CN111915089A - Method and device for predicting pump set energy consumption of sewage treatment plant - Google Patents
Method and device for predicting pump set energy consumption of sewage treatment plant Download PDFInfo
- Publication number
- CN111915089A CN111915089A CN202010786759.2A CN202010786759A CN111915089A CN 111915089 A CN111915089 A CN 111915089A CN 202010786759 A CN202010786759 A CN 202010786759A CN 111915089 A CN111915089 A CN 111915089A
- Authority
- CN
- China
- Prior art keywords
- pump
- energy consumption
- time
- data
- pump set
- 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 166
- 239000010865 sewage Substances 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 36
- 239000013598 vector Substances 0.000 claims abstract description 45
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 40
- 238000007781 pre-processing Methods 0.000 claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 238000012549 training Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 238000013500 data storage Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 239000002351 wastewater Substances 0.000 claims description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement 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
- 230000001932 seasonal effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000009466 transformation Effects 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
- G06Q10/04—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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The invention discloses a method and a device for predicting pump set energy consumption of a sewage treatment plant, and relates to the technical field of pump set energy consumption prediction. Aiming at a pump group to be predicted, acquiring data such as the rotating speed of each pump in the pump group, the energy consumption of the pump group, the water level of a sewage confluence chamber and the like under different working conditions to obtain a historical data set; then, preprocessing historical data to obtain an energy consumption vector of the pump group; inputting the pump set energy consumption characteristic vector into a classification and regression tree algorithm, and calculating to obtain a pump set energy consumption model; inputting the current pump speed of each pump, the pump speed of each pump in the previous period, the water level of the sewage converging chamber in the previous period and the water level of the sewage converging chamber in the previous period into a pump set energy consumption model, and calculating to obtain the predicted energy consumption of the pump set; the pump set to be predicted refers to a pump set positioned in a sewage converging chamber of a sewage treatment plant, and the types of the pumps are different. By applying the method and the device, the energy consumption of the pump set can be predicted in advance and accurately.
Description
Technical Field
The invention relates to the technical field of pump set energy consumption prediction, in particular to a method and a device for predicting pump set energy consumption of a sewage treatment plant.
Background
The energy consumption of the sewage confluence chamber pump set in the sewage treatment plant occupies most of the electric energy in the sewage treatment process. With the enlargement of the urban scale, the sewage treatment pressure is increased, and more electric energy is inevitably consumed. In the existing traditional sewage treatment plant, the pump set energy consumption management of the sewage converging chamber is not always transparent.
However, the energy consumption level is one of key indexes for sewage treatment key control, and sewage treatment plants often make annual, seasonal or monthly energy consumption plan targets, which take into account not only the structural characteristics, operating conditions and the previous energy consumption level of each sewage treatment process, but also the targets for improving energy consumption management, technical improvement of equipment systems and other factors.
The energy consumption completion condition in the prior art is generally analyzed by counting the average energy consumption data accumulated in the time period within the time period specified by the energy consumption control target, and analyzing the difference between the energy consumption level and the energy consumption control target.
If the energy consumption of the pump set can be predicted in advance, the energy consumption level of the sewage treatment process can be reduced to a certain extent, the cost is reduced, and the sewage treatment efficiency is improved.
Disclosure of Invention
The invention aims to provide a method and a device for predicting pump set energy consumption of a sewage treatment plant, which can predict the pump set energy consumption in advance.
In order to solve the technical problems, the invention adopts the following technical scheme: a prediction method for pump set energy consumption of a sewage treatment plant is characterized by comprising the following steps:
s1, acquiring historical data of the pump group to be predicted:
s1-1, acquiring the pump speed PS of each pump in the pump set, the water level CL of the sewage confluence chamber and the total energy consumption E of the pump set;
s1-2, collecting and summarizing the data acquired in the step S1-1 by using a data acquisition module according to a time interval T;
s1-3, the data storage module stores the data in the database by taking the time stamp as a main key;
s2, the data preprocessing module processes the historical data to obtain a pump set energy consumption characteristic vector v, and the pump set energy consumption characteristic vector v is stored in a database after being preprocessed;
s3, inputting the pump unit energy consumption characteristic vector v subjected to data processing into a classification and regression tree algorithm, training an energy consumption model of the pump unit, and measuring the accuracy of the model by using the average absolute error MAE and the average absolute percentage error WMAPE;
s4, obtaining the pump speed PS ' of each current pump of the pump set to be predicted and the water level CL ' of the sewage converging chamber, preprocessing the data to obtain energy consumption prediction characteristic vector data v ', and inputting the energy consumption prediction characteristic vector data v ' into the pump set energy consumption prediction model to obtain the total energy consumption E ' of the pump set at the next time interval.
Still further, in step S1, the time interval T is not less than 15 minutes.
A further technical solution is that the specific process of the step S2 is as follows,
and S2-1, converting the total energy consumption of the pump set in the historical data into the energy consumption in a time period, wherein the calculation method is to subtract the total energy consumption at the previous moment from the total energy consumption at the current moment to obtain the total energy consumption at the previous time interval at the current moment. ,
s2-2, converting the historical data into a pump set energy consumption characteristic vector v by taking the time stamp as a main key:
v=(Et,Et-T,PS1,t,PS2,t,…,PSn,t,PS1,t-T,PS2,t-T,…,PSn,t-T,CLt,CLt-T)
wherein E istTotal energy consumption of pump group for time interval before t, Et-TTotal pump set energy consumption, PS, for the time interval preceding T-T1,tNumber 1 pump speed at time t, PS1,t-TNumber 1 pump speed at time T-T, PS2,tSpeed of pump numbered 2 at time t, PS2,t-TSpeed of rotation, PS, of the pump numbered 2 at time T-Tn,tNumber n pump speed at time t, PSn,t-TNumber n pump speed at time T-T, CLtThe water level of the sewage converging chamber at the time t, CLt-TThe water level of the sewage confluence chamber at the time T-T, T is the time interval in the step 1-2, and n is the number of pumps in the pump set;
s2-3, preprocessing the energy consumption characteristic vector of the pump set;
and S2-4, storing the pump set energy consumption characteristic vector in a database.
A further technical solution is that the specific process of the step S3 is as follows,
s3-1, reading all pump set energy consumption characteristic vectors v from a database;
s3-2, inputting the pump set energy consumption feature vector v into a classification and regression tree algorithm in an energy consumption model training module, wherein the algorithm regression model is as follows:
Et=f(Et-T,PS1,t,PS2,t,…,PSn,t,PS1,t-T,PS2,t-T,…,PSn,t-T,CLt,CLt-T)
wherein E istTotal energy consumption of pump group for time interval before t, Et-TTotal pump set energy consumption, PS, for the time interval preceding T-T1,tNumber 1 pump speed at time t, PS1,t-TNumber 1 pump speed at time T-T, PS2,tSpeed of pump numbered 2 at time t, PS2,t-TSpeed of rotation, PS, of the pump numbered 2 at time T-Tn,tNumber n pump speed at time t, PSn,t-TNumber n pump speed at time T-T, CLtThe water level of the sewage converging chamber at the time t, CLt-TThe water level of the sewage confluence chamber at the time T-T, T is the time interval in the step 1-2, and n is the number of pumps in the pump set;
and S3-3, storing the results of the classification and regression tree algorithm as model files.
A further technical solution is that the specific process of the step S4 is as follows,
s4-1, acquiring the pump speed PS 'of each pump of the pump group through a PLC, and measuring the water level CL' of the sewage confluence chamber through a water level meter;
s4-2, collecting and summarizing the data by using a data acquisition module according to the time interval T;
s4-3, preprocessing the real-time data to obtain energy consumption prediction feature vector data v':
v'=(Et-T',PS1,t',PS2,t',…,PSn,t',PS1,t-T',PS2,t-T',…,PSn,t-T',CLt',CLt-T')
wherein E ist-T' Total Pump Unit energy consumption, PS, for the preceding time interval T-T1,t' rotational speed of the pump numbered 1 at time t, PS1,t-T' rotational speed of the pump numbered 1 at time T-T, PS2,t' rotational speed of the pump numbered 2 at time t, PS2,t-T' rotational speed of the pump numbered 2 at time T-T, PSn,t' rotational speed of the pump numbered n at time t, PSn,t-T' rotational speed of the pump numbered n at time T-T, CLt' Water level of the wastewater collection chamber at time t, CLt-TThe water level of the sewage confluence chamber is T-T, T is the time interval in the step 1-2, n is the number of pumps in the pump set, and T is the current time;
s4-4, inputting the energy consumption prediction characteristic vector data v' into a pump set energy consumption prediction model to obtain predicted pump set energy consumption Et。
The further technical scheme is that the data preprocessing module performs dimensionality reduction on the data through principal component analysis, and the specific steps are as follows: 1) carrying out zero equalization on each characteristic field in the original data matrix; 2) solving a covariance matrix, an eigenvalue and an eigenvector; 3) arranging the eigenvectors from large to small according to the sizes of the corresponding eigenvalues, and taking the first k eigenvectors to form a data matrix after dimension reduction; where k represents the dimensionality after dimensionality reduction.
The invention also relates to a device for predicting the pump set energy consumption of a sewage treatment plant, which is characterized in that: comprises a data acquisition module, a data storage module, a data preprocessing module, an energy consumption model training module and an energy consumption prediction module, wherein,
the data acquisition module is used for acquiring the pump speed PS of each pump of the pump group through the PLC, acquiring the water level CL of the sewage confluence chamber through a water level meter and acquiring the total energy consumption E of the pump group through an electric meter;
the data storage module is used for storing the data in the database by taking the time stamp as a main key;
the data preprocessing module is used for preprocessing the energy consumption characteristic vector v of the pump set and real-time data;
the energy consumption model training module is used for inputting the pump set energy consumption characteristic vector v into a classification and regression tree algorithm and calculating to obtain a pump set energy consumption model;
and the energy consumption prediction module is used for inputting the energy consumption prediction characteristic vector data v' into the pump set energy consumption prediction model to obtain the total energy consumption of the pump set at the next time interval.
Compared with the prior art, the invention has the beneficial effects that: the energy consumption of the pump set at the next time interval is accurately predicted so as to be further applied to pump set optimization control, finally, the energy consumption level of the sewage treatment process is reduced to a certain extent, the cost is reduced, and the sewage treatment efficiency is improved.
Drawings
FIG. 1 is a flow chart of a prediction method of pump set energy consumption of a sewage treatment plant in the invention.
Fig. 2 is a structural block diagram of a device for predicting pump set energy consumption of a sewage treatment plant in the invention.
Fig. 3 is a graph of predicted values and observed values of pump set energy consumption.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
Fig. 1 shows a method for predicting pump set energy consumption of a sewage treatment plant, as shown in fig. 1, and the specific implementation steps are as follows:
s1: firstly, data acquisition is carried out on a pump group to be predicted, and the specific steps are as follows:
s1-1, acquiring the pump speed PS of each pump of the pump set through a PLC, acquiring the water level CL of the sewage confluence chamber through a water level meter, and acquiring the total energy consumption E of the pump set through an electric meter;
s1-2, collecting and summarizing the data acquired in the S1-1 by using a data acquisition module according to a time interval T, wherein the T is 15 minutes;
s1-3, the data storage module stores the data in the database by taking the time stamp as a main key;
s2: the data preprocessing module preprocesses the historical data to obtain a pump set energy consumption characteristic vector v, and the specific steps are as follows:
and S2-1, converting the total energy consumption of the pump set in the historical data into the energy consumption in a time period, wherein the calculation method is to subtract the total energy consumption at the previous moment from the total energy consumption at the current moment to obtain the total energy consumption at the previous time interval at the current moment.
S2-2, converting the historical data into a pump set energy consumption characteristic vector v by taking the time stamp as a main key:
v=(Et,Et-T,PS1,t,PS2,t,…,PSn,t,PS1,t-T,PS2,t-T,…,PSn,t-T,CLt,CLt-T)
wherein E istTotal energy consumption of pump group for time interval before t, Et-TTotal pump set energy consumption, PS, for the time interval preceding T-T1,tNumber 1 pump speed at time t, PS1,t-TNumber 1 pump speed at time T-T, PS2,tSpeed of pump numbered 2 at time t, PS2,t-TSpeed of rotation, PS, of the pump numbered 2 at time T-Tn,tNumber n pump speed at time t, PSn,t-TNumber n pump speed at time T-T, CLtThe water level of the sewage converging chamber at the time t, CLt-TThe water level of the sewage confluence chamber at the time T-T, T is the time interval in the step 1-2, and n is the number of pumps in the pump set;
s2-3, preprocessing the energy consumption characteristic vector of the pump set, and reducing the dimension of the data through principal component analysis.
The method comprises the following specific steps: 1) carrying out zero equalization on each characteristic field in the original data matrix; 2) solving a covariance matrix, an eigenvalue and an eigenvector; 3) arranging the eigenvectors from large to small according to the sizes of the corresponding eigenvalues, and taking the first k eigenvectors to form a data matrix after dimension reduction; where k represents the dimensionality after dimensionality reduction.
And S2-4, storing the pump set energy consumption characteristic vector in a database.
S3: inputting the pump set energy consumption characteristic vector v subjected to data processing into a classification and regression tree algorithm, training an energy consumption model of the pump set, and measuring the accuracy of the model by using an average percentage error MPE and a weighted average absolute percentage error WMAPE, wherein the method specifically comprises the following steps:
s3-1, reading all pump set energy consumption characteristic vectors v from a database;
s3-2, inputting the pump set energy consumption feature vector v into a classification and regression tree algorithm in an energy consumption model training module, wherein the algorithm regression model is as follows:
Et=f(Et-T,PS1,t,PS2,t,…,PSn,t,PS1,t-T,PS2,t-T,…,PSn,t-T,CLt,CLt-T)
wherein E istTotal energy consumption of pump group for time interval before t, Et-TTotal pump set energy consumption, PS, for the time interval preceding T-T1,tNumber 1 pump speed at time t, PS1,t-TNumber 1 pump speed at time T-T, PS2,tSpeed of pump numbered 2 at time t, PS2,t-TSpeed of rotation, PS, of the pump numbered 2 at time T-Tn,tNumber n pump speed at time t, PSn,t-TNumber n pump speed at time T-T, CLtThe water level of the sewage converging chamber at the time t, CLt-TThe water level of the sewage confluence chamber at the time T-T, T is the time interval in the step 1-2, and n is the number of pumps in the pump set;
and S3-3, storing the results of the classification and regression tree algorithm as model files.
S4: the method comprises the following steps of obtaining the rotating speed and water level data of the current pump set, inputting the data into a pump set energy consumption prediction module to predict the energy consumption of the pump set, and specifically comprises the following steps:
s4-1, acquiring the pump speed PS 'of each pump of the pump group through a PLC, and measuring the water level CL' of the sewage confluence chamber through a water level meter;
s4-2, collecting and summarizing the data by using a data acquisition module according to the time interval T;
s4-3, preprocessing the real-time data to obtain energy consumption prediction feature vector data v':
v'=(Et-T',PS1,t',PS2,t',…,PSn,t',PS1,t-T',PS2,t-T',…,PSn,t-T',CLt',CLt-T')
wherein E ist-T' Total Pump Unit energy consumption, PS, for the preceding time interval T-T1,t' rotational speed of the pump numbered 1 at time t, PS1,t-T' rotational speed of the pump numbered 1 at time T-T, PS2,t' rotational speed of the pump numbered 2 at time t, PS2,t-T' rotational speed of the pump numbered 2 at time T-T, PSn,t' rotational speed of the pump numbered n at time t, PSn,t-T' rotational speed of the pump numbered n at time T-T, CLt' Water level of the wastewater collection chamber at time t, CLt-TThe water level of the sewage confluence chamber is T-T, T is the time interval in the step 1-2, n is the number of pumps in the pump set, and T is the current time;
s4-4, inputting the energy consumption prediction characteristic vector data v' into a pump set energy consumption prediction model to obtain predicted pump set energy consumption Et。
In order to verify the accuracy of the energy consumption model trained by the classification and regression tree algorithm, another two algorithms are adopted to train the model according to the algorithm, and the comparison result is shown in table 1.
TABLE 1
Algorithm | Mean percentage error | Weighted mean absolute percentage error |
Classification and regression tree | 0.0149 | 0.0004741 |
Support vector machine | 0.0226 | 0.0005257 |
Nearest neighbor of K | 0.0183 | 0.0005082 |
As can be seen from the above table, the prediction model obtained by the classification and regression tree algorithm is the best, and provides an accurate prediction result, and the predicted value of the model is compared with the actual value, as shown in fig. 3, which proves the feasibility and accuracy of the method of the present invention.
Example 2
Fig. 2 shows a prediction device for pump set energy consumption of sewage treatment plant, which comprises a data acquisition module, a data storage module, a data preprocessing module, an energy consumption model training module and an energy consumption prediction module, wherein,
the data acquisition module is used for acquiring the pump speed PS of each pump of the pump group through the PLC, acquiring the water level CL of the sewage confluence chamber through a water level meter and acquiring the total energy consumption E of the pump group through an electric meter;
the data storage module is used for storing the data in the database by taking the time stamp as a main key;
the data preprocessing module is used for preprocessing the energy consumption characteristic vector v of the pump set and real-time data;
the energy consumption model training module is used for inputting the pump set energy consumption characteristic vector v into a classification and regression tree algorithm and calculating to obtain a pump set energy consumption model;
and the energy consumption prediction module is used for inputting the energy consumption prediction characteristic vector data v' into the pump set energy consumption prediction model to obtain the total energy consumption of the pump set at the next time interval.
The above-mentioned apparatus is used for executing the method provided by the foregoing embodiment, and the implementation principle and technical effect are similar, which are not described herein again.
The embodiment of the invention also provides a storage medium, wherein a computer program is stored on the storage medium, and when the computer program is read and operated by a processor, the energy consumption prediction method is realized.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
An embodiment of the present invention further provides an electronic device, including: the energy consumption prediction system comprises a processor, a storage medium and a bus, wherein the storage medium stores machine readable instructions executable by the processor, when an electronic device runs, the processor is communicated with the storage medium through the bus, and the processor executes the machine readable instructions to execute the steps of the energy consumption prediction method.
The above-described embodiments are merely preferred embodiments of the present invention, which should not be construed as limiting the invention. Various changes and modifications may be made by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present invention. Therefore, the technical scheme obtained by adopting the mode of equivalent replacement or equivalent transformation is within the protection scope of the invention.
Claims (7)
1. A prediction method for pump set energy consumption of a sewage treatment plant is characterized by comprising the following steps:
s1, acquiring historical data of the pump group to be predicted:
s1-1, acquiring the pump speed PS of each pump in the pump set, the water level CL of the sewage confluence chamber and the total energy consumption E of the pump set;
s1-2, collecting and summarizing the data acquired in the step S1-1 by using a data acquisition module according to a time interval T;
s1-3, the data storage module stores the data in the database by taking the time stamp as a main key;
s2, preprocessing the historical data by the data preprocessing module to obtain a pump set energy consumption characteristic vector v, preprocessing the pump set energy consumption characteristic vector v, and storing the preprocessed pump set energy consumption characteristic vector v in a database;
s3, inputting the pump unit energy consumption characteristic vector v subjected to data processing into a classification and regression tree algorithm, training an energy consumption model of the pump unit, and measuring the accuracy of the model by using an average percentage error MPE and a weighted average absolute percentage error WMAPE;
s4, obtaining the pump speed PS ' of each pump of the pump group to be predicted and the water level CL ' of the sewage converging chamber, preprocessing the data to obtain energy consumption prediction characteristic vector data v ', and inputting the energy consumption prediction characteristic vector data v ' into the pump group energy consumption prediction model to obtain the total energy consumption E ' of the pump group at the next time interval.
2. The method for predicting the pump set energy consumption of the sewage treatment plant according to claim 1, characterized in that: step S1 shows that the time interval T is not less than 15 minutes.
3. The method for predicting the pump set energy consumption of the sewage treatment plant according to claim 1, characterized in that: said step (c) is
The specific process of S2 is as follows,
and S2-1, converting the total energy consumption of the pump set in the historical data into the energy consumption in a time period, wherein the calculation method is to subtract the total energy consumption at the previous moment from the total energy consumption at the current moment to obtain the total energy consumption at the previous time interval at the current moment.
S2-2, converting the historical data into a pump set energy consumption characteristic vector v by taking the time stamp as a main key:
v=(Et,Et-T,PS1,t,PS2,t,…,PSn,t,PS1,t-T,PS2,t-T,…,PSn,t-T,CLt,CLt-T)
wherein E istTotal energy consumption of pump group for time interval before t, Et-TTotal pump set energy consumption, PS, for the time interval preceding T-T1,tNumber 1 pump speed at time t, PS1,t-TNumber 1 pump speed at time T-T, PS2,tSpeed of pump numbered 2 at time t, PS2,t-TSpeed of rotation, PS, of the pump numbered 2 at time T-Tn,tNumber n pump speed at time t, PSn,t-TNumber n pump speed at time T-T, CLtThe water level of the sewage converging chamber at the time t, CLt-TThe water level of the sewage confluence chamber at the time T-T, T is the time interval in the step 1-2, and n is the number of pumps in the pump set;
s2-3, preprocessing the energy consumption characteristic vector of the pump set;
and S2-4, storing the pump set energy consumption characteristic vector in a database.
4. The method for predicting the pump set energy consumption of the sewage treatment plant according to claim 1, characterized in that: said step (c) is
The specific process of S3 is as follows,
s3-1, reading all pump set energy consumption characteristic vectors v from a database;
s3-2, inputting the pump set energy consumption feature vector v into a classification and regression tree algorithm in an energy consumption model training module, wherein the algorithm regression model is as follows:
Et=f(Et-T,PS1,t,PS2,t,…,PSn,t,PS1,t-T,PS2,t-T,…,PSn,t-T,CLt,CLt-T)
wherein E istTotal energy consumption of pump group for time interval before t, Et-TTotal pump set energy consumption, PS, for the time interval preceding T-T1,tNumber 1 pump speed at time t, PS1,t-TNumber 1 pump speed at time T-T, PS2,tSpeed of pump numbered 2 at time t, PS2,t-TSpeed of rotation, PS, of the pump numbered 2 at time T-Tn,tNumber n pump speed at time t, PSn,t-TNumber n pump speed at time T-T, CLtThe water level of the sewage converging chamber at the time t, CLt-TThe water level of the sewage confluence chamber at the time T-T, T is the time interval in the step 1-2, and n is the number of pumps in the pump set;
and S3-3, storing the results of the classification and regression tree algorithm as model files.
5. The method for predicting the pump set energy consumption of the sewage treatment plant according to claim 1, characterized in that: said step (c) is
The specific process of S4 is as follows,
s4-1, acquiring the pump speed PS 'of each pump of the pump group through a PLC, and measuring the water level CL' of the sewage confluence chamber through a water level meter;
s4-2, collecting and summarizing the data by using a data acquisition module according to the time interval T;
s4-3, preprocessing the real-time data to obtain energy consumption prediction feature vector data v':
v′=(Et-T′,PS1,t′,PS2,t′,…;PSn,t′,PS1,t-T′,PS2,t-T′,…;PSn,t-T′,CLt′,CLt-T′)
wherein E ist-T' Total Pump Unit energy consumption, PS, for the preceding time interval T-T1,t' rotational speed of the pump numbered 1 at time t, PS1,t-T' rotational speed of the pump numbered 1 at time T-T, PS2,t' rotational speed of the pump numbered 2 at time t, PS2,t-T' rotational speed of the pump numbered 2 at time T-T, PSn,t' rotational speed of the pump numbered n at time t, PSn,t-T' rotational speed of the pump numbered n at time T-T, CLt' Water level of the wastewater collection chamber at time t, CLt-TThe water level of the sewage confluence chamber is T-T, T is the time interval in the step 1-2, n is the number of pumps in the pump set, and T is the current time;
s4-4, inputting the energy consumption prediction characteristic vector data v' into a pump set energy consumption prediction model to obtain the energy consumption E predicted by the pump sett。
6. The method for predicting the pump set energy consumption of the sewage treatment plant according to claim 1, characterized in that: the data preprocessing module performs dimensionality reduction on data through principal component analysis, and the method comprises the following specific steps: 1) carrying out zero equalization on each characteristic field in the original data matrix; 2) solving a covariance matrix, an eigenvalue and an eigenvector; 3) arranging the eigenvectors from large to small according to the sizes of the corresponding eigenvalues, and taking the first k eigenvectors to form a data matrix after dimension reduction; where k represents the dimensionality after dimensionality reduction.
7. The utility model provides a prediction unit of sewage treatment plant pump package energy consumption which characterized in that: comprises a data acquisition module, a data storage module, a data preprocessing module, an energy consumption model training module and an energy consumption prediction module, wherein,
the data acquisition module is used for acquiring the pump speed PS of each pump of the pump group through the PLC, acquiring the water level CL of the sewage confluence chamber through a water level meter and acquiring the total energy consumption E of the pump group through an electric meter;
the data storage module is used for storing the data in the database by taking the time stamp as a main key;
the data preprocessing module is used for preprocessing the energy consumption characteristic vector v of the pump set and real-time data;
the energy consumption model training module is used for inputting the pump set energy consumption characteristic vector v into a classification and regression tree algorithm and calculating to obtain a pump set energy consumption model;
and the energy consumption prediction module is used for inputting the energy consumption prediction characteristic vector data v' into the pump set energy consumption prediction model to obtain the total energy consumption of the pump set at the next time interval.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010786759.2A CN111915089A (en) | 2020-08-07 | 2020-08-07 | Method and device for predicting pump set energy consumption of sewage treatment plant |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010786759.2A CN111915089A (en) | 2020-08-07 | 2020-08-07 | Method and device for predicting pump set energy consumption of sewage treatment plant |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111915089A true CN111915089A (en) | 2020-11-10 |
Family
ID=73288299
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010786759.2A Pending CN111915089A (en) | 2020-08-07 | 2020-08-07 | Method and device for predicting pump set energy consumption of sewage treatment plant |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111915089A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112906306A (en) * | 2021-03-24 | 2021-06-04 | 青岛洪锦智慧能源技术有限公司 | Prediction method for energy consumption of air compressor unit of air compression station |
CN112966446A (en) * | 2021-03-24 | 2021-06-15 | 青岛洪锦智慧能源技术有限公司 | Method for predicting cooling water circulation energy consumption in central air-conditioning refrigeration system |
CN113033092A (en) * | 2021-03-24 | 2021-06-25 | 石化盈科信息技术有限责任公司 | Sewage treatment data processing method and device, computer equipment and storage medium |
CN115859808A (en) * | 2022-12-01 | 2023-03-28 | 南栖仙策(南京)科技有限公司 | Pump set work prediction method and device, electronic equipment and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102004041661A1 (en) * | 2004-08-27 | 2006-03-30 | Siemens Ag | Pump stations and pumps control method in pipeline, involves total energy consumption of all pumps minimised at predetermined total flow and height |
JP2014105989A (en) * | 2012-11-28 | 2014-06-09 | Mitsubishi Electric Corp | Energy consumption prediction method of building power equipment |
WO2014157751A1 (en) * | 2013-03-27 | 2014-10-02 | 부산대학교 산학협력단 | Energy-saving prediction system and method based on diagnosis of state of energy consumption in sewage treatment plant |
EP2796724A1 (en) * | 2013-04-24 | 2014-10-29 | Wilo Se | Optimised operation of a variable speed pump in a waste water pumping station |
CN106597879A (en) * | 2016-11-03 | 2017-04-26 | 中冶华天工程技术有限公司 | Sewage treatment elevator pump optimized scheduling method |
CN109376934A (en) * | 2018-10-31 | 2019-02-22 | 广东兴发铝业有限公司 | A kind of energy consumption prediction technique of the extruder based on big data |
CN109687447A (en) * | 2018-12-29 | 2019-04-26 | 华润电力技术研究院有限公司 | A kind of electric power energy consumption prediction technique and device |
CN109726872A (en) * | 2018-12-29 | 2019-05-07 | 华润电力技术研究院有限公司 | A kind of energy consumption prediction technique, device, storage medium and electronic equipment |
CN110866528A (en) * | 2019-10-28 | 2020-03-06 | 腾讯科技(深圳)有限公司 | Model training method, energy consumption use efficiency prediction method, device and medium |
CN111160611A (en) * | 2019-12-02 | 2020-05-15 | 万翼科技有限公司 | Energy consumption estimation method and device, computer equipment and storage medium |
CN111191712A (en) * | 2019-12-27 | 2020-05-22 | 浙江工业大学 | Printing and dyeing setting machine energy consumption classification prediction method based on gradient lifting decision tree |
-
2020
- 2020-08-07 CN CN202010786759.2A patent/CN111915089A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102004041661A1 (en) * | 2004-08-27 | 2006-03-30 | Siemens Ag | Pump stations and pumps control method in pipeline, involves total energy consumption of all pumps minimised at predetermined total flow and height |
JP2014105989A (en) * | 2012-11-28 | 2014-06-09 | Mitsubishi Electric Corp | Energy consumption prediction method of building power equipment |
WO2014157751A1 (en) * | 2013-03-27 | 2014-10-02 | 부산대학교 산학협력단 | Energy-saving prediction system and method based on diagnosis of state of energy consumption in sewage treatment plant |
EP2796724A1 (en) * | 2013-04-24 | 2014-10-29 | Wilo Se | Optimised operation of a variable speed pump in a waste water pumping station |
CN106597879A (en) * | 2016-11-03 | 2017-04-26 | 中冶华天工程技术有限公司 | Sewage treatment elevator pump optimized scheduling method |
CN109376934A (en) * | 2018-10-31 | 2019-02-22 | 广东兴发铝业有限公司 | A kind of energy consumption prediction technique of the extruder based on big data |
CN109687447A (en) * | 2018-12-29 | 2019-04-26 | 华润电力技术研究院有限公司 | A kind of electric power energy consumption prediction technique and device |
CN109726872A (en) * | 2018-12-29 | 2019-05-07 | 华润电力技术研究院有限公司 | A kind of energy consumption prediction technique, device, storage medium and electronic equipment |
CN110866528A (en) * | 2019-10-28 | 2020-03-06 | 腾讯科技(深圳)有限公司 | Model training method, energy consumption use efficiency prediction method, device and medium |
CN111160611A (en) * | 2019-12-02 | 2020-05-15 | 万翼科技有限公司 | Energy consumption estimation method and device, computer equipment and storage medium |
CN111191712A (en) * | 2019-12-27 | 2020-05-22 | 浙江工业大学 | Printing and dyeing setting machine energy consumption classification prediction method based on gradient lifting decision tree |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112906306A (en) * | 2021-03-24 | 2021-06-04 | 青岛洪锦智慧能源技术有限公司 | Prediction method for energy consumption of air compressor unit of air compression station |
CN112966446A (en) * | 2021-03-24 | 2021-06-15 | 青岛洪锦智慧能源技术有限公司 | Method for predicting cooling water circulation energy consumption in central air-conditioning refrigeration system |
CN113033092A (en) * | 2021-03-24 | 2021-06-25 | 石化盈科信息技术有限责任公司 | Sewage treatment data processing method and device, computer equipment and storage medium |
CN115859808A (en) * | 2022-12-01 | 2023-03-28 | 南栖仙策(南京)科技有限公司 | Pump set work prediction method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111915089A (en) | Method and device for predicting pump set energy consumption of sewage treatment plant | |
CN109543943B (en) | Electric price checking execution method based on big data deep learning | |
CN110163429B (en) | Short-term load prediction method based on similarity day optimization screening | |
CN109726865A (en) | Customer charge probability density prediction technique, device and storage medium based on EMD-QRF | |
CN109934301B (en) | Power load cluster analysis method, device and equipment | |
CN111241755A (en) | Power load prediction method | |
CN102832617A (en) | Large power grid transient state stabilization analyzing method based on precision pattern discrimination | |
CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
CN109190184A (en) | A kind of heating system historical data preprocess method | |
CN111460001A (en) | Theoretical line loss rate evaluation method and system for power distribution network | |
Dong et al. | Forecasting smart meter energy usage using distributed systems and machine learning | |
CN101976301A (en) | Method and device for preprocessing historical data in yearly load forecasting | |
CN107590747A (en) | Power grid asset turnover rate computational methods based on the analysis of comprehensive energy big data | |
CN113434989A (en) | Pipe network leakage amount prediction method and system based on attention mechanism and LSTM | |
CN110008981B (en) | Electric-water gas energy-consumption alternative guidable evaluation method based on vector fuzzy matrix model | |
CN114676931B (en) | Electric quantity prediction system based on data center technology | |
CN111080089A (en) | Method and device for determining critical factors of line loss rate based on random matrix theory | |
CN113835964B (en) | Cloud data center server energy consumption prediction method based on small sample learning | |
CN110659681B (en) | Time sequence data prediction system and method based on pattern recognition | |
CN109189775B (en) | Industrial monitoring platform mass data processing system and method | |
Yan et al. | Comparative study of electricity-theft detection based on gradient boosting machine | |
CN109871998B (en) | Power distribution network line loss rate prediction method and device based on expert sample library | |
CN112966446B (en) | Method for predicting cooling water circulation energy consumption in central air-conditioning refrigeration system | |
Yu et al. | Research on risk identification of power theft in low-voltage distribution network based on machine learning hybrid algorithm | |
CN111626586B (en) | Data quality detection method, device, computer equipment and storage medium |
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 |