CN116341796A - Energy consumption monitoring and evaluating system and method - Google Patents
Energy consumption monitoring and evaluating system and method Download PDFInfo
- Publication number
- CN116341796A CN116341796A CN202310608932.3A CN202310608932A CN116341796A CN 116341796 A CN116341796 A CN 116341796A CN 202310608932 A CN202310608932 A CN 202310608932A CN 116341796 A CN116341796 A CN 116341796A
- Authority
- CN
- China
- Prior art keywords
- data
- energy consumption
- output
- energy
- monitoring
- 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
- 238000005265 energy consumption Methods 0.000 title claims abstract description 98
- 238000012544 monitoring process Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012549 training Methods 0.000 claims abstract description 42
- 239000013598 vector Substances 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 238000003062 neural network model Methods 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims description 21
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 125000004122 cyclic group Chemical group 0.000 claims description 4
- 238000007418 data mining Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 2
- 238000012417 linear regression Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 description 7
- 238000009776 industrial production Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 241000135164 Timea Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011157 data evaluation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002912 waste gas Substances 0.000 description 1
- 239000002351 wastewater Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Abstract
The invention discloses an energy consumption monitoring and evaluating system and method, which are applied to the technical field of energy monitoring, and the method comprises the following steps: acquiring data sources in different time periods by using terminal acquisition equipment; constructing a data set, and converting data sources corresponding to different time periods into numerical data; carrying out standardization processing on the numerical data, forming a vector sequence according to time sequence, and carrying out mean value interpolation processing on missing values in the numerical data; importing the data set into a neural network model for sample training, performing hidden layer output calculation and output of a predicted value, and calculating an error value according to the predicted value to obtain a final predicted result; monitoring the energy consumption of a data source according to a prediction result, analyzing related parameters affecting the data source, and establishing an input-output model; taking time as a transverse axis, and accurately evaluating a data source; and the energy consumption data is reasonably monitored and evaluated, so that manual data acquisition is avoided.
Description
Technical Field
The invention relates to the technical field of energy monitoring, in particular to an energy consumption monitoring and evaluating system and method.
Background
Along with the acceleration of industrialization and urbanization in China, the energy demand is also huge and increases year by year. The manufacturing industry in China rapidly develops, becomes a main strength for pulling economy, and consumes a large amount of energy while creating huge wealth. When current mill, workshop are produced, need monitor various production and operational equipment, need monitor waste gas, the waste water that produces after producing when necessary to monitor equipment, avoid appearing the production accident, but traditional monitoring means has following problem:
the workflow is complicated, the staff needs to install the corresponding type of monitoring instrument in advance at the equipment or the area needing to be monitored, the patrol staff is regularly arranged to check the monitoring condition of the monitoring instrument and record the monitoring data, then the monitoring evaluation data is obtained through system analysis, and finally the staff manually arranges the subsequent maintenance work.
The patent application number CN202210528464.4 references to disclose a data type imbalance treatment method in large industrial user energy consumption anomaly monitoring, which comprises the following specific contents: acquiring load data in a power system and time period data corresponding to the load data, and constructing a standard data set; constructing a plurality of base classifiers, and obtaining a classifier set through a balance bagging method according to a standard data set; according to the classifier set, calculating a random sensitivity evaluation index of each sample in the standard data set, and removing the sample in the standard data set when the random sensitivity evaluation index of the sample in the standard data set is greater than a preset threshold lambda to obtain a filtered standard data set; and (3) according to the filtered standard data set, realizing power data analysis of a downstream task of the power system.
In the prior art, the classification and management of the energy consumption are carried out by constructing a data set, the problem of errors exists in the data processing process, the acquired data is not monitored in real time, the data evaluation is inaccurate, and therefore, the energy consumption monitoring and evaluating system and method are provided.
Disclosure of Invention
Accordingly, embodiments of the present invention seek to provide systems and methods for monitoring and evaluating energy consumption that solve or mitigate the technical problems associated with the prior art, and at least provide a useful choice;
the invention provides an energy consumption monitoring and evaluating method, which comprises the following steps:
s1: acquiring data sources in different time periods by using terminal acquisition equipment, wherein the data sources comprise real-time energy consumption states, unit energy consumption data, energy consumption change trends and real-time operation parameters;
s2: constructing a data set, and converting data sources corresponding to different time periods into numerical data; carrying out standardization processing on the numerical data, forming a vector sequence according to time sequence, and carrying out mean value interpolation processing on missing values in the numerical data;
s3: leading the data set into a neural network model for sample training, carrying out hidden layer output calculation and output of a predicted value, calculating an error value according to the predicted value, stopping sample training if the error value is within a threshold range, adopting output data of current training, carrying out weight updating if the error value is not within the threshold range, and adding the output data to obtain an average value after training is completed, so as to obtain a final predicted result;
s4: monitoring the energy consumption of a data source according to a prediction result, analyzing related parameters affecting the data source, and establishing an input-output model;
s5: and taking time as a transverse axis, accurately evaluating the data source, scheduling and controlling the energy-saving equipment according to the energy-saving plan designated by the user, and generating a corresponding plan list through the energy-saving plan.
Further, based on the vector x of the dataset input, the hidden layer output H is calculated:
wherein the method comprises the steps ofFor hidden layer activation function, ++>For connecting weights between the input layer and the hidden layer, < ->J is the hidden layer threshold value and j is the number of input layer nodes;
calculating a predicted value Y according to the hidden layer output H:
wherein the method comprises the steps ofFor the connection weight, b is a threshold value, k is the number of hidden layer nodes, j is the number of input layer nodes, < ->The number of cells as input;
and calculating an error value e according to the predicted value Y and the expected output C:
further, the weight updating is to update the connection weight according to the error value, specifically:
wherein the method comprises the steps ofFor learning efficiency, < >>And->For updated connection weights, +.>For connecting weights between the input layer and the hidden layer, < ->E is an error value, and H is hidden layer output;
wherein the method comprises the steps ofFor the updated threshold value, H is hidden layer output, e is error value, m is output layer node number, k is hidden layer node number, +.>Is a constant value.
Further, in S2, the method includes: analyzing and judging through the numerical data to obtain the energy consumption factor of the monitoring target; comparing the energy consumption factor with a preset threshold value to obtain a judging result; and transmitting the judgment result to the mobile terminal, and performing cyclic alarm through the ringtone when the energy consumption factor exceeds a preset threshold.
Further, the step of monitoring the energy consumption of the data source according to the prediction result, analyzing the relevant parameters affecting the data source, and establishing the input/output model includes:
parsing a vector of relevant parameters affecting the data source YCalculating the t-th period corresponding to the relevant parameter vector +.>Obtaining a final input/output model: />Wherein->Is the influencing data source of the t-th period.
Further, after the model is input and output, carrying out correlation analysis on the abnormal data source based on the key performance index and the external data index; and performing linear fitting on the abnormal data sources through a linear regression model to obtain corrected abnormal data sources, and performing energy consumption assessment according to time sequence arrangement.
Further, the step of accurately evaluating the data source by using time as a transverse axis, and scheduling and controlling the energy-saving device according to the energy-saving plan specified by the user, and generating a corresponding plan list through the energy-saving plan includes:
the energy-saving equipment is scheduled and controlled through dynamic energy consumption curves and data, different combinations are formed according to time, energy consumption and user demand information, and various analysis charts and reports are generated for the user to conduct data mining, so that different energy-saving plans are formulated or the existing energy-saving plans are corrected.
Also provided is an energy consumption monitoring and assessment system comprising:
and the acquisition module is used for: acquiring data sources in different time periods by using terminal acquisition equipment, wherein the data sources comprise real-time energy consumption states, unit energy consumption data, energy consumption change trends and real-time operation parameters;
and (3) constructing a data set module: constructing a data set, and converting data sources corresponding to different time periods into numerical data; carrying out standardization processing on the numerical data, forming a vector sequence according to time sequence, and carrying out mean value interpolation processing on missing values in the numerical data;
training module: leading the data set into a neural network model for sample training, carrying out hidden layer output calculation and output of a predicted value, calculating an error value according to the predicted value, stopping sample training if the error value is within a threshold range, adopting output data of current training, carrying out weight updating if the error value is not within the threshold range, and adding the output data to obtain an average value after training is completed, so as to obtain a final predicted result;
and a monitoring module: monitoring the energy consumption of a data source according to a prediction result, analyzing related parameters affecting the data source, and establishing an input-output model;
and an evaluation module: and taking time as a transverse axis, accurately evaluating the data source, scheduling and controlling the energy-saving equipment according to the energy-saving plan designated by the user, and generating a corresponding plan list through the energy-saving plan.
Compared with the prior art, the invention has the beneficial effects that:
(1) The invention realizes the automatic acquisition of the energy consumption of industry users, obtains real-time, accurate and effective data, completes the statistical analysis, evaluation, scheduling and guiding the input application of energy-saving equipment and saves the energy to the maximum extent;
(2) The energy consumption monitoring and evaluating system comprises an acquisition module, a data training module, a monitoring module and an evaluating module, wherein the energy consumption monitoring and evaluating system is used for converting and analyzing energy consumption data through automatic acquisition data sources in different time periods, performing sample training, adding output data to obtain an average value after the training is finished, and obtaining a final prediction result; the method comprises the steps of monitoring energy consumption of a data source according to a prediction result, analyzing relevant parameters affecting the data source, and establishing an input/output model, wherein the method has the advantages of accurate sampling, high efficiency, reasonable monitoring and evaluation of energy consumption data, and manual data acquisition is avoided; the method has evaluation value and reduces the waste of energy.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an energy consumption monitoring and evaluating method according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of an energy consumption monitoring and evaluating system according to an embodiment of the present application.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
Referring to fig. 1, a flow chart of a method and a system for analyzing and controlling a drum water level measurement error are provided;
the energy consumption monitoring and evaluating method provided by the application comprises the following steps:
s1: acquiring data sources in different time periods by using terminal acquisition equipment, wherein the data sources comprise real-time energy consumption states, unit energy consumption data, energy consumption change trends and real-time operation parameters;
in the step, acquiring a data source at intervals of preset time length, and determining the acquired data source as data of a current time interval, wherein the data source comprises a real-time energy consumption state, unit energy consumption data, an energy consumption change trend and real-time operation parameters; determining a plurality of time sub-intervals according to the states of the industrial production equipment in a plurality of continuous time intervals; acquiring energy consumption monitoring data of industrial production equipment in each time subinterval, and determining average energy consumption of the industrial production equipment in each time subinterval; presetting a time interval of energy consumption analysis of the industrial production equipment, and generating an energy consumption statistical analysis report of the industrial production equipment, wherein the energy consumption statistical analysis report comprises the following components: run-time statistical analysis and energy consumption analysis.
S2: constructing a data set, and converting data sources corresponding to different time periods into numerical data; carrying out standardization processing on the numerical data, forming a vector sequence according to time sequence, and carrying out mean value interpolation processing on missing values in the numerical data; analyzing and judging through the numerical data to obtain the energy consumption factor of the monitoring target; comparing the energy consumption factor with a preset threshold value to obtain a judging result; and transmitting the judgment result to the mobile terminal, and performing cyclic alarm through the ringtone when the energy consumption factor exceeds a preset threshold.
In the step, the acquired data sources are transmitted to a database for storage, and the data sources corresponding to different time periods are converted into numerical data for standardization processing; measuring index parameters of a monitoring target in a preset period to obtain a plurality of measurement results; calculating and obtaining standard deviation of energy consumption according to a plurality of measurement results; analyzing and judging theoretical energy consumption and actual energy consumption through a processing system, and calculating and obtaining an energy consumption factor of a monitoring target; analyzing and judging the upper limit value, the lower limit value and the standard deviation through a processing system, and comparing the energy consumption factor with a preset threshold value to obtain a judging result; and transmitting the judgment result to the mobile terminal, and performing cyclic alarm through the ringtone when the energy consumption factor exceeds a preset threshold.
S3: leading the data set into a neural network model for sample training, carrying out hidden layer output calculation and output of a predicted value, calculating an error value according to the predicted value, stopping sample training if the error value is within a threshold range, adopting output data of current training, carrying out weight updating if the error value is not within the threshold range, and adding the output data to obtain an average value after training is completed, so as to obtain a final predicted result; calculating hidden layer output H according to vector x input by the data set:
wherein the method comprises the steps ofFor hidden layer activation function, ++>For connecting weights between the input layer and the hidden layer, < ->J is the hidden layer threshold value and j is the number of input layer nodes;
calculating a predicted value Y according to the hidden layer output H:
wherein the method comprises the steps ofFor the connection weight, b is a threshold value, k is the number of hidden layer nodes, j is the number of input layer nodes, < ->The number of cells as input;
and calculating an error value e according to the predicted value Y and the expected output C:
in this step, the data set is classified, i.e. training samples are defined as:
wherein->The value is 1 or-1, i.e. sample +.>Category of->Is +.>Vector of dimensions, will->The hyperplanes are separated by a maximum separation, the hyperplanes being represented as follows:let the normal vector of the plane be->,/>And->For internal accumulation, add>For the intercept of the hyperplane normal vector direction, two linear planes are defined as hyperplanes: />And->These two planes can correctly separate the data,/->Is the spacing of two planes; before the data source prediction, the prediction mode is selected, the prediction of the data source is a prediction based on a time sequence, the time sequence prediction is divided into short-range prediction and long-range prediction, the short-range prediction is to utilize the existing sample data to predict a certain time point, then the actual value is used for replacing the point, so that new sample data is formed, and then the prediction of the next time point is performed. This method can only predict at a timeA value of a day in the future; the long-range prediction is to directly add the predicted value of a certain time point into a test sample so as to predict the value of the next time point, and the long-range prediction is not limited to one-day prediction, but can obtain the numerical change of a plurality of days; in the prediction of this matter, long-range prediction is adopted because comprehensive data is involved.
In the training of a neural network model, in a traditional algorithm, the gradient descending direction is adjusted based on the gradient direction at the time t, the gradient direction before the time t is not considered, network oscillation is often caused by one volunteer, the convergence speed in training is very slow, the effect of errors on the gradient is considered, the shape change trend on an error curved surface is analyzed, and the tiny change on the neural network curved surface is allowed, so that the traditional algorithm is helped to jump out of local minimum points; the algorithm is to add a value proportional to the previous change amount to each change amount of the weight, and generate new weight according to the back propagation methodAs a momentum factor, the mathematical expression of the weight change becomes:
wherein the method comprises the steps ofFor the input layer and hidden layer connection weights, when i=1, j=2,/is +.>Denoted as->G is training frequency, < >>For learning rate +.>Outputting gradient vectors of the error pair weight values or threshold values for the neural network of the g-th iteration; when->The weight change is then produced by the gradient descent method when +.>When the new weight change is used as the last weight change, the change value generated by the gradient method is not counted any more, and the weight continuously tends to the average direction of the bottom of the error curved surface after multiple times of calculation, when->When entering the flat area at the bottom of the curved surface, +.>The variation of (2) will be very small, so +.>Will not be equal to 0, then->The prediction is therefore more accurate; when the new weight causes the error to grow excessively, the new weight should be abandoned and momentum use should be stopped, when the new error change rate exceeds a preset maximum value for the old change rate, the calculated weight change is canceled, the maximum error change rate can be any value greater than or equal to 1, the common value is 1.04, and a judgment condition is added in the training process to correctly use the weight correction formula, wherein the judgment condition is that:
s4: and monitoring the energy consumption of the data source according to the prediction result, analyzing relevant parameters affecting the data source, and establishing an input and output model. Parsing a vector of relevant parameters affecting the data source YCalculating the t-th period corresponding to the relevant parameter vector +.>Obtaining a final input/output model: />Wherein->Is the influencing data source of the t-th period.
In one embodiment, the number of network input layer nodes n=12, the number of output layer nodes m=12, and the number of hidden layer nodes k=6 are obtained according to the input/output sequence, and are weight matrices among the neurons of the input layer, the hidden layer and the output layerAssigning a value, initializing a hidden layer threshold value a, outputting a layer threshold value b, and setting a learning rate +.>Determining that the neuron activation function is a logarithmic S-type activation function, and importing a data source into an input layer, wherein the data source is subjected to grouping random input; according to the input vector X, the connection weight between the input layer and the hidden layer is +.>Hidden layer threshold +.>Calculating hidden layer output H; outputting H and connecting weight value according to the hidden layer>Outputting a layer threshold b, and calculating a predicted value Y; according to the predicted value Y and the expected output C, calculating a network predicted error e, stopping training if the error value is within an allowable range, and updating the weight and updating the threshold value if the error value is not within the range by utilizing the predicted value at the moment; and after training is completed, adding the predicted values obtained each time, and finally taking an average value.
At this stepIn step (a), the observed value of the data source is set according to the input/output modelCalculating the observed value +.>Error of the predicted value Y>Wherein the formula is: />Wherein->For error->Total error,/->For the sample matrix at the time of prediction, +.>To influence the parameter vector matrix of the data source, +.>For training the matrix of samples, +.>The estimation is performed using the formula: />Where u is the dimension of the parameter vector affecting the data source; judging the observed value +.>Whether it falls within the prediction interval, if so, observe +.>If the fault falls into the prediction interval, the fault needs to be removed in time.
S5: and taking time as a transverse axis, accurately evaluating the data source, scheduling and controlling the energy-saving equipment according to the energy-saving plan designated by the user, and generating a corresponding plan list through the energy-saving plan. The energy-saving equipment is scheduled and controlled through dynamic energy consumption curves and data, different combinations are formed according to time, energy consumption and user demand information, and various analysis charts and reports are generated for the user to conduct data mining, so that different energy-saving plans are formulated or the existing energy-saving plans are corrected.
In the step, the user authority management authority adopts a multi-level regional authority system solution, a multi-level authority region can be established according to regions, user levels, energy consumption items and the like, authorities are allocated for different users or user groups, and the login system autonomously inquires about energy consumption related information.
Referring to fig. 2, the present invention also provides an energy consumption monitoring and assessment system, comprising:
and the acquisition module is used for: acquiring data sources in different time periods by using terminal acquisition equipment, wherein the data sources comprise real-time energy consumption states, unit energy consumption data, energy consumption change trends and real-time operation parameters;
and (3) constructing a data set module: constructing a data set, and converting data sources corresponding to different time periods into numerical data; carrying out standardization processing on the numerical data, forming a vector sequence according to time sequence, and carrying out mean value interpolation processing on missing values in the numerical data;
training module: leading the data set into a neural network model for sample training, carrying out hidden layer output calculation and output of a predicted value, calculating an error value according to the predicted value, stopping sample training if the error value is within a threshold range, adopting output data of current training, carrying out weight updating if the error value is not within the threshold range, and adding the output data to obtain an average value after training is completed, so as to obtain a final predicted result;
and a monitoring module: monitoring the energy consumption of a data source according to a prediction result, analyzing related parameters affecting the data source, and establishing an input-output model;
and an evaluation module: and taking time as a transverse axis, accurately evaluating the data source, scheduling and controlling the energy-saving equipment according to the energy-saving plan designated by the user, and generating a corresponding plan list through the energy-saving plan.
In one embodiment, the monitoring module includes a communication unit, which respectively adopts a wired data collector and a wireless data collector according to different network environments, collects ammeter data, converts the ammeter data into an uploaded protocol, and uploads the uploaded protocol to the software platform. The wired data collector can convert RTU devices (such as RS232, RS485 and RS 422) with different communication modes into Ethernet communication and connect the Ethernet communication with the same network; the wireless data collector comprises a GPRS-DTU and a CDMA-DTU, can complete transparent conversion between RS232/485 and TCP/UDP/IP protocols on the premise of being based on a GPRS or CDMA network, and can carry out remote wireless data transmission so as to realize interconnection and intercommunication among all modules; the acquisition module comprises an open-type current transformer which is used for acquiring electric power data, can be installed under the condition of no power failure, realizes acquisition of current and voltage, generates new data for terminal acquisition equipment of the acquisition module at any time, can reflect the energy consumption data of single or multiple equipment at a certain period of time to a certain extent, can also be used for inquiring and displaying requirements at a mobile terminal, can firstly inquire the working state data of related equipment at a certain moment so as to be convenient for tracking the working state and monitoring data of the equipment, and is required to calculate and process by constructing a data set module and a training module because the energy consumption data is complex after all, so that the problem of error in energy consumption data analysis is solved; the evaluation module adopts an operation scheduling mechanism to control the start/stop of energy-saving facilities in the energy consumption system, and monitors the energy consumption saving amount brought by various energy-saving facilities under different environments.
In summary, the method and the device perform conversion and analysis of energy consumption data through automatic data acquisition sources in different time periods, perform sample training, and add output data to average after training is completed to obtain a final prediction result; the method comprises the steps of monitoring energy consumption of a data source according to a prediction result, analyzing relevant parameters affecting the data source, and establishing an input/output model, wherein the method has the advantages of accurate sampling, high efficiency, reasonable monitoring and evaluation of energy consumption data, and manual data acquisition is avoided; the method has evaluation value and reduces the waste of energy.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.
Although embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the application, the scope of which is defined in the appended claims and their equivalents.
Of course, the present invention can be implemented in various other embodiments, and based on this embodiment, those skilled in the art can obtain other embodiments without any inventive effort, which fall within the scope of the present invention.
Claims (8)
1. The energy consumption monitoring and evaluating method is characterized by comprising the following steps:
s1: acquiring data sources in different time periods by using terminal acquisition equipment, wherein the data sources comprise real-time energy consumption states, unit energy consumption data, energy consumption change trends and real-time operation parameters;
s2: constructing a data set, and converting data sources corresponding to different time periods into numerical data; carrying out standardization processing on the numerical data, forming a vector sequence according to time sequence, and carrying out mean value interpolation processing on missing values in the numerical data;
s3: leading the data set into a neural network model for sample training, carrying out hidden layer output calculation and output of a predicted value, calculating an error value according to the predicted value, stopping sample training if the error value is within a threshold range, adopting output data of current training, carrying out weight updating if the error value is not within the threshold range, and adding the output data to obtain an average value after training is completed, so as to obtain a final predicted result;
s4: monitoring the energy consumption of a data source according to a prediction result, analyzing related parameters affecting the data source, and establishing an input-output model;
s5: and taking time as a transverse axis, accurately evaluating the data source, scheduling and controlling the energy-saving equipment according to the energy-saving plan designated by the user, and generating a corresponding plan list through the energy-saving plan.
2. The energy consumption monitoring and assessment method according to claim 1, wherein in S3, it includes: calculating hidden layer output H according to vector x input by the data set:
wherein the method comprises the steps ofFor hidden layer activation function, ++>For connecting weights between the input layer and the hidden layer, < ->J is the hidden layer threshold value and j is the number of input layer nodes;
calculating a predicted value Y according to the hidden layer output H:
wherein the method comprises the steps ofFor the connection weight, b is a threshold value, k is the number of hidden layer nodes, j is the number of input layer nodes, < ->The number of cells as input;
and calculating an error value e according to the predicted value Y and the expected output C:
3. the energy consumption monitoring and evaluating method according to claim 1, wherein the weight updating is to update the connection weight according to the error value, specifically:
wherein the method comprises the steps ofFor learning efficiency, < >>And->For updated connection weights, +.>For connecting weights between the input layer and the hidden layer, < ->E is an error value, and H is hidden layer output;
4. The energy consumption monitoring and assessment method according to claim 1, wherein in S2, it includes: analyzing and judging through the numerical data to obtain the energy consumption factor of the monitoring target; comparing the energy consumption factor with a preset threshold value to obtain a judging result; and transmitting the judgment result to the mobile terminal, and performing cyclic alarm through the ringtone when the energy consumption factor exceeds a preset threshold.
5. The method for monitoring and evaluating energy consumption according to claim 1, wherein the step of monitoring energy consumption of a data source according to a prediction result, analyzing relevant parameters affecting the data source, and establishing an input/output model comprises:
6. The energy consumption monitoring and assessment method according to claim 1, wherein after the input and output of the model, correlation analysis is performed on the abnormal data source based on the key performance index and the external data index; and performing linear fitting on the abnormal data sources through a linear regression model to obtain corrected abnormal data sources, and performing energy consumption assessment according to time sequence arrangement.
7. The energy consumption monitoring and evaluating method according to claim 1, wherein the step of accurately evaluating the data source with time as a transverse axis, scheduling and controlling the energy saving device according to the energy saving plan specified by the user, and generating the corresponding plan list through the energy saving plan includes:
the energy-saving equipment is scheduled and controlled through dynamic energy consumption curves and data, different combinations are formed according to time, energy consumption and user demand information, and various analysis charts and reports are generated for the user to conduct data mining, so that different energy-saving plans are formulated or the existing energy-saving plans are corrected.
8. An energy consumption monitoring and assessment system, comprising:
and the acquisition module is used for: acquiring data sources in different time periods by using terminal acquisition equipment, wherein the data sources comprise real-time energy consumption states, unit energy consumption data, energy consumption change trends and real-time operation parameters;
and (3) constructing a data set module: constructing a data set, and converting data sources corresponding to different time periods into numerical data; carrying out standardization processing on the numerical data, forming a vector sequence according to time sequence, and carrying out mean value interpolation processing on missing values in the numerical data;
training module: leading the data set into a neural network model for sample training, carrying out hidden layer output calculation and output of a predicted value, calculating an error value according to the predicted value, stopping sample training if the error value is within a threshold range, adopting output data of current training, carrying out weight updating if the error value is not within the threshold range, and adding the output data to obtain an average value after training is completed, so as to obtain a final predicted result;
and a monitoring module: monitoring the energy consumption of a data source according to a prediction result, analyzing related parameters affecting the data source, and establishing an input-output model;
and an evaluation module: and taking time as a transverse axis, accurately evaluating the data source, scheduling and controlling the energy-saving equipment according to the energy-saving plan designated by the user, and generating a corresponding plan list through the energy-saving plan.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310608932.3A CN116341796A (en) | 2023-05-29 | 2023-05-29 | Energy consumption monitoring and evaluating system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310608932.3A CN116341796A (en) | 2023-05-29 | 2023-05-29 | Energy consumption monitoring and evaluating system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116341796A true CN116341796A (en) | 2023-06-27 |
Family
ID=86893309
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310608932.3A Pending CN116341796A (en) | 2023-05-29 | 2023-05-29 | Energy consumption monitoring and evaluating system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116341796A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116840765A (en) * | 2023-08-31 | 2023-10-03 | 武汉格蓝若智能技术股份有限公司 | Voltage transformer error state evaluation method based on multivariate time sequence analysis |
CN116893297A (en) * | 2023-09-11 | 2023-10-17 | 常州旭泰克系统科技有限公司 | Method and system for monitoring energy consumption of rotating equipment |
CN116993232A (en) * | 2023-09-27 | 2023-11-03 | 青岛艾德森物联科技有限公司 | Energy consumption management optimization method and system for comprehensive energy station |
CN117318312A (en) * | 2023-11-28 | 2023-12-29 | 南方电网调峰调频发电有限公司工程建设管理分公司 | Method and device for displaying power consumption data |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103077267A (en) * | 2012-12-28 | 2013-05-01 | 电子科技大学 | Parameter sound source modeling method based on improved BP (Back Propagation) neural network |
CN105678407A (en) * | 2015-12-31 | 2016-06-15 | 国网上海市电力公司 | Daily electricity consumption prediction method based on artificial neural network |
CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
WO2022028257A1 (en) * | 2020-08-07 | 2022-02-10 | 厦门雅迅网络股份有限公司 | Method for predicting energy consumption-recovery ratio of new energy vehicle, and energy saving control method and system |
CN114266454A (en) * | 2021-12-03 | 2022-04-01 | 山东中烟工业有限责任公司 | Cigarette factory energy consumption abnormity monitoring and judging method and system thereof |
CN114298387A (en) * | 2021-12-19 | 2022-04-08 | 南京理工大学 | Hadoop-based energy consumption prediction method for parallelization BP neural network |
-
2023
- 2023-05-29 CN CN202310608932.3A patent/CN116341796A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103077267A (en) * | 2012-12-28 | 2013-05-01 | 电子科技大学 | Parameter sound source modeling method based on improved BP (Back Propagation) neural network |
CN105678407A (en) * | 2015-12-31 | 2016-06-15 | 国网上海市电力公司 | Daily electricity consumption prediction method based on artificial neural network |
CN106874581A (en) * | 2016-12-30 | 2017-06-20 | 浙江大学 | A kind of energy consumption of air conditioning system in buildings Forecasting Methodology based on BP neural network model |
WO2022028257A1 (en) * | 2020-08-07 | 2022-02-10 | 厦门雅迅网络股份有限公司 | Method for predicting energy consumption-recovery ratio of new energy vehicle, and energy saving control method and system |
CN114266454A (en) * | 2021-12-03 | 2022-04-01 | 山东中烟工业有限责任公司 | Cigarette factory energy consumption abnormity monitoring and judging method and system thereof |
CN114298387A (en) * | 2021-12-19 | 2022-04-08 | 南京理工大学 | Hadoop-based energy consumption prediction method for parallelization BP neural network |
Non-Patent Citations (1)
Title |
---|
康琦等: "《SAS数据统计分析与编程实践》", 同济大学出版社, pages: 217 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116840765A (en) * | 2023-08-31 | 2023-10-03 | 武汉格蓝若智能技术股份有限公司 | Voltage transformer error state evaluation method based on multivariate time sequence analysis |
CN116840765B (en) * | 2023-08-31 | 2023-11-07 | 武汉格蓝若智能技术股份有限公司 | Voltage transformer error state evaluation method based on multivariate time sequence analysis |
CN116893297A (en) * | 2023-09-11 | 2023-10-17 | 常州旭泰克系统科技有限公司 | Method and system for monitoring energy consumption of rotating equipment |
CN116893297B (en) * | 2023-09-11 | 2024-01-12 | 常州旭泰克系统科技有限公司 | Method and system for monitoring energy consumption of rotating equipment |
CN116993232A (en) * | 2023-09-27 | 2023-11-03 | 青岛艾德森物联科技有限公司 | Energy consumption management optimization method and system for comprehensive energy station |
CN116993232B (en) * | 2023-09-27 | 2023-12-19 | 青岛艾德森物联科技有限公司 | Energy consumption management optimization method and system for comprehensive energy station |
CN117318312A (en) * | 2023-11-28 | 2023-12-29 | 南方电网调峰调频发电有限公司工程建设管理分公司 | Method and device for displaying power consumption data |
CN117318312B (en) * | 2023-11-28 | 2024-02-06 | 南方电网调峰调频发电有限公司工程建设管理分公司 | Method and device for displaying power consumption data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116341796A (en) | Energy consumption monitoring and evaluating system and method | |
CN111783953B (en) | 24-point power load value 7-day prediction method based on optimized LSTM network | |
CN105117602B (en) | A kind of metering device running status method for early warning | |
CN108763729B (en) | Process industry electromechanical system coupling state evaluation method based on network structure entropy | |
CN111178621A (en) | Parameter optimization method of electric heating load prediction support vector regression model | |
CN113036913B (en) | Method and device for monitoring state of comprehensive energy equipment | |
CN113535765A (en) | Intelligent factory remote real-time monitoring regulation cloud platform based on industrial internet | |
CN114444660A (en) | Short-term power load prediction method based on attention mechanism and LSTM | |
Yu et al. | Load forecasting based on smart meter data and gradient boosting decision tree | |
CN114021848A (en) | Generating capacity demand prediction method based on LSTM deep learning | |
CN114119273A (en) | Park comprehensive energy system non-invasive load decomposition method and system | |
CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
Liu et al. | Research on data correction method of micro air quality detector based on combination of partial least squares and random forest regression | |
CN110826794A (en) | Power plant coal consumption reference value rolling prediction method and device based on PSO (particle swarm optimization) SVM (support vector machine) | |
CN110941558A (en) | Intelligent office remote operation and maintenance method and system | |
CN116722605B (en) | Power distribution network scheduling optimization method based on Internet of things | |
CN106022542A (en) | Enterprise gateway load prediction method based on operation load characteristics | |
CN108345996B (en) | System and method for reducing wind power assessment electric quantity | |
CN115640980A (en) | Power grid engineering cost dynamic management system based on target control | |
CN113361737A (en) | Abnormity early warning method and system for photovoltaic module | |
CN114912700A (en) | Factory workshop electric power energy consumption assessment method and system | |
CN103984305A (en) | Method for evaluating clock state of power grid automation equipment based on data statistic analysis | |
CN111612227A (en) | Load prediction method based on K-means clustering and bat optimization neural network | |
CN111780149B (en) | Remote diagnosis method for equipment state of pulverizing system of thermal power plant | |
CN117076260B (en) | Parameter and equipment abnormality detection method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |