CN114896825B - Intelligent control method for building energy-saving water supply and drainage system - Google Patents
Intelligent control method for building energy-saving water supply and drainage system Download PDFInfo
- Publication number
- CN114896825B CN114896825B CN202210818029.5A CN202210818029A CN114896825B CN 114896825 B CN114896825 B CN 114896825B CN 202210818029 A CN202210818029 A CN 202210818029A CN 114896825 B CN114896825 B CN 114896825B
- Authority
- CN
- China
- Prior art keywords
- independent
- abnormal
- drainage pump
- value
- trend
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The invention relates to the technical field of intelligent control, in particular to an intelligent control method for a building energy-saving water supply and drainage system. The method comprises the steps of firstly, obtaining a common factor matrix and an independent factor vector of each drainage pump based on a multi-section vibration sequence of each drainage pump; constructing a public scatter diagram and an independent scatter diagram, calculating corresponding abnormal degrees according to scatter point distribution conditions in the public scatter diagram and the independent scatter diagram, and screening out an abnormal drainage pump and a normal drainage pump based on the abnormal degrees; stopping the work of the abnormal drainage pump; and distributing the power of the abnormal drainage pump according to the proportion of the abnormal degree of each normal drainage pump to obtain the extra boost power of each normal drainage pump. According to the embodiment of the invention, the abnormal degree of the drainage pump is obtained through the common factor and the independent factor of the vibration sequence of the molecular drainage pump, and the aim of intelligently controlling the working power of the drainage pump in a drainage system is further realized according to the abnormal degree.
Description
Technical Field
The invention relates to the technical field of intelligent control, in particular to an intelligent control method for a building energy-saving water supply and drainage system.
Background
The building water supply and drainage system is used for removing sewage in residential buildings, public buildings and production buildings. The drainage system inside a building generally consists of a water receiver, a drainage pipeline, a dredging facility, an air duct, a sewage and wastewater lifting device and a local treatment structure of sanitary ware or production equipment. In the building water supply and drainage system, the drainage pump has irreplaceable effect, and the reasonable control drainage pump in the building water supply and drainage system can provide guarantee for the stable operation of the building water supply and drainage system, and when the drainage pump appears abnormally, the drainage pump appears as vibration abnormity.
At present, a common method for detecting an abnormal condition of a drain pump and controlling the drain pump comprises the following steps: and judging whether the drainage pump works abnormally or not by detecting the change of the vibration data of each drainage pump and the vibration data of the normal drainage pump. The abnormal vibration is obvious because the vibration exists in the drainage pump originally when the drainage pump works, namely the abnormal vibration is serious, the abnormity of the drainage pump can be judged only by detecting the vibration data of the drainage pump; however, when the drain pump is slightly abnormal, the abnormal vibration is not obvious, and it is difficult to distinguish the abnormality of the drain pump only by comparing with the vibration data of the normal drain pump.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an intelligent control method for a building energy-saving water supply and drainage system, which adopts the following technical scheme:
acquiring a vibration sequence of the drainage pump; based on the multi-section vibration sequence of each drainage pump, obtaining a public factor matrix and an independent factor vector of each drainage pump by using a factor analysis method;
constructing a public scatter diagram, wherein one point in the public scatter diagram corresponds to a public factor matrix; acquiring the maximum public principal component direction of a point in each fixed segment on the public scatter diagram; the ratio of the direction value of the maximum public principal component direction to the direction value of the preset principal component direction is a public trend value; constructing an independent scatter diagram, and acquiring a corresponding independent trend value;
acquiring the ratio of the direction value of the principal component direction of the public tendency value to the direction value of a preset principal component direction as a public tendency direction change value; taking the product of the average value of a plurality of common trend values and the common trend direction change value as a first probability; acquiring a second probability corresponding to the independent trend value; selecting the larger value of the first probability and the second probability as an abnormal probability;
matching the independent factor vectors of the current section of the drainage pumps with the independent factor vectors of the previous section to obtain current matching, wherein the difference between the current matching and the standard matching is used as the integral state variation; taking the product of the abnormal probability and the integral state variation as an abnormal degree, and screening out an abnormal drainage pump and a normal drainage pump based on the abnormal degree;
stopping the operation of the abnormal drainage pump; and distributing the power of the abnormal drainage pump according to the proportion of the abnormal degree of each normal drainage pump to obtain the extra boost power of each normal drainage pump.
Preferably, the constructing an independent scatter diagram and acquiring corresponding independent trend values includes:
constructing an independent scatter diagram, wherein one point in the independent scatter diagram corresponds to one independent factor vector; acquiring the maximum independent principal component direction of a point in each fixed segment on the independent scatter diagram; and the ratio of the direction value of the maximum independent principal component direction to the direction value of the preset principal component direction is an independent trend value.
Preferably, the method for acquiring the principal component direction of the common trend value includes:
constructing a public trend scatter diagram according to the public trend values, wherein one point in the public trend scatter diagram corresponds to one public trend value; and the principal component directions corresponding to all the points in the public trend scatter diagram are the principal component directions of the public trend values.
Preferably, the obtaining of the second probability corresponding to the independent trend value includes:
acquiring the ratio of the principal component direction of the independent trend value to the direction value of a preset principal component direction as an independent trend direction change value; and taking the product of the average value of the independent trend values and the independent trend direction change value as a second probability.
Preferably, the method for acquiring the principal component direction of the independent trend value includes:
constructing an independent trend scatter diagram according to the independent trend values, wherein one point in the independent trend scatter diagram corresponds to one independent trend value; and the principal component directions corresponding to all the points in the independent trend scatter diagram are the principal component directions of the independent trend values.
Preferably, the matching the independent factor vectors of the current segment of the drainage pumps with the independent factor vectors of the previous segment to obtain the current match, and taking the difference between the current match and the standard match as the overall state variation includes:
the elements in the independent factor vector of the current segment are arranged in an ascending order, and each element is marked with a label; taking the reciprocal of the difference value of the elements in the independent factor vector as an edge weight value; matching elements in two independent factor vectors of a current segment and an adjacent previous segment to obtain a current match;
calculating the difference value of the labels of the two matched elements based on the current matching, and acquiring the sum of a plurality of difference values as the current difference value sum; acquiring a standard difference sum when the standards are matched; and the ratio of the current difference sum to the standard difference sum is the overall state variation.
Preferably, the screening of the abnormal drain pump and the normal drain pump based on the abnormal degree includes:
taking the drainage pump with the abnormal degree larger than a preset abnormal threshold value as an abnormal drainage pump; and taking the drainage pump with the abnormal degree smaller than or equal to a preset abnormal threshold value as a normal drainage pump.
Preferably, the distributing the power of the abnormal drain pump according to the percentage of the abnormal degree of each normal drain pump to obtain the extra boost power of each normal drain pump includes:
acquiring the abnormal degree of each normal drainage pump; marking the abnormal degrees in a descending order; sequencing the corresponding normal drainage pumps and marking labels according to the sequence of the abnormal degrees from small to large; taking the abnormal degree with the same label as the normal drainage pump as the corresponding regulation coefficient of the drainage pump;
acquiring the power of the abnormal drainage pump as abnormal power; and taking the product of the regulating coefficient and the abnormal power as the additional boosting power of the corresponding normal drainage pump.
The embodiment of the invention at least has the following beneficial effects:
the embodiment of the invention relates to the technical field of intelligent control, and the method comprises the following steps of firstly, obtaining a public factor matrix and an independent factor vector of each drainage pump based on a multi-section vibration sequence of each drainage pump; constructing a public scatter diagram and an independent scatter diagram, calculating corresponding abnormal degree according to scatter distribution conditions in the public scatter diagram and the independent scatter diagram, and performing overall analysis on the working state and independent parameters of the drainage pumps working simultaneously and performing respective analysis by combining the independent state of the drainage pump, so that the drainage pump can be detected in time when slight abnormality exists in the drainage pump; screening out an abnormal draining pump and a normal draining pump based on the abnormal degree; stopping the work of the abnormal drainage pump; and distributing the power of the abnormal drainage pumps according to the proportion of the abnormal degree of each normal drainage pump to obtain the extra boosting power of each normal drainage pump. According to the embodiment of the invention, the abnormal degree of the drainage pump is obtained through the common factor and the independent factor of the vibration sequence of the molecular drainage pump, and the aim of intelligently controlling the working power of the drainage pump in a drainage system is further realized according to the abnormal degree.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a method for intelligently controlling a building energy-saving water supply and drainage system according to an embodiment of the present invention.
Detailed Description
In order to further explain the technical means and effects of the present invention adopted to achieve the predetermined invention purpose, the following describes the method for intelligently controlling the building energy saving water supply and drainage system according to the present invention in detail with reference to the accompanying drawings and preferred embodiments, and the specific implementation, structure, features and effects thereof are described in detail as follows. In the following description, the different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The embodiment of the invention provides a concrete implementation method of an intelligent control method of a building energy-saving water supply and drainage system, which is suitable for a control scene of the building water supply and drainage system. And each drainage pump in the drainage system in the scene is provided with a corresponding vibration sensor for acquiring vibration data of the drainage pump. The problem that when the drainage pump is slightly abnormal and abnormal vibration is not obvious is solved, the abnormal situation of the drainage pump is difficult to judge by detecting the change of the vibration data of the drainage pump and the vibration data of a normal drainage pump. The embodiment of the invention. According to the embodiment of the invention, the abnormal degree of the drainage pump is obtained through the common factor and the independent factor of the vibration sequence of the molecular drainage pump, and the aim of intelligently controlling the working power of the drainage pump in a drainage system is further fulfilled according to the abnormal degree.
The concrete scheme of the intelligent control method for the building energy-saving water supply and drainage system provided by the invention is specifically described below by combining the attached drawings.
Referring to fig. 1, a flow chart of steps of an intelligent control method for a building energy-saving water supply and drainage system according to an embodiment of the present invention is shown, where the method includes the following steps:
step S100, acquiring a vibration sequence of the drainage pump; and obtaining a common factor matrix and an independent factor vector of each drainage pump by using a factor analysis method based on the multi-section vibration sequence of each drainage pump.
When the drainage pump is abnormal, the abnormal drainage pump is usually represented as vibration abnormity, vibration data can be obtained through the vibration sensor, and the abnormal drainage pump can be obtained through analyzing the vibration data. There are many causes for the abnormality of the drain pump, for example: the inlet and outlet pipelines are blocked, the flow impeller is blocked, and the motor of the drainage pump is heated.
The vibration data of the drain pump is cycle data. When the motor drives the impeller to rotate, the pump shell is filled with water, the liquid rotates at a high speed under the action of the impeller, and each time the impeller rotates for one period, the time sequence data of one vibration period corresponds to. Namely, the vibration sensor is used for acquiring the vibration sequence of the drainage pump.
The same water collecting tank is provided with a plurality of drainage pumps frequently, different drainage pumps are used in work, the generated suction force to water can influence other drainage pumps to cause vibration, the drainage pumps also have vibration in normal work, vibration caused by slight abnormality is difficult to recognize under the influence of various factors, and the abnormal drainage pumps cannot be precisely controlled. The existing method is to analyze the vibration sequence of a single drainage pump, often only can detect the single drainage pump when the abnormity of the single drainage pump is serious, the detection sensitivity and the detection real-time performance are low, when the abnormity of the drainage pump is detected, the drainage control is carried out at the moment, the drainage pump is often damaged greatly, the service life of the drainage pump is further shortened, and the expected drainage control purpose cannot be achieved. The invention can detect the abnormal condition of the drainage pump in time when the abnormal condition of the drainage pump is not serious, namely the abnormal condition is slight, thereby improving the detection sensitivity and further realizing the intelligent control of the drainage system.
The overall aspect, i.e. all the drain pumps are considered as one entity. Considering that the same working principle exists when different drainage pumps work, the same characteristics inevitably exist, meanwhile, different drainage pumps cannot be completely the same, different characteristics also exist, but the different characteristics are smaller, and the same characteristics exist in the same working state. Meanwhile, when different drainage pumps work, the higher probability is that one or more of the drainage pumps are abnormal, and the probability that all the drainage pumps are abnormal is lower. When the drainage pump is abnormal, the corresponding element in the independent factor vector is changed greatly, and the corresponding element in the independent factor vector corresponding to the drainage pump in a normal state is changed slightly.
The individual aspects, i.e. a drain pump as an individual, are considered from a drain pump aspect. When a drain pump is previously in a normal operating condition and thereafter experiences an abnormal condition due to clogging or other problems, the abnormal condition may be more severe if the operating parameters of the drain pump are not controlled. The common factors at different periods in the corresponding factor analysis process are reduced, and the independent factors are increased. The same factors, namely common factors, must exist in the factors due to different periods of the same drainage pump, and the different factors, namely corresponding independent factors, exist in different periods due to abnormal state changes. After the abnormity is generated, the common factors of the same drainage pump in different periods are reduced, and the independent factors are increased.
Considering the two aspects, when a certain drainage pump is slightly abnormal, on one hand, the change trends of factors of the drainage pump in different periods are consistent, namely, the common factor is reduced, and the independent factor is increased; on the other hand the other drain pumps have smaller factor variations.
The method comprises the steps of firstly calculating the period of vibration data in a normal state, dividing the period into stages, and then calculating the change condition of each stage for the actual vibration data, wherein the vibration data is externally represented as a data sequence of periodic change.
Wherein, drain pump theory of operation does: when the motor drives the impeller to rotate, the pump shell is filled with water, and the liquid rotates at a high speed under the action of the impeller. The centrifugal force increases the pressure of the liquid at the outer edge of the impeller, and the pressure is used to drive the water to the water pipe. Meanwhile, the liquid pressure at the center of the impeller is reduced to form vacuum, and water comes from the water suction pipe pool, so that the centrifugal water pump continuously sucks and presses the water out to achieve the aim of draining. In this process, if the drainage pump is in a normal working state, each time the impeller rotates one cycle, a period is corresponded. The period can be obtained by fourier transformation, a technique well known to those skilled in the art.
And after the period of each drainage pump is obtained, dividing the actual vibration data of each drainage pump into different stage data according to the corresponding period. The method for acquiring the common factor matrix and the independent factor vector corresponding to the vibration data of the drainage pump A comprises the following steps: the actual vibration data of the drainage pump are periodically divided to obtain different stage data, and a corresponding public factor matrix and an independent factor vector are calculated for each stage data by a factor analysis method.
Obtaining the abnormal probability of each drain pump according to the historical data factor analysis result and the actual data factor analysis result of each drain pump, and firstly, obtaining the abnormal probability of each drain pump according to the vibration periodicity of each drain pump and the vibration data factor analysis result of each drain pump. Therefore, a common factor matrix and an independent factor vector of each drainage pump are obtained by using a factor analysis method.
Step S200, constructing a public scatter diagram, wherein one point in the public scatter diagram corresponds to a public factor matrix; acquiring the maximum public principal component direction of a point in each fixed segment on a public scatter diagram; the ratio of the direction value of the maximum public principal component direction to the direction value of the preset principal component direction is a public trend value; and constructing an independent scatter diagram and acquiring a corresponding independent trend value.
The public factor matrixes of different stages form a one-dimensional vector in time, each element in the one-dimensional vector is a public factor matrix of different stages, and the vector is called as a public factor matrix vector; the independent factor vectors in different stages are also combined into a one-dimensional vector in time, each element in the vector is the independent factor vector in different stages, and the one-dimensional vector in time formed by the independent factor vectors in different stages is called as an independent factor time vector.
When the drainage pump is abnormal, along the time line, the information quantity of the common factor matrix vector is reduced, and the information quantity of the independent factor time vector is increased, so that the abnormal probability of the current drainage pump can be obtained only by calculating the change trends of the common factor matrix vector and the independent factor time vector in the current time period.
Calculating the direction change of the public trend of the public factor matrix vector, specifically: the fixed segment is set to be 10 in the embodiment of the invention, namely, the vibration data of each 10 stages corresponds to one common factor matrix vector, and the value can be adjusted by an implementer according to the actual situation in other embodiments. Namely, the common factor matrix vector of the current stage is obtained from the current stage to 10 stages in the past.
And constructing a public scatter diagram based on the public factor matrix, wherein one point in the public scatter diagram corresponds to one public factor matrix, the abscissa of the public scatter diagram is the serial number of the public factor matrix, and the ordinate of the public scatter diagram is the entropy of the corresponding public factor matrix.
Coordinates of all points on the public scatter diagram are obtained, principal component directions of the data are obtained by using a PCA algorithm, k principal component directions can be obtained, each principal component direction is a 2-dimensional unit vector, and each principal component direction corresponds to a characteristic value. And acquiring the principal component direction with the largest characteristic value, namely the maximum common principal component direction of the scattered point data, and expressing the direction with the largest projection direction of the data, namely the main distribution direction of the data. It should be noted that, a point in each fixed segment on the common scattergram constitutes a maximum common principal component direction, that is, every 10 points on the common scattergram constitutes a maximum common principal component direction.
Obtaining the maximum public principal component direction corresponding to each fixed segment on the public scatter diagram, wherein when the maximum public principal component direction is in the first quadrant of the coordinate system, the range of the angle value is [0 degrees and 90 degrees ], and the corresponding public factor matrix vector does not carry the information of abnormal operation of the drainage pump, namely the corresponding drainage pump does not have abnormality; and when the direction of the maximum public principal component is in the fourth quadrant of the coordinate system, and the range of the angle value is [ -90 degrees, 0 degrees ], reflecting that the corresponding public factor matrix vector carries the information of the abnormal work of the drainage pump, namely that the corresponding drainage pump is abnormal.
And only calculating the public trend value of the abnormal drainage pump, namely, the ratio of the direction value of the maximum public principal component direction corresponding to the drainage pump with the abnormality to the direction value of the preset principal component direction is the public trend value. In the embodiment of the present invention, the direction value of the principal component direction is preset to be 90, and in other embodiments, the value may be adjusted by an implementer according to an actual situation. It should be noted that in the embodiments of the present invention, all direction values of the mentioned directions are angle values between the direction and the horizontal line.
The step of calculating the direction change of the independent trend of the independent factor time vector includes: the fixed segment is set to be 10 in the embodiment of the invention, namely, the vibration data of each 10 stages corresponds to an independent factor time vector, and the value can be adjusted by an implementer according to the actual situation in other embodiments. I.e. 10 stages from the current stage onwards back to the current stage, the independent factor time vector of the current stage is obtained.
And constructing an independent scatter diagram based on the independent factor vectors, wherein one point in the independent scatter diagram corresponds to one independent factor vector, the horizontal coordinate of the independent scatter diagram is the serial number of the independent factor vector, and the vertical coordinate of the independent scatter diagram is the entropy of the independent factor vector corresponding to the point.
And acquiring coordinates of all points on the independent scatter diagram, acquiring principal component directions of the data by using a PCA algorithm, and acquiring k principal component directions, wherein each principal component direction is a 2-dimensional unit vector and corresponds to a characteristic value. And acquiring the principal component direction with the largest characteristic value, namely the maximum independent principal component direction of the scattered point data, and expressing the direction with the largest projection direction of the data, namely the main distribution direction of the data. It should be noted that, a point in each fixed segment on the independent scattergram constitutes a maximum independent principal component direction, that is, every 10 points on the independent scattergram constitute a maximum independent principal component direction.
Obtaining the maximum independent principal component direction corresponding to each fixed segment on the independent scatter diagram, and when the maximum independent principal component direction is in the fourth quadrant of the coordinate system, the range of the angle value is [ -90 degrees, 0 degrees ], reflecting that the corresponding independent factor time vector does not carry the information that the drainage pump works abnormally, namely the corresponding drainage pump does not work abnormally; when the direction of the maximum independent principal component is in the first quadrant of the coordinate system, and the range of the angle value is [0 degrees, 90 degrees ], the corresponding independent factor time vector is reflected to carry the information of the abnormal work of the drainage pump, namely the corresponding drainage pump is abnormal.
And only calculating the independent trend value of the abnormal drainage pump, namely, the ratio of the direction value of the maximum independent principal component direction corresponding to the abnormal drainage pump to the direction value of the preset principal component direction is the independent trend value. In the embodiment of the present invention, the direction value of the principal component direction is preset to be 90 °, and in other embodiments, the value may be adjusted by an implementer according to an actual situation.
Step S300, acquiring the ratio of the direction value of the principal component direction of the public tendency value to the direction value of the preset principal component direction as the public tendency direction change value; taking the product of the average value of the plurality of common trend values and the common trend direction change value as a first probability; acquiring a second probability corresponding to the independent trend value; and selecting the larger value of the first probability and the second probability as the abnormal probability.
The larger the trend values of the common factor matrix vector and the independent factor time vector are, the larger the corresponding abnormal probability is, and the faster the change speed of the common factor matrix vector and the independent factor time vector along the direction of the trend values is, the larger the abnormal probability is.
After the abnormity is generated, the abnormity degree becomes more serious with the time extension, the trend value indicates the possibility of the abnormity in a certain period of time, the trend direction change is to judge whether the abnormity in the adjacent time period is larger, and if the abnormity is larger, the probability of the abnormity is high. The adjacent time period is a time period corresponding to the vector length, and 10 phases corresponding to time are taken as a vector length, namely a time period. The adjacent time period refers to a time period obtained by sliding a window with 1 step as a step size at the time represented by the step. It should be noted that the time period, that is, the set fixed segment, takes every 10 phases as a fixed segment, that is, takes every 10 phases as a time period.
If a trend value exists in a time period nearest to the current period, namely a trend value exists in an adjacent time period adjacent to the current time period, acquiring the trend value of the previous adjacent time period, and if the trend value exists, calculating the change speed of the trend value along the trend direction, wherein the faster the change speed, the larger the abnormal probability. The trend direction refers to the increasing trend of the corresponding trend value of the public factor matrix vector.
And for the public factor matrix, acquiring the ratio of the principal component direction of the corresponding public trend value and the direction value of the preset principal component direction as the public trend direction change value. The closer the direction value of the principal component direction of the common tendency value is to the preset principal component direction, the faster the common tendency changes, and the faster the abnormal deterioration speed of the corresponding drain pump. The method for acquiring the principal component direction of the public trend value comprises the following steps: and one fixed segment corresponds to one public trend value, a public trend scatter diagram is constructed by the plurality of public trend values, and one point in the public trend scatter diagram corresponds to one public trend value. And calculating the principal component directions of all points in the public trend scatter diagram through a PCA algorithm, wherein the principal component directions corresponding to all points in the public trend scatter diagram are the principal component directions of the public trend values.
And for the independent factor vector, acquiring the ratio of the principal component direction of the corresponding independent trend value to the direction value of the preset principal component direction as an independent trend direction change value. The closer the direction value of the principal component direction of the independent tendency value is to the preset principal component direction, the faster the independent tendency is changed, and the faster the abnormal deterioration speed of the corresponding drain pump is. The method for acquiring the principal component direction of the independent trend value comprises the following steps: and one fixed segment corresponds to one independent trend value, an independent trend scatter diagram is constructed by the independent trend values, and one independent trend scatter diagram corresponds to one independent trend value. And calculating the principal component directions of all points in the independent trend scatter diagram through a PCA algorithm, wherein the principal component directions corresponding to all points in the independent trend scatter diagram are the principal component directions of the independent trend values.
Further, the product of the mean value of the plurality of common trend values in the common trend scatter diagram and the common trend direction change value is used as a first probability, and the product of the mean value of the plurality of independent trend values in the independent trend scatter diagram and the independent trend direction change value is used as a second probability. And selecting the larger value of the first probability and the second probability as the abnormal probability.
S400, matching the independent factor vectors of the current section and the independent factor vectors of the previous section of the plurality of drainage pumps to obtain current matching, wherein the difference between the current matching and the standard matching is used as the overall state variation; and taking the product of the abnormal probability and the integral state variation as the abnormal degree, and screening the abnormal water discharge pump and the normal water discharge pump based on the abnormal degree.
And after the abnormal probability is calculated, calculating the variation of the integral state of the time period with the abnormality and the previous time period, and reflecting that the abnormal state exists in the drainage pump if the variation is large.
The integral method refers to that all the drainage pumps are regarded as a system, a small number of the drainage pumps are abnormal, most of the drainage pumps are normal, and the probability of the abnormality in the integral system is obtained by comparing the drainage pumps. Namely, the input data of the factor analysis is the characteristic value of the vibration sequence of different drainage pumps, and the clustering result variability of the independent factor elements of the current time period and the previous time period is calculated as the overall state variation, for example: the total number of the drainage pumps is 5, the clustering conditions of the original independent factor elements are the same, and if one drainage pump is abnormal, the clustering conditions of the independent factor elements in the front time period and the back time period can be changed.
And matching the independent factor vectors of the current section of the drainage pumps with the independent factor vectors of the previous section to obtain current matching, wherein the difference between the current matching and the standard matching is used as the integral state variation. The greater the difference of the current match to the standard match, the greater the corresponding overall state change amount. The method comprises the steps of obtaining the overall state variable quantity, specifically: and for the independent factor vector of the current section and the independent factor vector of the previous section, performing ascending arrangement on elements in the independent factor vector of the current section, labeling each element, taking the reciprocal of the difference value of the elements in the independent factor vector as an edge weight value, and matching the elements in the two independent factor vectors of the current section and the two adjacent independent factor vectors of the previous section to obtain the current matching.
Further, the difference between the current match and the standard match is calculated as the overall state change amount. Specifically, the method comprises the following steps: and calculating the difference value of the labels of the two matched elements based on the current matching, and acquiring the sum of the difference values as the current difference value sum. And acquiring a standard difference sum when the standards are matched, wherein the ratio of the current difference sum to the standard difference sum is the overall state variation. It should be noted that the standard matching is a matching mode when the sum of the differences is the maximum among all matches.
And calculating the product of the abnormal probability of each drainage pump and the overall state variation as the abnormal degree, and screening the abnormal drainage pump and the normal drainage pump based on the abnormal degree. Specifically, the method comprises the following steps: taking the drainage pump with the abnormal degree larger than a preset abnormal threshold value as an abnormal drainage pump; and taking the drainage pump with the abnormal degree less than or equal to the preset abnormal threshold value as a normal drainage pump. In the embodiment of the present invention, the preset abnormal threshold is 0.7, and in other embodiments, an implementer may adjust the value according to the actual situation.
Step S500, stopping the work of the abnormal drainage pump; and distributing the power of the abnormal drainage pump according to the proportion of the abnormal degree of each normal drainage pump to obtain the extra boost power of each normal drainage pump.
And after obtaining the abnormal drainage pump, further controlling the working power of the drainage pump in the drainage system. Firstly, the abnormal drainage pumps need to stop working, so that the abnormal serious abnormal drainage pumps caused by continuous working of the abnormal drainage pumps are avoided, and under the condition that the rated maximum power of other drainage pumps is not exceeded, the power of the abnormal drainage pumps is distributed according to the proportion of the abnormal degree of each normal drainage pump, and the extra boost power of each abnormal drainage pump is obtained. Specifically, the method comprises the following steps: the operation of the abnormal drainage pump is stopped. And acquiring the abnormal degree of each normal drainage pump, and marking the abnormal degrees of the normal drainage pumps according to the sequence from large to small. Further, according to the sequence of the abnormal degrees from small to large, the corresponding normal drainage pumps are sequenced and marked with labels, and the abnormal degree which is the same as the label of the normal drainage pump is used as the corresponding regulating coefficient of the drainage pump. And acquiring the power of the abnormal drainage pump as the abnormal power, and taking the product of the regulating coefficient and the abnormal power as the extra boosting power of the corresponding normal drainage pump. It should be noted that, when the original working power of the normal drainage pump plus the extra boost power is greater than the rated maximum power, the working power of the normal drainage pump is directly adjusted to the rated maximum power.
If there are 5 original drain pumps, the normal drainage can be realized, the original working power of each drain pump is the same, and one abnormal drain pump is detected. After the abnormal drainage pump stops working, the work task of the abnormal drainage pump needs to be distributed to other normal drainage pumps, and the distribution is carried out according to the proportion of the abnormal degree of different drainage pumps. For example: a. b, c, d, e, if a is abnormal, stopping the operation of the abnormal drainage pump a, and distributing the operation of the abnormal drainage pump a to the normal drainage pumps b, c, d, e. The larger the abnormal degree of the drainage pump is, the larger the probability of the abnormal is, so that less extra workload needs to be distributed, that is, less extra boost power needs to be distributed, and the abnormal is avoided. The abnormal degrees of the normal drainage pumps b, c, d and e are respectively 0.03, 0.05, 0.07 and 0.08; the four abnormal degrees are marked with numbers in descending order, wherein the number of the abnormal degree is 0.07, the number of the abnormal degree is 2, the number of the abnormal degree is 0.05, and the number of the abnormal degree is 0.03, is 4; and according to the sequence from small to large of the abnormal degree, sequencing and marking the corresponding normal drainage pumps with the reference numbers, wherein the reference number of the normal drainage pump b is 1, the reference number of the normal drainage pump c is 2, the reference number of the normal drainage pump d is 3, and the reference number of the normal drainage pump e is 4. And taking the abnormal degree with the same label as the normal drainage pump as the corresponding regulation coefficient of the normal drainage pump. The regulation coefficients of the normal drain pumps b, c, d and e are 0.08, 0.07, 0.05 and 0.03, respectively. The additional boost powers of the normal drainage pumps b, c, d, e are: v (a) 0.08, v (a) 0.07, v (a) 0.05, v (a) 0.03. Where v (a) is the power of the abnormal drain pump a, i.e. the abnormal power.
In summary, the embodiment of the present invention relates to the technical field of intelligent control, and first, based on a multi-segment vibration sequence of each drain pump, a common factor matrix and an independent factor vector of each drain pump are obtained by using a factor analysis method; constructing a public scatter diagram, and acquiring the maximum public principal component direction of points in each fixed segment on the public scatter diagram; the ratio of the direction value of the maximum public principal component direction to the direction value of the preset principal component direction is a public trend value; constructing an independent scatter diagram and acquiring a corresponding independent trend value; acquiring the ratio of the direction value of the principal component direction of the public tendency value to the direction value of the preset principal component direction as a public tendency direction change value; taking the product of the average value of the plurality of common trend values and the common trend direction change value as a first probability; acquiring a second probability corresponding to the independent trend value; selecting a larger value of the first probability and the second probability as an abnormal probability; matching the independent factor vectors of the current section of the drainage pumps with the independent factor vectors of the previous section to obtain current matching, wherein the difference between the current matching and the standard matching is used as the integral state variation; taking the product of the abnormal probability and the integral state variation as the abnormal degree, and screening out the abnormal drainage pump and the normal drainage pump based on the abnormal degree; stopping the work of the abnormal drainage pump; and distributing the power of the abnormal drainage pump according to the proportion of the abnormal degree of each normal drainage pump to obtain the extra boost power of each normal drainage pump. According to the embodiment of the invention, the abnormal degree of the drainage pump is obtained through the common factor and the independent factor of the vibration sequence of the molecular drainage pump, and the aim of intelligently controlling the working power of the drainage pump in a drainage system is further realized according to the abnormal degree.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. The processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
All the embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (6)
1. An intelligent control method for a building energy-saving water supply and drainage system is characterized by comprising the following steps:
acquiring a vibration sequence of the drainage pump; based on the multi-section vibration sequence of each drainage pump, obtaining a public factor matrix and an independent factor vector of each drainage pump by using a factor analysis method;
constructing a public scatter diagram, wherein one point in the public scatter diagram corresponds to one public factor matrix; acquiring the maximum public principal component direction of a point in each fixed segment on the public scatter diagram; the ratio of the direction value of the maximum public principal component direction to the direction value of the preset principal component direction is a public trend value; constructing an independent scatter diagram and acquiring a corresponding independent trend value;
acquiring the ratio of the direction value of the principal component direction of the public tendency value to the direction value of a preset principal component direction as a public tendency direction change value; taking the product of the average value of a plurality of common trend values and the common trend direction change value as a first probability; acquiring a second probability corresponding to the independent trend value; selecting a larger value of the first probability and the second probability as an abnormal probability;
matching the independent factor vectors of the current section of the drainage pumps with the independent factor vectors of the previous section to obtain current matching, wherein the difference between the current matching and the standard matching is used as the integral state variation; taking the product of the abnormal probability and the integral state variation as an abnormal degree, and screening out an abnormal drainage pump and a normal drainage pump based on the abnormal degree;
stopping the operation of the abnormal drainage pump; distributing the power of the abnormal drainage pump according to the proportion of the abnormal degree of each normal drainage pump to obtain the additional boost power of each normal drainage pump;
the method for constructing the independent scatter diagram and acquiring the corresponding independent trend value comprises the following steps: constructing an independent scatter diagram, wherein one point in the independent scatter diagram corresponds to one independent factor vector; acquiring the maximum independent principal component direction of a point in each fixed segment on the independent scatter diagram; the ratio of the direction value of the maximum independent principal component direction to the direction value of the preset principal component direction is an independent trend value;
the method for acquiring the second probability corresponding to the independent trend value comprises the following steps: acquiring the ratio of the principal component direction of the independent trend value to the direction value of a preset principal component direction as an independent trend direction change value; and taking the product of the average value of the independent trend values and the independent trend direction change value as a second probability.
2. The intelligent control method for the building energy-saving water supply and drainage system according to claim 1, wherein the method for acquiring the principal component direction of the public trend value comprises the following steps:
constructing a public trend scatter diagram according to the public trend values, wherein one point in the public trend scatter diagram corresponds to one public trend value; and the principal component directions corresponding to all the points in the public trend scatter diagram are the principal component directions of the public trend values.
3. The intelligent control method for the building energy-saving water supply and drainage system according to claim 1, wherein the method for acquiring the principal component direction of the independent trend value is as follows:
constructing an independent trend scatter diagram according to the independent trend values, wherein one point in the independent trend scatter diagram corresponds to one independent trend value; and the principal component directions corresponding to all the points in the independent trend scatter diagram are the principal component directions of the independent trend values.
4. The intelligent control method of the energy-saving water supply and drainage system of the building according to claim 1, wherein the step of matching the independent factor vectors of the current segment of the plurality of drainage pumps with the independent factor vector of the previous segment to obtain a current match, and the difference between the current match and the standard match is used as an overall state variation, comprises the steps of:
the elements in the independent factor vector of the current segment are arranged in an ascending order, and each element is marked with a label; taking the reciprocal of the difference value of the elements in the independent factor vector as an edge weight; matching elements in two independent factor vectors of a current section and an adjacent previous section to obtain a current match;
calculating the difference value of the labels of the two matched elements based on the current matching, and acquiring the sum of a plurality of difference values as the current difference value sum; obtaining the sum of standard differences when the standards are matched; and the ratio of the current difference sum to the standard difference sum is the overall state variation.
5. The intelligent control method for the energy-saving water supply and drainage system of the building as claimed in claim 1, wherein the screening out abnormal drainage pump and normal drainage pump based on the abnormal degree comprises:
taking the drainage pump with the abnormal degree larger than a preset abnormal threshold value as an abnormal drainage pump; and taking the drainage pump with the abnormal degree smaller than or equal to a preset abnormal threshold value as a normal drainage pump.
6. The intelligent control method of claim 1, wherein the distributing the power of the abnormal drainage pumps according to the percentage of the abnormal degree of each normal drainage pump to obtain the extra boost power of each normal drainage pump comprises:
acquiring the abnormal degree of each normal drainage pump; marking the abnormal degrees in a descending order; according to the sequence of the abnormal degrees from small to large, sequencing the corresponding normal drainage pumps and marking the corresponding normal drainage pumps with labels; taking the abnormal degree with the same label as the normal drainage pump as the corresponding regulation coefficient of the drainage pump;
acquiring the power of the abnormal drainage pump as abnormal power; and taking the product of the regulating coefficient and the abnormal power as the additional boosting power of the corresponding normal drainage pump.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210818029.5A CN114896825B (en) | 2022-07-13 | 2022-07-13 | Intelligent control method for building energy-saving water supply and drainage system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210818029.5A CN114896825B (en) | 2022-07-13 | 2022-07-13 | Intelligent control method for building energy-saving water supply and drainage system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114896825A CN114896825A (en) | 2022-08-12 |
| CN114896825B true CN114896825B (en) | 2022-09-30 |
Family
ID=82730212
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210818029.5A Active CN114896825B (en) | 2022-07-13 | 2022-07-13 | Intelligent control method for building energy-saving water supply and drainage system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114896825B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118605377B (en) * | 2024-08-08 | 2024-10-15 | 济冠钢铁(山东)有限公司 | Log data recording method and system for full-automatic PLC control equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006313428A (en) * | 2005-05-06 | 2006-11-16 | Toyota Motor Corp | Database evaluation device |
| JP2010225029A (en) * | 2009-03-25 | 2010-10-07 | Fuji Electric Holdings Co Ltd | Manufacture history analysis support device and manufacture history analysis support method |
| CN104079452A (en) * | 2014-06-30 | 2014-10-01 | 电子科技大学 | Data monitoring technology and network traffic abnormality classifying method |
| CN110717687A (en) * | 2019-10-16 | 2020-01-21 | 青岛海信网络科技股份有限公司 | Evaluation index acquisition method and system |
| CN113660674A (en) * | 2021-08-24 | 2021-11-16 | 电子科技大学 | Method for intelligently realizing network construction and network optimization |
| US11269752B1 (en) * | 2021-07-07 | 2022-03-08 | Eugenie Technologies Private Limited | System and method for unsupervised anomaly prediction |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780154B (en) * | 2017-01-23 | 2020-10-16 | 国网山东省电力公司电力科学研究院 | Multithread information aggregation power transmission and transformation project construction process environmental protection measure monitoring system and method |
| CN109711663B (en) * | 2018-11-15 | 2021-03-02 | 国网山东省电力公司淄博供电公司 | Transformer substation oil-immersed transformer state evaluation and correction method and system based on big data analysis |
-
2022
- 2022-07-13 CN CN202210818029.5A patent/CN114896825B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006313428A (en) * | 2005-05-06 | 2006-11-16 | Toyota Motor Corp | Database evaluation device |
| JP2010225029A (en) * | 2009-03-25 | 2010-10-07 | Fuji Electric Holdings Co Ltd | Manufacture history analysis support device and manufacture history analysis support method |
| CN104079452A (en) * | 2014-06-30 | 2014-10-01 | 电子科技大学 | Data monitoring technology and network traffic abnormality classifying method |
| CN110717687A (en) * | 2019-10-16 | 2020-01-21 | 青岛海信网络科技股份有限公司 | Evaluation index acquisition method and system |
| US11269752B1 (en) * | 2021-07-07 | 2022-03-08 | Eugenie Technologies Private Limited | System and method for unsupervised anomaly prediction |
| CN113660674A (en) * | 2021-08-24 | 2021-11-16 | 电子科技大学 | Method for intelligently realizing network construction and network optimization |
Non-Patent Citations (1)
| Title |
|---|
| An Enhanced Factor Analysis of Performance Degradation Assessment on Slurry Pump Impellers;Shilong Sun, Peter W. Tse, and Y. L. Tse;《Shock and Vibration》;20150104;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114896825A (en) | 2022-08-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114896825B (en) | Intelligent control method for building energy-saving water supply and drainage system | |
| CN108279632B (en) | A kind of pumping plant wisdom draining Dispatching Control System | |
| CN104141603A (en) | Water pump control system with energy saving function | |
| CN112780539A (en) | Energy-saving operation optimization method for speed regulating pump stations of same type | |
| CN103206364A (en) | System and method for single-model water pump energy-saving operation dispatching | |
| CN117217503B (en) | Intelligent pump station pump group remote intelligent scheduling management system based on big data | |
| CN112483427A (en) | Efficient centrifugal pump energy efficiency management method and system | |
| CN105644724B (en) | A kind of cargo oil control method and system | |
| CN112416996B (en) | Vibration area determination method and device | |
| CN107862866B (en) | Data noise point detection method based on average offset translation | |
| CN117189563A (en) | Pump unit operation control method of sewage lifting pump unit, electronic equipment and storage medium | |
| CN111008731A (en) | Flow regulation and control method for blade mechanism of intelligent pump station | |
| CN111520874A (en) | Water system air conditioner room energy efficiency detection optimization system | |
| CN114396385B (en) | Scheduling control method based on pump station operation | |
| CN1159146C (en) | Energy saving device of frequency change injection moulding machine and its energy saving method | |
| CN113869266B (en) | Centrifugal compressor rotating stall early warning method based on big data analysis | |
| CN112797017B (en) | Energy-saving space estimation method for energy-saving reconstruction of cooling circulating water | |
| CN112303688B (en) | Control method of multi-range hood system and multi-range hood system | |
| CN210768903U (en) | Mine drainage system is based on sectional control device of peak valley price of electricity | |
| CN111188386A (en) | Energy-saving system suitable for water supply equipment | |
| CN115434902B (en) | Design method of high-flow high-vacuum air pumping system | |
| CN118468072B (en) | MVR evaporator-oriented intelligent inspection method | |
| CN118309640B (en) | Pump unit optimization intelligent scheduling method and system based on evolutionary algorithm | |
| CN115094977B (en) | Energy-saving self-adaptive pump station control method | |
| CN114492247B (en) | Impeller high-efficiency low-vibration optimization method based on Euler lift standard function of blade |
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 |