual average period cost.
In one possible implementation, dividing the total operational life of each power device into a plurality of phases includes:
for each power equipment, establishing a feature vector corresponding to each operation period according to historical operation data of the power equipment to obtain a feature vector sample set of the power equipment;
and respectively carrying out K-means clustering on the feature vector sample set of each power device to obtain a clustering result of each power device, and dividing the power device according to the clustering result.
In one possible implementation, the plurality of phases includes a cost reduction phase, a cost leveling phase, and a cost rise phase;
based on the actual annual average cycle cost of the individual power devices within each phase, a cycle cost model for the individual phase is built, comprising:
training a preset neural network model based on the actual annual average period cost of each power device in the cost reduction stage to obtain a period cost model in the cost reduction stage;
training a preset time sequence prediction model based on the actual annual average period cost of each power device in the cost leveling stage to obtain a period cost model of the cost leveling stage;
training a preset neural network model based on the actual annual average period cost of each power device in the cost rising stage to obtain a period cost model in the cost rising stage.
In one possible implementation, predicting the predicted annual average period cost for each operating year of the electrical device to be predicted according to the period cost model of each stage includes:
determining a stage in which the current operation age of the power equipment to be predicted is located;
selecting a corresponding period cost model according to the stage of the current operation period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period;
And obtaining the predicted annual average period cost of each operation period of the power equipment to be predicted according to the actual annual average period cost of each operation period of the power equipment to be predicted before the current operation period and the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period.
In one possible implementation, selecting a corresponding period cost model according to a stage in which a current operating period is located, predicting a predicted annual average period cost for each operating period of the electrical device to be predicted after the current operating period includes:
if the current operation period is a cost reduction period, selecting a period cost model of the cost reduction period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost reduction period; selecting a period cost model of a cost leveling stage, predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost leveling stage, selecting a period cost model of a cost rising stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost rising stage;
If the current operation period is a cost leveling period, selecting a period cost model of the cost leveling period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost leveling period; selecting a period cost model of a cost rising stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost rising stage;
if the current operation period is a cost rising period, selecting a period cost model of the cost rising period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost rising period.
In one possible implementation, calculating the economic life of the electrical device to be predicted based on predicting the annual average period cost includes:
fitting the predicted annual average period cost of each operation period of the power equipment to be predicted to obtain an annual average period cost function of the power equipment to be predicted;
and determining a cost minimum value of the annual average period cost function, and determining the operation life corresponding to the cost minimum value as the economic life of the power equipment to be predicted.
In one possible implementation, before determining the cost minimum of the annual cycle cost function, the method further includes:
calculating a fault distribution function of the power equipment to be predicted based on the historical operation data;
and optimizing the annual average period cost function based on the fault distribution function.
In one possible implementation, after acquiring the historical operation data of all the power devices of the target type, the method further includes:
and performing outlier processing and missing value filling on the historical operation data.
In a second aspect, an embodiment of the present invention provides an economic life calculation device for an electrical device, including:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring historical operation data of all electric equipment of a target type, and acquiring actual annual average period cost corresponding to each operation period of each electric equipment based on the historical operation data, wherein the actual annual average period cost is a value obtained by dividing the current total operation cost of the electric equipment by the current operation period;
the dividing module is used for dividing the total operation period of each power device into a plurality of stages;
the prediction module is used for establishing a period cost model of each stage based on the actual annual average period cost of each power equipment in each stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted according to the period cost model of each stage;
And the calculating module is used for calculating the economic life of the power equipment to be predicted based on the predicted annual average period cost.
In one possible implementation, the partitioning module is specifically configured to:
for each power equipment, establishing a feature vector corresponding to each operation period according to historical operation data of the power equipment to obtain a feature vector sample set of the power equipment;
and respectively carrying out K-means clustering on the feature vector sample set of each power device to obtain a clustering result of each power device, and dividing the power device according to the clustering result.
Compared with the prior art, the embodiment of the invention has the beneficial effects that:
according to the embodiment of the invention, the total operation years of the target type power equipment are divided to obtain different change stages of the annual average period cost of the target type power equipment, the period cost model of each stage is built according to each stage, the relation between the cost of the power equipment and the service life of the power equipment is fully considered to obtain the change trend of each stage, each period cost model can be more in line with the change trend of the corresponding stage, and the pertinence of the period cost model is improved; according to the period cost model of each stage, the prediction annual average period cost of each operation period of the power equipment to be predicted is obtained through prediction, the predicted annual average period cost is more reasonable, the actual situation of the power equipment to be predicted is more met, the accuracy of a prediction result is improved, the economic life of the power equipment to be predicted is accurately calculated, and the reliability of the calculated economic life is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of an implementation of a method for calculating an economic lifetime of an electrical device according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a trend of annual cycle costs of a power device according to an embodiment of the present invention;
FIG. 3 is a graphical representation of an annual cycle cost function of an electrical device provided by an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an economic life calculating device of an electric power device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the following description will be made by way of specific embodiments with reference to the accompanying drawings.
The economic life of the power equipment, that is, the life of the power equipment which is economically optimal, when the power equipment is used continuously beyond the time, the cost and risk of enterprises are increased, and when the power equipment is retired prematurely before the time, the assets of the enterprises are wasted, so that the economic life of the power equipment needs to be accurately calculated.
Based on this, the present invention provides a method for calculating the economic life of an electrical device, referring to an implementation flowchart of the method for calculating the economic life of an electrical device shown in fig. 1, the method is described in detail as follows:
step S101, historical operation data of all the electric devices of the target type are obtained, and based on the historical operation data, the actual annual average period cost corresponding to each operation period of each electric device is obtained, wherein the actual annual average period cost is the current total operation cost of the electric device divided by the current operation period.
In this embodiment, all the power devices of the target type include all the retired power devices and running power devices of the target type; the historical operating data includes operational years, decommissioning years, service years, various cost fees, decommissioning reasons, etc. of all the power devices of the target type, wherein the various cost fees invested include initial investment costs, operating costs, maintenance costs, fault costs, and decommissioning disposal costs of the power devices.
Specifically, the initial investment cost of a certain power transformer is 25 ten thousand yuan, the sum of the operation cost, the maintenance cost, the fault cost and the retired disposal cost is variable cost, the variable cost of the first operation year is 2 ten thousand yuan, the variable cost of the second operation year is 3 ten thousand yuan, the actual annual average period cost corresponding to the first operation year of the power equipment is 27 ten thousand yuan, namely 25+2=27, and the annual average period cost of the second operation year is 15 ten thousand yuan, namely (25+2+3)/2=15.
Step S102, dividing the total operation years of each power device into a plurality of stages.
In this embodiment, for a retired power device, the total operating period is the service period of the retired power device; for an operating power device, the total operating period is the period that the operating power device has been operating.
The operation years of the power equipment are different, the operation cost, maintenance cost, fault cost and retired disposal cost of the power equipment are also changed, and the variable cost of the power equipment has different characteristics in different operation years, for example, the maintenance cost of the power equipment is also increased along with the increase of the operation years, and accordingly, the influence of the variable cost on the annual average period cost is also changed. Thus, a division of the phases of the total operational years is required in order to clarify the different impact of the variable cost on the annual cycle costs.
In addition, since the operation conditions of the respective power devices are different due to the inclusion of the retired power device and the operating power device, the division of each power device may be different, for example, the retired power device may be divided into 3 stages, and the operation duration of the operating power device may be uncertain, and may be divided into 1 stage, 2 stages, or 3 stages.
Step S103, based on the actual annual average period cost of each power equipment in each stage, a period cost model of each stage is established, and according to the period cost model of each stage, the predicted annual average period cost of each operation year of the power equipment to be predicted is predicted.
In this embodiment, since each power device is of the same type, when the total operation years of the power devices are divided according to the same rule, the same phases of all the power devices will have similar characteristics, and thus a period cost model can be established for each phase. Specifically, a period cost model of the first phase may be established based on actual annual average period costs of the first phase of all the power devices; establishing a period cost model of the second stage based on the actual annual average period costs of the second stage of all the power devices; and establishing a period cost model of the third stage and the like based on the actual annual average period cost of the third stage of all the power equipment.
When the equipment to be predicted is predicted, the prediction annual average period cost of the power equipment to be predicted in each stage can be obtained by predicting according to the period cost model of each stage, the annual average period cost obtained by prediction is ensured to be more in line with the change trend of the power equipment, and the accuracy of prediction is ensured.
Step S104, calculating the economic life of the power equipment to be predicted based on the predicted annual average period cost.
According to the embodiment of the invention, the total operation years of the target type power equipment are divided to obtain different change stages of the annual average period cost of the target type power equipment, the period cost model of each stage is built according to each stage, the relation between the cost of the power equipment and the service life of the power equipment is fully considered to obtain the change trend of each stage, each period cost model can be more in line with the change trend of the corresponding stage, and the pertinence of the period cost model is improved; according to the period cost model of each stage, the prediction annual average period cost of each operation period of the power equipment to be predicted is obtained through prediction, the predicted annual average period cost is more reasonable, the actual situation of the power equipment to be predicted is more met, the accuracy of a prediction result is improved, the economic life of the power equipment to be predicted is accurately calculated, and the reliability of the calculated economic life is improved.
In one possible implementation, step S102 divides the total operation period of each power device into a plurality of phases, which can be described in detail as:
for each power equipment, establishing a feature vector corresponding to each operation period according to historical operation data of the power equipment to obtain a feature vector sample set of the power equipment;
and respectively carrying out K-means clustering on the feature vector sample set of each power device to obtain a clustering result of each power device, and dividing the power device according to the clustering result.
In this embodiment, since the initial investment cost is already generated at the time of purchase of the apparatus and does not vary with other factors, the initial investment cost belongs to a fixed cost, and the operation cost, the fault cost, the maintenance cost, and the retired disposal cost all relate to the operation state after the apparatus is put into operation, and belong to a non-fixed cost, i.e., a variable cost. Since the operation cost, maintenance cost and fault cost have different characteristics at different stages, for example, in the initial stage of operation of the power equipment, the power equipment has a good operation state, and only a small amount of operation cost and maintenance cost may be required; in the later operation period of the power equipment, as the power equipment ages, the power equipment may frequently fail, and accordingly, the operation cost, the maintenance cost and the failure cost may also increase. Therefore, the feature vector can be constructed according to the operation cost, the maintenance cost and the fault cost corresponding to each operation period of the power equipment, and the stages are divided.
Optionally, a feature vector corresponding to each operation period can be established according to the operation cost, maintenance cost and fault cost of each power device, so as to obtain a feature vector sample set of the power device.
The process of performing K-means clustering on a feature vector sample set of an electrical device may be:
randomly selecting a predetermined number of initial cluster centers, e.g. three initial cluster centersCan be expressed asWherein (1)>Represents the 0 th iteration, i.e. the j-th initial cluster center,>representing the running cost of the electrical equipment, < >>Representing maintenance costs of the electrical equipment,/->Representing the fault cost of the power equipment, (0) representing the iteration number, i.e. the initial value;
according to the principle that Euclidean distance between each feature vector in the feature vector sample set and each cluster center is minimum, each feature vector is respectively distributed to clusters with the nearest Euclidean distance; for example, the r-th iteration of a certain sample u isWherein (1)>Representing sample u and cluster center->Is provided with->To->For a sample subset of the cluster center, then +.>I.e., u is assigned to the cluster of the j-th cluster closest to the euclidean distance;
updating the cluster center of each cluster according to the feature vector in each cluster, and detecting whether the current cluster center is consistent with the last cluster center; for example according to Updating a cluster center, wherein ∈>Representing the updated cluster center in the (r+1) th iteration,/o>Representing sample subset +.>The total number of samples contained in the sample; and detect->Whether the characteristic vectors are consistent or not, wherein x represents the characteristic vectors;
if the feature vectors are inconsistent, re-executing the step of respectively distributing the feature vectors to clusters with the nearest Euclidean distance and the subsequent step according to the principle that the Euclidean distance of each feature vector in the feature vector sample set from each cluster center is minimum;
and if the feature vectors are consistent, obtaining a clustering result according to the feature vectors corresponding to the current clustering center.
In one possible implementation, the plurality of phases includes a cost reduction phase, a cost leveling phase, and a cost rise phase.
The initial investment cost, i.e., the fixed cost, is increased along with the operation period of the power equipment, the allocated fixed cost in unit time is smaller and smaller, and the operation cost, the maintenance cost and the fault cost are also increased along with the increase of the operation period, and the annual period cost of the power equipment is reduced to be equal to the rising trend along with the increase of the operation period, so that the annual period cost can be divided into a cost reduction stage, a cost leveling stage and a cost rising stage, which are shown in a trend diagram of the annual period cost of the power equipment in fig. 2.
Specifically, the total operation period of the power equipment shown in fig. 2 is 30 years, wherein 0-9 years of the operation period are cost reduction stages, 9-24 years of the operation period are cost leveling stages, and 24-30 years of the operation period are cost rising stages.
In addition, the annual cycle cost of the power equipment may also show a trend of 'falling' to 'rising', that is, a cost leveling stage does not exist, so that the annual cycle cost can be divided into a cost falling stage and a cost rising stage, and the annual cycle cost of the power equipment can be divided according to the annual cycle cost of the power equipment.
In step S103, based on the actual annual average period cost of each power device in each stage, a period cost model of each stage is established, which can be described in detail as follows:
training a preset neural network model based on the actual annual average period cost of each power device in the cost reduction stage to obtain a period cost model in the cost reduction stage;
training a preset time sequence prediction model based on the actual annual average period cost of each power device in the cost leveling stage to obtain a period cost model of the cost leveling stage;
training a preset neural network model based on the actual annual average period cost of each power device in the cost rising stage to obtain a period cost model in the cost rising stage.
In the present embodiment, the relevant factors of the annual cycle cost of the electric power equipment of the target type, such as the initial investment cost, the model number of the electric power equipment, the setting position of the electric power equipment, and the like, may be determined first; and obtaining a period cost model of each stage by establishing a relation between related factors and actual annual average period cost.
Alternatively, the preset neural network model may be an LSTM-BP neural network model based on a combination of a long-short-term memory neural network (Long Short Term Memory, LSTM) and a Back Propagation neural network (BP), and the weight vector and the bias vector of the LSTM-BP neural network model are optimized by a wolf algorithm.
The method comprises the steps of utilizing long-term memory characteristics of an LSTM neural network model, optimizing a BP neural network model, constructing an LSTM-BP neural network model, analyzing the relation between power equipment to be predicted and the acquired power equipment of a target type mainly through the memory characteristics of the LSTM neural network model, and processing the historical operation data of the power equipment of the target type and the power equipment to be predicted; the hidden layer output of the LSTM neural network model is used as the input of the LSTM-BP neural network model, and information transmission is completed; finally, learning historical operation data of the power equipment of the target type is completed through the LSTM-BP neural network model, so that prediction of annual average period cost of the power equipment is realized.
The process of optimizing the weight vector and the bias vector of the LSTM-BP neural network model by the gray wolf algorithm can be as follows:
setting relevant parameters of the gray wolf algorithm, wherein the relevant parameters comprise population size, fitness threshold, iteration times and maximum iteration times;
initializing a population, and taking the positions of individuals of each population in the population as a weight vector and a bias vector of an LSTM-BP neural network model respectively;
calculating the fitness value of each population individual in the current population according to the predicted output value and the actual output value of the LSTM-BP neural network model corresponding to each population individual;
selecting the population individuals corresponding to the minimum three fitness values as a wolf king method, a left protection method and a right protection method respectively, updating the positions of the individuals of each population in the population, and recalculating the fitness values of the individuals of each population in the current population;
detecting whether the minimum fitness value is smaller than a fitness threshold value or not and whether the current iteration number is larger than the maximum iteration number or not;
if the minimum fitness value is not less than the fitness threshold value and the current iteration number is not greater than the maximum iteration number, adding 1 to the current iteration number, and jumping to the step of selecting the population individuals corresponding to the three minimum fitness values as the wolf king, the left guard method and the right guard method respectively and executing the subsequent steps;
And if the minimum fitness value is smaller than the fitness threshold value or the current iteration number is larger than the maximum iteration number, taking the position of the population individual corresponding to the minimum fitness value in the current population as a weight vector and a bias vector of the LSTM-BP neural network model to obtain the LSTM-BP neural network model optimized by the gray wolf algorithm.
The calculation formula of the fitness value is as follows:
wherein f represents a fitness value, N represents the total sample amount of training the LSTM-BP neural network model, f p (i) Representing the predicted value of the ith sample, f o (i) Representing the actual value corresponding to the i-th sample.
Alternatively, the predetermined time series prediction model may be a differential integrated moving average autoregressive model (Autoregressive Integrated Moving Average, ARIMA).
In training and prediction, the data may be preprocessed, specifically by zero-averaging the original sequence, e.g., the original sequence is { y (t) }, and the average value of { y (t) } isThe value of each sample in the new sequence obtained by zero-equalizing the original sequence is x (t) =y (t) -y, so as to form a new sequence { x (t) } for subsequent prediction.
The original sequence may be annual average period cost data corresponding to a cost leveling stage in the obtained historical operation data of the target type of power equipment.
In the differential integration moving average autoregressive model, the number of differential processes is determined by the parameter d in the ARIMA (p, d, 0) model structure, and since the data corresponding to the cost leveling stage in this embodiment is a stable sequence, the parameter d can take a value of 0.
The original sequence is ARIMA (p, d, 0) model, the model of the new sequence obtained by differentiating the original sequence for 0 times is AR (p) model, and parameter estimation and prediction are carried out on the AR (p) model; and obtaining a final predicted value through inverse transformation after obtaining a predicted result.
Wherein, a recursive least squares method with forgetting factors can be adopted for parameter estimation. The forgetting factor has the functions of strengthening the effect of current observation data on parameter estimation, weakening the influence of previous observation data and mainly taking the time variability of model parameters into consideration.
The AR (p) model of the original sequence is a (B) y (t) =e (t), where e (t) represents zero-mean white noise, a (B) represents a back shift operator, and y (t) represents the original sequence.
Then y (t) =a can be obtained 1 y(t-1)+a 2 y(t-2)+…+a p y (t-p) +e (t) in vector form y (t) =φ T (t) θ+e (t), where φ T (t)＝[y(t-1),y(t-2),…,y(t-p)]，θ＝[a 1 ,a 2 ,…,a p ] T 。
Will phi T And (t) and theta are substituted into a recursive least square method formula with forgetting factors, initial values are given, and online recursive parameter estimation is carried out.
Substituting the parameter estimation result into an AR (p) model to predict the annual average period cost of the cost leveling stage.
In addition, the above description has mainly been made of the case where the annual average period cost shows a tendency from "down" to "flat" to "up", and the process of creating the period cost model of each stage is identical to the above embodiment except for the removal of a part of the cost flat stage, for the case where the annual average period cost shows a tendency from "down" to "up".
In a possible implementation manner, the predicting annual average period cost of each operation year of the power equipment to be predicted according to the period cost model of each stage in step S103 may be described in detail as:
step S1031, determining a stage in which the current operation years of the power equipment to be predicted are located;
step S1032, selecting a corresponding period cost model according to the stage of the current operation period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period;
step S1033, obtaining the predicted annual average period cost of each operating period of the electric power equipment to be predicted according to the actual annual average period cost of each operating period of the electric power equipment to be predicted before the current operating period and the predicted annual average period cost of each operating period of the electric power equipment to be predicted after the current operating period.
In this embodiment, the power device to be predicted is a power device that is running, and it is necessary to predict the annual average period cost after the current running period, and since the current running period may be in a cost-down stage, a cost-leveling stage, or a cost-up stage, it is necessary to determine the stage in which the current running period is located first, so as to select a corresponding period cost model for prediction.
In one possible implementation manner, step S1032 selects a corresponding period cost model according to the stage in which the current operation period is located, predicts the predicted annual average period cost of each operation period of the power device to be predicted after the current operation period, and may be described in detail as:
if the current operation period is a cost reduction period, selecting a period cost model of the cost reduction period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost reduction period; selecting a period cost model of a cost leveling stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost leveling stage; selecting a period cost model of a cost rising stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost rising stage;
If the current operation period is a cost leveling period, selecting a period cost model of the cost leveling period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost leveling period; selecting a period cost model of a cost rising stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost rising stage;
if the current operation period is a cost rising period, selecting a period cost model of the cost rising period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost rising period.
In this embodiment, according to the stage in which the current operation period of the power equipment is located, the cycle cost models of the located stage and the later stage are selected, and prediction of the predicted annual average cycle cost of each operation period after the current operation period is performed.
The determination of each stage of the power equipment to be predicted may be determined according to the operation years of each stage of the power equipment of the target type. For example, the annual average period cost of the target type of power equipment tends to "fall" to "level" to "rise", and most of the stages thereof are three stages divided by the operation years of 9 and 24, so that the power equipment to be predicted in the cost-down stage can also be divided by the operation years of 9 and 24; the limit of the cost reduction stage and the cost leveling stage is definitely divided for the power equipment to be predicted in the cost leveling stage, and the cost leveling stage and the cost rising stage are directly divided by the operation period 24; no further partitioning is required for the power plant to be predicted in the cost-up phase.
Further, after the prediction is performed based on the three stages of the division, the boundary points between the annual average period costs corresponding to the stages are selected as the basis of the division stages, so that the boundary of each stage is more clear, and the predicted annual average period cost corresponding to each operation period is accurately determined.
In one possible implementation manner, step S104 calculates, based on the predicted annual average period cost, an economic life of the electrical equipment to be predicted, which may be described in detail as:
step S1041, fitting the predicted annual average period cost of each operation year of the power equipment to be predicted to obtain an annual average period cost function of the power equipment to be predicted;
and step S1042, determining a cost minimum of the annual cycle cost function, and determining the operation life corresponding to the cost minimum as the economic life of the power equipment to be predicted.
In this embodiment, when the annual average period cost is the smallest, i.e. in the current optimal situation, continuing to operate increases the cost and risk of the power equipment to be predicted, so that the annual average period cost is increased, and therefore, the operation period corresponding to the case where the annual average period cost is the smallest is determined to be the economic life of the power equipment to be predicted.
In this embodiment, by fitting the predicted annual average period cost, an annual average period cost function with t as a variable of the power equipment to be predicted can be obtained, and a curve corresponding to the annual average period cost function can be specifically referred to a graph schematic diagram of the annual average period cost function of the power equipment shown in fig. 3, and it is obvious that when the annual average period cost is minimum, the corresponding operation period is the time point with the optimal economical efficiency of the power equipment, and the economic life of the power equipment can be determined.
Specifically, the annual cycle cost function can be derived, and the economic life of the power equipment can be rapidly determined by calculating the function value corresponding to the annual cycle cost function when the derivative is 0.
For example, a quadratic polynomial may be used to fit the predicted annual average period cost to obtain an annual average period cost function for the electrical device to be predicted. Since the annual average period cost function is a convex function, and the annual average period cost of the power equipment is 'down' and 'up' (including the two cases of 'down' to 'level' to 'up' trend and 'down' to 'up' trend), the annual average period cost function has a minimum value point; and then the economic life of the power equipment and the corresponding annual cycle cost can be obtained by solving the extreme points of the annual cycle cost function.
In addition, for the power equipment with the annual average period cost in a trend of 'falling' to 'rising', the least square method can be adopted to fit the annual average period cost to be predicted, so as to obtain the annual average period cost function of the power equipment to be predicted. Because the annual cycle cost of the power equipment is in a trend of 'falling' to 'rising', the annual cycle cost function also has a minimum point, so that the economic life of the power equipment and the corresponding annual cycle cost can be obtained by solving the extreme point of the annual cycle cost function.
In one possible implementation, before determining the cost minimum of the annual cycle cost function in step S1042, the method further includes:
calculating a fault distribution function of the power equipment to be predicted based on the historical operation data;
and optimizing the annual average period cost function based on the fault distribution function.
In this embodiment, the variable cost of the power device is mainly dependent on the operating state of the power device after the power device is put into operation, and the operating state of the power device is related to the operation maintenance and the number of times of fault maintenance of the power device, so that the variable cost of the power device is closely related to the fault distribution function of the power device, i.e. the annual cycle cost function can be optimized by using the fault distribution function.
Alternatively, the power device is an electromechanical device, and the fault distribution thereof satisfies the weibull distribution, so that the weibull distribution may be used to determine the fault distribution function of the power device to be predicted.
Specifically, the fault distribution function of the power equipment to be predicted is thatWherein F (t) is a fault distribution function of the power equipment to be predicted, which is obtained based on a double-parameter Weibull distribution function, t is the operation life of the power equipment, beta is a shape parameter, and eta is a scaling factor.
Wherein the fault distribution function may be determined by:
by fitting the variable cost over the total operational lifetime of the target type of power device, a variable cost function of the power device can be obtained.
The variable cost function and the fault distribution function of the power equipment meet C kb (t)＝C kbi F (t), where C kb Variable cost function representing a target type of power device, C kbi A variable cost coefficient representing a target type of electrical device, the variable cost coefficient being related to operational maintenance and troubleshooting costs required for the electrical device per unit time.
And carrying the acquired historical operation data of the power equipment of the target type into a Weibull distribution function, and obtaining parameters of Weibull distribution of the historical operation data through least square fitting, so that the fault distribution function of the power equipment to be predicted can be determined.
Optionally, the annual average period cost function is optimized based on the fault distribution function, which may be directly multiplying the fault distribution function by the annual average period cost function to obtain an optimized annual average period cost function.
In one possible implementation manner, the historical operation data of all the power devices of the target type are obtained, the relevant information of the power devices is derived through ERP data of a power grid company, and the derived cost includes: initial investment costs, inspection costs, switching costs, overhaul costs, special costs, retired disposal costs, etc., wherein the initial investment costs include purchase costs, installation costs, and commissioning costs of the power equipment.
Besides the initial investment cost and the retired disposal cost, each cost of the power equipment is related to the operation, the fault and the maintenance of the power equipment, so that the dimension reduction of the derived cost data can be realized by combining the related costs, the subsequent process of calculating the economic life of the power equipment is simplified, and the efficiency of calculating the economic life is improved.
Illustratively, the patrol cost and the switching cost are both related to the operation of the power device, and the operation cost of the power device may be obtained by combining the patrol cost and the switching cost; the overhaul cost and the overhaul cost are both related to the maintenance of the power equipment, and the maintenance cost of the power equipment can be obtained by combining the overhaul cost and the overhaul cost; the special cost is related to the failure of the power equipment, and the failure cost of the power equipment can be obtained by combining the special cost with other failure costs. In addition, if there are other cost fees, it can be classified into one of an operation cost, a fault cost, and a maintenance cost through analysis of the cost fees.
Correspondingly, the full life cycle cost data of each power equipment can be correspondingly calculated by linearly accumulating the initial investment cost, the running cost, the fault cost, the maintenance cost and the retired disposal cost of the power equipment.
In one possible implementation manner, after acquiring the historical operation data of all the power devices of the target type in step S101, the method further includes:
and performing outlier processing and missing value filling on the historical operation data.
Optionally, the missing value of the obtained historical operation data can be filled by a k-nearest neighbor algorithm.
Taking the historical operation data corresponding to each operation period in the historical operation data as a sample, and constructing a sample set to be filled;
selecting a k value in a k neighbor algorithm;
respectively calculating Euclidean distance between each sample and the blank value, and selecting k samples with the minimum Euclidean distance as similar samples;
and calculating the average value of all similar samples, and filling the average value as a vacancy value.
Wherein, the K value in the K-nearest neighbor algorithm can be selected to evaluate the most suitable K value by using K-fold cross-validation.
Specifically, splitting a sample set to be filled into a preset number of sets, and dividing each set into a training set and a verification set;
Attempting all designated K (KNN) values to train the K nearest neighbor algorithm on each segment;
adding the accuracy rate of each set evaluation, dividing by the preset number to obtain the final accuracy rate when the K nearest neighbor algorithm is a certain K value;
and comparing the final accuracy of all the K (KNN) values, and selecting the K (KNN) value with the highest final accuracy as the K value in the K nearest neighbor algorithm.
According to the embodiment of the invention, the total operation years of the target type power equipment are divided to obtain different change stages of the annual average period cost of the target type power equipment, the period cost model of each stage is built according to each stage, the relation between the cost of the power equipment and the service life of the power equipment is fully considered to obtain the change trend of each stage, each period cost model can be more in line with the change trend of the corresponding stage, and the pertinence of the period cost model is improved; specifically, the LSTM-BP neural network model optimized by the gray wolf algorithm is used for carrying out model establishment in a cost reduction stage and a cost rising stage, so that the model is more in line with the trend of data reduction and rising during prediction, and the accuracy of a prediction result is improved; the cost leveling stage is predicted by the differential integration moving average autoregressive model, so that a stable data sequence can be reasonably and accurately predicted, and the accuracy and rationality of a prediction result are improved; according to the period cost model of each stage, the predicted annual average period cost of each operation period of the power equipment to be predicted is predicted, so that the predicted annual average period cost is more reasonable, the actual situation of the power equipment to be predicted is more met, the accuracy of a prediction result is improved, the economic life of the power equipment to be predicted is accurately calculated, and the reliability of the calculated economic life is improved; the obtained historical operation data is subjected to dimension reduction, so that the number of items of cost data can be reduced, and the subsequent analysis and prediction processes are simplified; the annual average period cost function is optimized through the fault distribution function, so that the fault distribution condition and the randomness of faults of the type of power equipment can be fully considered, the calculated economic life is more in line with the actual condition, and the reliability of the economic life is further improved.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
The following are device embodiments of the invention, for details not described in detail therein, reference may be made to the corresponding method embodiments described above.
Fig. 4 is a schematic structural diagram of an economic life calculating device of an electrical device according to an embodiment of the present invention, and for convenience of explanation, only a portion related to the embodiment of the present invention is shown, which is described in detail below:
as shown in fig. 4, an economic life calculation device 40 of an electric power apparatus includes:
the obtaining module 41 is configured to obtain historical operation data of all power devices of a target type, and obtain an actual annual average period cost corresponding to each operation period of each power device based on the historical operation data, where the actual annual average period cost is a value obtained by dividing a current total operation cost of the power device by the current operation period;
a dividing module 42 for dividing the total operational life of each power device into a plurality of stages;
the prediction module 43 is configured to establish a period cost model of each stage based on the actual annual average period cost of each power device in each stage, and predict and obtain a predicted annual average period cost of each operation year of the power device to be predicted according to the period cost model of each stage;
A calculation module 44 for calculating an economic life of the electrical equipment to be predicted based on the predicted annual average period cost.
In one possible implementation, the partitioning module 42 is specifically configured to:
for each power equipment, establishing a feature vector corresponding to each operation period according to historical operation data of the power equipment to obtain a feature vector sample set of the power equipment;
and respectively carrying out K-means clustering on the feature vector sample set of each power device to obtain a clustering result of each power device, and dividing the power device according to the clustering result.
In one possible implementation, the plurality of phases includes a cost reduction phase, a cost leveling phase, and a cost rise phase;
the prediction module 43 is specifically configured to:
training a preset neural network model based on the actual annual average period cost of each power device in the cost reduction stage to obtain a period cost model in the cost reduction stage;
training a preset time sequence prediction model based on the actual annual average period cost of each power device in the cost leveling stage to obtain a period cost model of the cost leveling stage;
training a preset neural network model based on the actual annual average period cost of each power device in the cost rising stage to obtain a period cost model in the cost rising stage.
In one possible implementation, the prediction module 43 is specifically configured to:
determining a stage in which the current operation age of the power equipment to be predicted is located;
selecting a corresponding period cost model according to the stage of the current operation period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period;
and obtaining the predicted annual average period cost of each operation period of the power equipment to be predicted according to the actual annual average period cost of each operation period of the power equipment to be predicted before the current operation period and the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period.
In one possible implementation, the prediction module 43 is specifically configured to:
if the current operation period is a cost reduction period, selecting a period cost model of the cost reduction period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost reduction period; selecting a period cost model of a cost leveling stage, predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost leveling stage, selecting a period cost model of a cost rising stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost rising stage;
If the current operation period is a cost leveling period, selecting a period cost model of the cost leveling period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost leveling period; selecting a period cost model of a cost rising stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost rising stage;
if the current operation period is a cost rising period, selecting a period cost model of the cost rising period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost rising period.
In one possible implementation, the computing module 44 is specifically configured to:
fitting the predicted annual average period cost of each operation period of the power equipment to be predicted to obtain an annual average period cost function of the power equipment to be predicted;
and determining a cost minimum value of the annual average period cost function, and determining the operation life corresponding to the cost minimum value as the economic life of the power equipment to be predicted.
In one possible implementation, the economic life calculation device 40 of the electrical equipment further comprises an optimization module for:
Calculating a fault distribution function of the power equipment to be predicted based on the historical operation data;
and optimizing the annual average period cost function based on the fault distribution function.
In one possible implementation, the obtaining module 41 is further configured to:
and performing outlier processing and missing value filling on the historical operation data.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the steps of each method embodiment described above may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (10)
1. A method of calculating an economic life of an electrical device, comprising:
acquiring historical operation data of all power equipment of a target type, and acquiring actual annual average period cost corresponding to each operation period of each power equipment based on the historical operation data, wherein the actual annual average period cost is a value obtained by dividing the current total operation cost of the power equipment by the current operation period;
dividing the total operational life of each power device into a plurality of phases;
based on the actual annual average period cost of each power equipment in each stage, establishing a period cost model of each stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted according to the period cost model of each stage;
And calculating the economic life of the power equipment to be predicted based on the predicted annual average period cost.
2. The method for calculating the economic life of an electrical device according to claim 1, wherein the dividing the total operation period of each electrical device into a plurality of stages comprises:
for each power equipment, establishing a feature vector corresponding to each operation period according to historical operation data of the power equipment to obtain a feature vector sample set of the power equipment;
and respectively carrying out K-means clustering on the feature vector sample set of each power device to obtain a clustering result of each power device, and dividing the power device according to the clustering result.
3. The method for calculating the economic life of an electrical device according to claim 2, wherein the plurality of stages includes a cost down stage, a cost leveling stage, and a cost up stage;
the method for establishing the period cost model of each stage based on the actual annual average period cost of each power equipment in each stage comprises the following steps:
training a preset neural network model based on the actual annual average period cost of each power device in the cost reduction stage to obtain a period cost model of the cost reduction stage;
Training a preset time sequence prediction model based on the actual annual average period cost of each power device in a cost leveling stage to obtain a period cost model of the cost leveling stage;
training a preset neural network model based on the actual annual average period cost of each power device in the cost rising stage to obtain a period cost model of the cost rising stage.
4. A method for calculating the economic life of an electrical device according to claim 3, wherein predicting the predicted annual average period cost for each operating year of the electrical device to be predicted based on the period cost model of each stage comprises:
determining a stage in which the current operation age of the power equipment to be predicted is located;
selecting a corresponding period cost model according to the stage of the current operation period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period;
and obtaining the predicted average period cost of each operation period of the power equipment to be predicted according to the actual average period cost of each operation period of the power equipment to be predicted before the current operation period and the predicted average period cost of each operation period of the power equipment to be predicted after the current operation period.
5. The method for calculating the economic life of an electrical device according to claim 4, wherein selecting the corresponding period cost model according to the stage in which the current operation period is located, predicting the predicted annual average period cost of each operation period of the electrical device to be predicted after the current operation period, comprises:
if the current operation period is a cost reduction period, selecting a period cost model of the cost reduction period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost reduction period; selecting a period cost model of a cost leveling stage, predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost leveling stage, selecting a period cost model of a cost rising stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost rising stage;
if the current operation period is a cost leveling period, selecting a period cost model of the cost leveling period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost leveling period; selecting a period cost model of a cost rising stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted in the cost rising stage;
And if the current operation period is a cost rising period, selecting a period cost model of the cost rising period, and predicting the predicted annual average period cost of each operation period of the power equipment to be predicted after the current operation period in the cost rising period.
6. The method for calculating the economic life of an electrical device according to any one of claims 1 to 5, wherein calculating the economic life of the electrical device to be predicted based on the predicted annual average period cost comprises:
fitting the predicted annual average period cost of each operation period of the power equipment to be predicted to obtain an annual average period cost function of the power equipment to be predicted;
and determining a cost minimum value of the annual cycle cost function, and determining an operation life corresponding to the cost minimum value as the economic life of the power equipment to be predicted.
7. The method of claim 6, further comprising, prior to determining the cost minimum of the annual cycle cost function:
calculating a fault distribution function of the power equipment to be predicted based on the historical operation data;
And optimizing the annual average period cost function based on the fault distribution function.
8. The method for calculating the economic life of an electrical device according to claim 1, further comprising, after the acquiring of the historical operation data of all electrical devices of the target type:
and carrying out outlier processing and missing value filling on the historical operation data.
9. An economic life calculation device of an electric power apparatus, comprising:
the system comprises an acquisition module, a calculation module and a calculation module, wherein the acquisition module is used for acquiring historical operation data of all power equipment of a target type, and acquiring actual annual average period cost corresponding to each operation period of each power equipment based on the historical operation data, wherein the actual annual average period cost is a value obtained by dividing the current total operation cost of the power equipment by the current operation period;
the dividing module is used for dividing the total operation period of each power device into a plurality of stages;
the prediction module is used for establishing a period cost model of each stage based on the actual annual average period cost of each power equipment in each stage, and predicting the predicted annual average period cost of each operation year of the power equipment to be predicted according to the period cost model of each stage;
And the calculating module is used for calculating the economic life of the power equipment to be predicted based on the predicted annual average period cost.
10. The apparatus according to claim 9, wherein the dividing module is specifically configured to:
for each power equipment, establishing a feature vector corresponding to each operation period according to historical operation data of the power equipment to obtain a feature vector sample set of the power equipment;
and respectively carrying out K-means clustering on the feature vector sample set of each power device to obtain a clustering result of each power device, and dividing the power device according to the clustering result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311426403.8A CN117422258A (en) | 2023-10-30 | 2023-10-30 | Economical life calculation method and device for power equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311426403.8A CN117422258A (en) | 2023-10-30 | 2023-10-30 | Economical life calculation method and device for power equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117422258A true CN117422258A (en) | 2024-01-19 |
Family
ID=89524462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311426403.8A Pending CN117422258A (en) | 2023-10-30 | 2023-10-30 | Economical life calculation method and device for power equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117422258A (en) |
-
2023
- 2023-10-30 CN CN202311426403.8A patent/CN117422258A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zaidan et al. | Gas turbine engine prognostics using Bayesian hierarchical models: A variational approach | |
| Singh et al. | An efficient time series forecasting model based on fuzzy time series | |
| Louen et al. | A new framework for remaining useful life estimation using support vector machine classifier | |
| CN110163429B (en) | Short-term load prediction method based on similarity day optimization screening | |
| CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
| Mathew et al. | Regression kernel for prognostics with support vector machines | |
| CN114548509A (en) | Multi-type load joint prediction method and system for multi-energy system | |
| JP7481902B2 (en) | Management computer, management program, and management method | |
| CN115034485A (en) | Wind power interval prediction method and device based on data space | |
| CN117543544A (en) | Load prediction method, device, equipment and storage medium | |
| CN115422687A (en) | Service life prediction method of rolling bearing | |
| CN110837857A (en) | Industrial electricity load prediction method, system and storage medium thereof | |
| Manoj et al. | FWS-DL: forecasting wind speed based on deep learning algorithms | |
| CN113537614A (en) | Construction method, system, equipment and medium of power grid engineering cost prediction model | |
| Liu et al. | Residual useful life prognosis of equipment based on modified hidden semi-Markov model with a co-evolutional optimization method | |
| CN114648178B (en) | Operation and maintenance strategy optimization method of electric energy metering device based on DDPG algorithm | |
| CN116777281A (en) | ARIMA model-based power equipment quality trend prediction method and device | |
| He et al. | Prediction of electricity demand of China based on the analysis of decoupling and driving force | |
| CN117422258A (en) | Economical life calculation method and device for power equipment | |
| Lin et al. | Hpt-rl: Calibrating power system models based on hierarchical parameter tuning and reinforcement learning | |
| US11629856B2 (en) | Apparatus for managing combustion optimization and method therefor | |
| CN113887816A (en) | Intelligent prediction method, device and equipment for social reserve of household appliances | |
| CN111931994A (en) | Short-term load and photovoltaic power prediction method, system, equipment and medium thereof | |
| JP7154468B2 (en) | Information processing device, information processing method and information processing program | |
| CN116539994A (en) | Substation main equipment operation state detection method based on multi-source time sequence data |
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 |