CN106773692B - Equipment operation control method based on Gaussian distribution - Google Patents
Equipment operation control method based on Gaussian distribution Download PDFInfo
- Publication number
- CN106773692B CN106773692B CN201611191551.6A CN201611191551A CN106773692B CN 106773692 B CN106773692 B CN 106773692B CN 201611191551 A CN201611191551 A CN 201611191551A CN 106773692 B CN106773692 B CN 106773692B
- Authority
- CN
- China
- Prior art keywords
- gaussian distribution
- parameter
- equipment
- working condition
- gaussian
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a device operation control method based on Gaussian distribution, which is characterized by comprising the following steps: the method comprises the steps of data acquisition and processing, establishing a mixed Gaussian distribution model, calculating Gaussian distribution model coefficients based on a nonlinear least square method, controlling equipment operation according to a mixed Gaussian distribution function and a piecewise function, and the like, wherein the mixed Gaussian distribution model is obtained by linearly combining a plurality of Gaussian distributions, and the model coefficients are calculated by the nonlinear least square method, so that the calculation complexity is reduced; model establishment and coefficient calculation are carried out according to working condition environment parameters, so that artificial subjectivity is avoided; the equipment operation is controlled according to the Gaussian mixture distribution function, so that the equipment operation is controlled more accurately, and the equipment control method has the advantages of strong practicability, high control accuracy and the like; and updating the Gaussian distribution function, namely continuously updating the mixed Gaussian distribution function, continuously maintaining the control precision and ensuring that the mixed Gaussian distribution function is highly consistent with the current equipment operation condition parameters.
Description
Technical Field
The invention relates to the field of operation control of equipment, in particular to a system and a method for controlling equipment operation based on Gaussian distribution.
Background
In recent years, with the increasing level of automation of equipment, the demand for control accuracy of the equipment is also increasing. Especially in the sewage treatment industry with relatively low automation level, how to improve the control precision of the equipment is more concerned by operation managers, especially for equipment with high energy consumption, such as a lifting pump, a blower and the like.
The operation control of equipment needs to be adjusted according to the working condition, and when the COD concentration in the inlet water is lower, the frequency or the air volume of the blower needs to be properly adjusted and reduced by taking the blower of a sewage treatment plant as an example. How to adjust the frequency of the blower according to the change of COD concentration and other water quality indexes at that time is a difficult point of preventing the improvement of control precision of equipment such as the blower and the like due to the correlation of the frequency of the blower and the water quality indexes. The quantitative corresponding relation between the water quality index and the running frequency or the air volume of the blower is compared by using experience mostly, quantitative setting is carried out, the flexibility is poor, and the actual inlet and outlet are larger. From the appearance frequency of different water qualities, a certain probability distribution is presented, the probability distribution is relatively close to the normal distribution, and a universal method is provided for different water qualities due to different areas and different sewage sources.
Disclosure of Invention
The invention provides a method and a system for controlling equipment operation based on Gaussian distribution, which are used for realizing continuous high-precision control on the equipment operation and improving the matching degree of the equipment operation and equipment operation environment parameters.
The embodiment of the invention provides a device operation control system and method based on Gaussian distribution, which comprises the following steps:
acquiring data information of working condition environmental parameters related to equipment operation through a data acquisition device;
establishing a mixed Gaussian distribution model;
calculating a mixed Gaussian distribution model coefficient based on a nonlinear least square method to obtain a mixed Gaussian distribution function;
controlling the equipment to operate according to the Gaussian mixture distribution function;
and updating the Gaussian mixture distribution function.
The method comprises the steps of acquiring and processing data, establishing a mixed Gaussian distribution model, calculating Gaussian distribution model coefficients based on a nonlinear least square method, controlling equipment to operate according to the mixed Gaussian model and the like, linearly combining a plurality of Gaussian distributions to obtain a mixed Gaussian distribution model, and calculating the model coefficients by the nonlinear least square method to reduce the calculation complexity; model establishment and coefficient calculation are carried out according to working condition environment parameters, so that artificial subjectivity is avoided; the equipment operation is controlled according to the Gaussian mixture distribution function, so that the equipment operation is controlled more accurately, and the equipment control method has the advantages of strong practicability, high control accuracy and the like; and updating the Gaussian distribution function, namely continuously updating the mixed Gaussian distribution function, continuously maintaining the control precision and ensuring that the mixed Gaussian distribution function is highly consistent with the current equipment operation condition parameters.
Drawings
FIG. 1 is a flow chart of a system and method for controlling the operation of a device based on Gaussian distribution according to an embodiment of the present invention;
FIG. 2 is a flow chart of a system and method for controlling the operation of a device based on Gaussian distribution according to a second embodiment of the present invention;
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are exemplary only, and are not limiting upon the present invention.
Example one
Fig. 1 is a flowchart of an apparatus operation control system and method based on gaussian distribution according to an embodiment of the present invention, where this embodiment is applicable to operation control of apparatuses in an environmental protection facility and a factory floor, and the method may be executed by a server, and specifically includes the following steps:
and S101, acquiring data information of the working condition environmental parameters related to equipment operation through a data acquisition device.
The method comprises the steps that data information of working condition environment parameters related to equipment operation is obtained in real time through remote interaction with an instrument;
the data information of the working condition environment parameters is acquired by multiple types of data information which need to be measured in real time for multiple times, and is preferably acquired and transmitted to the server at the first time through the data acquisition device;
preferably, the acquisition may be implemented by hardware to acquire data of an electric meter and a detection instrument, or may be implemented by network communication or other methods to acquire online data such as a database and other methods, and a gas data acquisition method;
and carrying out primary filtering treatment according to the data information in the server to remove abnormal data.
And S102, establishing a mixed Gaussian model.
1) Establishing a Gaussian distribution model;
the Gaussian mixture model is a linear combination of multiple Gaussian distributions, and a probability density function expression of the Gaussian distributions is shown as a formula (1)
Where x is the sample point, μiIs the sample mean, σi 2Is the sample variance;
2) establishing a mixed Gaussian distribution model
The probability density function of Gaussian mixture distribution is expressed as
Wherein X is a total sample, aiInfluence factor of Gaussian distribution, μ, as the i-th indexiIs the mean of the gaussian distribution of the ith index,
the variance of the i-th index gaussian distribution, k is the number of gaussian distributions, and when k is 1, the mixed gaussian distribution model f (x) ═ N (μ, σ) is a probability density function of one-dimensional gaussian distribution.
And S103, calculating a mixed Gaussian distribution model coefficient based on a nonlinear least square method to obtain a mixed Gaussian distribution function.
1) Recording X as input training data according to the data information of the working condition environment parameters;
2) calculating a Gaussian distribution model coefficient of each working condition environment parameter according to a nonlinear least square method to obtain a probability density function of Gaussian distribution;
3) distributing different influence factor coefficients for different parameters according to the influence of different parameters of the working condition environment on the operation control of the equipment;
4) and calculating a mixed Gaussian distribution model coefficient according to the probability density function expression of Gaussian distribution of different parameters of the working condition environment and the influence factor coefficients of the different working condition environment parameters to obtain a mixed Gaussian distribution function.
And step S104, controlling the equipment to operate according to the Gaussian mixture distribution function.
1) Selecting an adjustable parameter index of the equipment operation key, and recording the parameter index as an equipment parameter Y;
2) constructing the relation between the equipment parameter Y and the Gaussian mixture distribution probability of the working condition environmental parameter, wherein the expression is
Wherein X' is the current working condition environment of equipment operationData information of the parameter, YmaxFor an upper limit value of the range in which a plant parameter can be adjusted during operation of the plant, YminThe lower limit value of the adjustable range of the equipment parameters is f (X), and a Gaussian distribution function is mixed with the working condition parameters;
3) calculating to obtain an equipment parameter Y (X') according to the formula (3) and the data information of the current working condition environment parameter of the equipment operation;
4) and the regulating equipment operates according to the equipment parameter Y (X') obtained by calculation.
Step S105, inputting training data by taking the current working condition environment parameters and the historical working condition environment parameters as models, calculating a Gaussian distribution model coefficient of each working condition environment parameter according to a nonlinear least square method, obtaining a probability density function formula of Gaussian distribution, updating a mixed Gaussian distribution function coefficient, and improving control accuracy.
Step S106, setting the time period T for updating the coefficient of the Gaussian distribution function according to the using state of the equipment1Preferably said time period T1Is in the range of 0.5h-24h, and sets the time period T for adjusting the equipment parameters2Preferably said time period T2The range of (1) is 0.5h-72 h.
According to the technical scheme, the problem of accurate control of equipment operation control is solved, the equipment operation state is adjusted according to the real-time working condition environment, the optimization operation of the equipment relative working condition environment is achieved, and the problem of accurate control of the equipment operation is solved.
Example two
Fig. 2 is a flowchart of a system and a method for controlling operation of devices based on gaussian distribution according to a second embodiment of the present invention, where the present embodiment is applicable to operation control of devices in an environmental protection facility and a factory floor, and the method may be executed by a server, and specifically includes the following steps:
step S201, acquiring data information of working condition environment parameters related to equipment operation through a data acquisition device.
The data information of the working condition environmental parameters related to the equipment operation is acquired in real time through remote interaction with the instrument.
The data information of the working condition environment parameters is acquired by multiple types of data information which need to be measured in real time for multiple times, and is preferably acquired and transmitted to the server through the data acquisition device at the first time.
Preferably, the collection may be implemented by hardware to collect data of an electric meter and a detection instrument, or may be implemented by network communication to obtain online data such as a database and a gas data obtaining method.
And carrying out primary filtering treatment according to the data information in the server to remove abnormal data.
And S202, establishing a mixed Gaussian model.
The mixed Gaussian distribution model is a linear combination of a plurality of Gaussian distributions, and a probability density function expression of the Gaussian distributions is shown as a formula (1);
the probability density function of the Gaussian mixture distribution is expressed as formula (2);
and S203, calculating a mixed Gaussian distribution model coefficient based on a nonlinear least square method to obtain a mixed Gaussian distribution function.
1) Recording X as input training data according to the data information of the working condition environment parameters;
2) calculating a Gaussian distribution model coefficient of each working condition environment parameter according to a nonlinear least square method to obtain a probability density function of Gaussian distribution;
3) and calculating the model precision according to the model evaluation index, wherein the model evaluation index calculation formula is as follows:
wherein x isiIs a sample point, which is the model input, and represents the data information of the working condition environment parameter, N (x)iμ, σ) is a model output, and is a probability value calculated from a probability density function of the Gaussian distribution, yiAs a condition parameter xiActual probability value of (d);
preferably, when Q (x)i) Judging whether the working condition environment parameters meet a Gaussian distribution model or not;when Q (x)i)>Theta, judging that the working condition parameters do not accord with a Gaussian distribution model; wherein x isiIs a working condition environment parameter, and theta is a precision threshold; the preferable range of θ is 0 to μ.
4) Distributing different influence factor coefficients for different parameters according to the influence of different parameters of the working condition environment conforming to the Gaussian distribution model on equipment operation control;
5) calculating a mixed Gaussian distribution function f (X) according to the influence factors of the working condition environment parameters conforming to the Gaussian distribution model and the Gaussian distribution model coefficientn) Wherein X isnWorking condition environment parameter samples conforming to a Gaussian distribution model;
step S204, constructing a piecewise function
Constructing a piecewise function g (X) according to data information of working condition environment parameters not conforming to the Gaussian distribution modelb) The expression is
Wherein, XbIs a working condition environment parameter sample, x 'not conforming to a Gaussian distribution model'lIs the current data information value x of the ith working condition environment parameter not conforming to the Gaussian distribution modelljSegment boundary value g of the I < th > working condition environment parameter not conforming to the Gaussian distribution modeljIs the function value of the piecewise function.
And step 205, controlling the equipment to operate according to the Gaussian mixture distribution function and the piecewise function.
1) Selecting an adjustable parameter index of the equipment operation key, and recording the parameter index as an equipment parameter Y;
2) constructing the relation between the equipment parameter Y and the working condition environment parameter Gaussian mixture distribution probability and the piecewise function, wherein the expression is
Where m is the number of segments of the piecewise function, Xn' Current data as operating condition parameters conforming to Gaussian distributionInformation value, X'bCurrent data information value, f, of a condition parameter not conforming to a Gaussian distributionjFor each boundary value, gjFor each segment of the piecewise function value, YmaxFor an upper limit value of the range in which a plant parameter can be adjusted during operation of the plant, YminFor the lower limit of the adjustable range of the equipment parameter, YjSetting an operation parameter value for each stage;
preferably, Y isjThe calculation formula of (A) is as follows;
Yj＝λfYf+λgYg(6)
wherein λ isf、λgFor different types of operating-condition environmental parameter weights, λf+λg＝1，YfIn order to meet the relation function of the working condition environment parameter and the equipment parameter of the Gaussian distribution model,
(Ymax-Ymin)+Ymin，Ygas a function of the relationship between the environmental parameters and the plant parameters for the conditions not conforming to the Gaussian distribution model, Yg＝g(Xb)*(Ymax-Ymin)+Ymin
3) Calculating to obtain an equipment parameter Y (X') according to the formula (5) and the data information of the current working condition environment parameter of the equipment operation;
4) the regulating equipment operates according to the equipment parameter Y (X') obtained by calculation
Step S206, inputting training data by taking the current working condition environment parameters and the historical working condition environment parameters as models, calculating a Gaussian distribution model coefficient of each working condition environment parameter according to a nonlinear least square method to obtain a probability density function formula of Gaussian distribution, updating a mixed Gaussian distribution function coefficient, and improving control accuracy; and updating the piecewise function according to the data information.
Step S207, setting the time period T for updating the coefficient of the Gaussian distribution function according to the using state of the equipment1Preferably said time period T1Is in the range of 0.5h-24h, and sets the time period T for adjusting the equipment parameters2Preferably said time period T2In the range of 0.5h-72h。
According to the technical scheme, the problem of accurate control of equipment operation control is solved, the equipment operation state is adjusted according to the real-time working condition environment, the optimization operation of the equipment relative working condition environment is achieved, and the problem of accurate control of the equipment operation is solved.
EXAMPLE III
The present embodiment may provide a preferred example based on the above-mentioned embodiment, so as to realize the operation control of the blower of the sewage treatment plant.
Step S301, data acquisition and processing
The data information of the working condition environmental parameters related to the equipment operation is acquired in real time through remote interaction with the instrument and meter, and is acquired and transmitted to the server at the first time.
Preferably, the data information acquisition interval is 1 min.
And carrying out primary filtering processing on the acquired data to remove abnormal data.
Preferably, the working condition environmental parameter indexes selected in the embodiment are the influent COD amount and the influent ammonia nitrogen amount of the sewage treatment plant.
And step S302, establishing a mixed Gaussian model.
1) Establishing a Gaussian distribution model
The mixed Gaussian distribution model is a linear combination of a plurality of Gaussian distributions, and the probability density function expression of the Gaussian distribution of the COD (chemical oxygen demand) of the inlet water is shown as a formula (7)
The probability density function expression of the Gaussian distribution of the ammonia nitrogen amount of the inlet water is
Wherein, CCODFor water inlet COD data sample point, CNHIs a water inlet ammonia nitrogen amount data sample point, mu1、μ2Is the average value of the water inlet COD data and the water inlet ammonia nitrogen dataMean value, σ1 2、σ2 2The water inlet COD amount and the water inlet ammonia nitrogen amount data variance are obtained;
2) establishing a mixed Gaussian distribution model
The Gaussian mixture distribution model is a linear combination of a plurality of Gaussian distributions, and the probability density function of the Gaussian mixture distribution is expressed as
Wherein, XCOD,XNHIs a water inlet COD amount and a water inlet ammonia nitrogen amount data sample, a1、a2The weight of the Gaussian distribution of the COD amount of the inlet water and the ammonia nitrogen amount of the inlet water is shown.
And step S303, calculating a mixed Gaussian distribution model coefficient based on a nonlinear least square method to obtain a mixed Gaussian distribution function.
1) According to the COD amount of the inlet water and the historical data information of the ammonia nitrogen amount of the inlet water, the historical data information is used as input training data;
2) calculating a Gaussian distribution model coefficient of each intake water COD amount and the intake water ammonia nitrogen amount according to a nonlinear least square method to obtain a probability density function formula of Gaussian distribution;
wherein the probability density function of the intake water COD amount Gaussian distribution is
The probability density function of the Gaussian distribution of the ammonia nitrogen amount of the inlet water is
3) Distributing different influence factor coefficients for different parameters according to the influence of different parameters of the working condition environment on the operation control of the equipment;
wherein, a1＝1、a2＝-0.1
4) And calculating a mixed Gaussian distribution model coefficient according to the probability density function expression of Gaussian distribution of different parameters of the working condition environment and the influence factor coefficients of the different working condition environment parameters to obtain a mixed Gaussian distribution function.
And step S304, controlling the equipment to operate according to the Gaussian mixture distribution function.
1) Selecting an adjustable parameter index of the equipment operation key, and recording the parameter index as an equipment parameter Y;
preferably, in the embodiment, the blower frequency is selected as a key controllable parameter index of the equipment;
2) constructing the relation between the equipment parameter Y and the Gaussian mixture distribution probability of the working condition environmental parameter, wherein the expression is
Wherein X' is data information of the current working condition environmental parameter of equipment operation, and YmaxFor an upper limit value of the range in which a plant parameter can be adjusted during operation of the plant, YminThe lower limit value of the adjustable range of the equipment parameters is f (X), and a Gaussian distribution function is mixed with the working condition parameters;
preferably, Y in the present embodimentmax＝50Hz，Ymin＝30Hz；
3) Acquiring a data information value of the current working condition environmental parameter through data acquisition equipment, wherein the water inlet COD (chemical oxygen demand) amount is 230g/h, and the water inlet ammonia nitrogen amount is 20g/h, namely the current working condition environmental parameter data is X' ═ 230, 20;
4) calculating to obtain an equipment parameter Y (X ') according to the formula (13) and data information X' (230,20) of the current working condition environment parameter of the equipment operation;
5) the blower is controlled to operate at Y (X'), i.e., 40 Hz.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (9)
1. The equipment operation control method based on Gaussian distribution is characterized by comprising the following steps:
acquiring data information of working condition environmental parameters related to equipment operation through a data acquisition device;
establishing a mixed Gaussian distribution model;
calculating a mixed Gaussian distribution model coefficient based on a nonlinear least square method to obtain a mixed Gaussian distribution function;
controlling the equipment to operate according to the Gaussian mixture distribution function;
updating a Gaussian mixture distribution function;
wherein the controlling the device to operate according to the Gaussian mixture distribution function comprises:
selecting an adjustable parameter index of the equipment operation key, and recording the parameter index as an equipment parameter Y;
constructing a first relation between the equipment parameter Y and the Gaussian mixture distribution probability of the working condition environment parameter, wherein the expression is as follows:
wherein X' is data information of the current working condition environmental parameter of equipment operation, and YmaxFor an upper limit value of the range in which a plant parameter can be adjusted during operation of the plant, YminThe lower limit value of the adjustable range of the equipment parameters is f (X), and a Gaussian distribution function is mixed with the working condition parameters;
calculating to obtain an equipment parameter Y (X') according to the first relation and the data information of the current working condition environment parameter of the equipment operation;
and the regulating equipment operates according to the equipment parameter Y (X') obtained by calculation.
2. The Gaussian distribution-based equipment operation control method according to claim 1, wherein the acquiring of the data information of the working condition environmental parameters related to the equipment operation by the data acquisition equipment comprises:
the data information of the working condition environmental parameters related to the equipment operation is acquired in real time through remote interaction with the instrument.
3. The gaussian-based distribution plant operation control method according to claim 1, wherein the establishing of the mixed gaussian distribution model comprises:
the Gaussian mixture model is a linear combination of a plurality of Gaussian distributions, and the probability density function expression of the Gaussian distributions is as follows:
where x is the sample point, μiIs the sample mean, σi 2Is the sample variance;
the Gaussian mixture distribution probability density function is expressed as:
wherein X is a total sample, aiInfluence factor of Gaussian distribution, μ, as the i-th indexiIs the mean of the gaussian distribution of the ith index,
the variance of the i-th index gaussian distribution, k is the number of gaussian distributions, and when k is 1, the mixed gaussian distribution model f (x) ═ N (μ σ) is a probability density function of one-dimensional gaussian distribution.
4. The gaussian-based distribution equipment operation control method according to claim 1, wherein the calculating a mixture gaussian distribution model coefficient based on a nonlinear least squares method to obtain a mixture gaussian distribution function comprises:
recording X as input training data according to the data information of the working condition environment parameters;
calculating a Gaussian distribution model coefficient of each working condition environment parameter according to a nonlinear least square method to obtain a probability density function of Gaussian distribution;
and calculating the model precision according to the model evaluation index, wherein the model evaluation index calculation formula is as follows:
Q＝∑[yj-N(xj，μ，σ)]2
wherein x isjAs model input, data information of the environmental parameters of the working conditions, N (x)jμ σ) is a model output, and is a probability value calculated from a probability density function of the gaussian distribution, yjAs a condition parameter xjActual probability value of (d);
distributing different influence factor coefficients for different parameters according to the influence of different parameters of the working condition environment on the operation control of the equipment;
and calculating a mixed Gaussian distribution model coefficient according to the probability density function expression of Gaussian distribution of different parameters of the working condition environment and the influence factor coefficients of the different working condition environment parameters to obtain a mixed Gaussian distribution function.
5. The gaussian-distribution-based plant operation control method according to claim 1, further comprising: and when the parameters which do not follow the Gaussian distribution exist in the working condition environment parameters, constructing a piecewise function, and controlling the equipment to operate according to the piecewise function and the mixed Gaussian distribution function.
6. The Gaussian distribution based equipment operation control method according to claim 5, characterized by comprising:
calculating a Gaussian distribution model coefficient by using a nonlinear least square method according to data information of the working condition environment parameters;
calculating the Gaussian model precision Q (x) according to the model evaluation indexi) When Q (x)i) Theta or less, judging that the working condition environment parameters accord with the Gaussian distribution model, and recording the working condition environment parameter sample as Xn(ii) a When Q (x)i) If theta is larger than theta, the working condition parameters are judged to be not accordant with the Gaussian distribution model, and the working condition environment parameter sample is recorded as Xb(ii) a Wherein x isiIs the ith working condition environment parameter, and theta is the precision threshold;
calculating a mixed Gaussian distribution function f (X) according to the influence factor of the working condition environment parameters conforming to the Gaussian distribution model and the coefficient of the Gaussian distribution modeln)；
Constructing a piecewise function g (X) according to data information of working condition environment parameters not conforming to the Gaussian distribution modelb)；
Selecting an adjustable parameter index of the equipment operation key, and recording the parameter index as an equipment parameter Y;
constructing a second relation between the equipment parameter Y and the working condition environment parameter Gaussian mixture distribution probability and the piecewise function, wherein the expression is as follows:
where m is the number of segments of the piecewise function, Xn' Current data information value, X ' of operating condition parameter conforming to Gaussian distribution 'bCurrent data information value, f, of a condition parameter not conforming to a Gaussian distributionjFor each boundary value, gjFor each segment of the piecewise function value, YmaxFor an upper limit value of the range in which a plant parameter can be adjusted during operation of the plant, YminFor the lower limit of the adjustable range of the equipment parameter, YjSetting an operation parameter value for each stage;
calculating to obtain an equipment parameter Y (X') according to the second relation and the data information of the current working condition environment parameter of the equipment operation;
and the regulating equipment operates according to the equipment parameter Y (X') obtained by calculation.
7. The Gaussian distribution based plant operation control method according to claim 5 or 6, characterized by comprising:
value of operating parameter Y of equipment at each stagejThe calculation formula of (2) is as follows:
Yj＝λfYf+λgYg
wherein λ isf、λgFor different types of operating conditions and environmental parameter weights, YfAs a function of the relation between the environmental parameters and the plant parameters in accordance with the Gaussian distribution model, YgThe relation function of the working condition environment parameter and the equipment parameter which are not in accordance with the Gaussian distribution model.
8. The Gaussian distribution based equipment operation control method according to claim 6, characterized by comprising:
and (4) according to the current working condition environment parameters and the historical working condition environment parameters as model input training data, calculating the probability density function coefficient of Gaussian distribution, the mixed Gaussian distribution model coefficient and the piecewise function again, and updating the mixed Gaussian distribution function and the piecewise function.
9. The gaussian-distribution-based plant operation control method according to claim 1, comprising:
and setting the time period for adjusting the equipment parameters according to the equipment use state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611191551.6A CN106773692B (en) | 2016-12-21 | 2016-12-21 | Equipment operation control method based on Gaussian distribution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611191551.6A CN106773692B (en) | 2016-12-21 | 2016-12-21 | Equipment operation control method based on Gaussian distribution |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106773692A CN106773692A (en) | 2017-05-31 |
| CN106773692B true CN106773692B (en) | 2020-04-28 |
Family
ID=58893567
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611191551.6A Active CN106773692B (en) | 2016-12-21 | 2016-12-21 | Equipment operation control method based on Gaussian distribution |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106773692B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110531656A (en) * | 2019-08-13 | 2019-12-03 | 大唐水电科学技术研究院有限公司 | A kind of monitoring system and method for Hydropower Unit performance |
| CN111652445B (en) * | 2020-06-11 | 2024-03-22 | 广东科创智水科技有限公司 | Sewage equipment optimizing operation control method based on Gaussian distribution |
| CN112097272A (en) * | 2020-08-14 | 2020-12-18 | 杭州科晟能源技术有限公司 | Automatic feeding control method and system for waste incineration feeding |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050053270A1 (en) * | 2003-09-05 | 2005-03-10 | Konica Minolta Medical & Graphic, Inc. | Image processing apparatus and signal processing apparatus |
| JP2007052166A (en) * | 2005-08-17 | 2007-03-01 | Advanced Telecommunication Research Institute International | Method for preparing acoustic model and automatic speech recognizer |
| US20100300985A1 (en) * | 2009-02-24 | 2010-12-02 | Aquifier Maintenance & Performance Systems, Inc | System and Methods for Treatment of Water Systems |
| CN103793604A (en) * | 2014-01-25 | 2014-05-14 | 华南理工大学 | Sewage treatment soft measuring method based on RVM |
| CN104091592B (en) * | 2014-07-02 | 2017-11-14 | 常州工学院 | A kind of speech conversion system based on hidden Gaussian random field |
| CN104464744A (en) * | 2014-11-19 | 2015-03-25 | 河海大学常州校区 | Cluster voice transforming method and system based on mixture Gaussian random process |
| CN104462850A (en) * | 2014-12-25 | 2015-03-25 | 江南大学 | Multi-stage batch process soft measurement method based on fuzzy gauss hybrid model |
| CN105930652B (en) * | 2016-04-19 | 2019-03-01 | 北京金控数据技术股份有限公司 | A kind of running quality detection method and device |
| CN106021924B (en) * | 2016-05-19 | 2019-01-18 | 华南理工大学 | Sewage online soft sensor method based on more attribute gaussian kernel function fast correlation vector machines |
-
2016
- 2016-12-21 CN CN201611191551.6A patent/CN106773692B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106773692A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106773692B (en) | Equipment operation control method based on Gaussian distribution | |
| JP5696171B2 (en) | Control parameter adjustment method, control parameter adjustment system, and control parameter setting device | |
| CN107609278B (en) | Method for improving accuracy of thermal power plant noise prediction model | |
| CN107026763B (en) | A kind of data communication network method for predicting decomposed based on flow | |
| CN111320246B (en) | Coagulant intelligent accurate adding control system based on multivariable control | |
| CN106251242B (en) | Wind power output interval combination prediction method | |
| CN106200381B (en) | A method of according to the operation of processing water control by stages water factory | |
| CN113325702B (en) | Aeration control method and device | |
| CN108363295A (en) | Fired power generating unit AGC Performance Assessment indexs based on System Discrimination calculate and prediction technique | |
| CN111695290A (en) | Short-term runoff intelligent forecasting hybrid model method suitable for variable environment | |
| CN104931040A (en) | Installation and debugging method of Beidou generation-II navigation system electric iron tower deformation monitoring device based on machine learning | |
| CN108490154A (en) | Mixing based on principal component analysis and online extreme learning machine sorts the concentrate grade flexible measurement method and system of system | |
| Hua et al. | Prediction method for network traffic based on maximum correntropy criterion | |
| CN107679657A (en) | Water quality prediction method for mineral spring | |
| Gao et al. | Design of PID controller for greenhouse temperature based on Kalman | |
| CN111695730B (en) | Vertical mill vibration prediction method and device based on ARIMA and RNN | |
| Zakharov et al. | Analysis of stationary means of measurement filters with optimum sensitivity | |
| CN105870919B (en) | A kind of method for evaluating AGC unit ancillary service efficiency | |
| EP3333802B1 (en) | Method and system for quantifying greenhouse gases emissions produced in a wastewater treatment plant and method of multivariable control for optimizing the operation of such plants | |
| CA3109182C (en) | Static gain estimation method for dynamic system based on historical data ramp responses | |
| CN109409666B (en) | Environmental impact assessment method based on atmospheric diffusion model and linear programming | |
| CN117469603B (en) | Multi-water-plant water supply system pressure optimal control method based on big data learning | |
| CN114781249A (en) | High-density clarification tank dosage prediction and control method based on multidimensional scoring model | |
| WO2020034248A1 (en) | Modelling cloud platform for rapid evaluation of crude oil based on nuclear magnetic resonance analyser | |
| CN109451522A (en) | A kind of method for predicting and device towards Bluetooth gateway |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |