CN112305184B - Sewage treatment multi-fault diagnosis system and method - Google Patents
Sewage treatment multi-fault diagnosis system and method Download PDFInfo
- Publication number
- CN112305184B CN112305184B CN202011081813.XA CN202011081813A CN112305184B CN 112305184 B CN112305184 B CN 112305184B CN 202011081813 A CN202011081813 A CN 202011081813A CN 112305184 B CN112305184 B CN 112305184B
- Authority
- CN
- China
- Prior art keywords
- data
- sewage
- subsystem
- sewage index
- index data
- 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
- 239000010865 sewage Substances 0.000 title claims abstract description 247
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000011282 treatment Methods 0.000 title claims abstract description 53
- 238000003745 diagnosis Methods 0.000 title claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 96
- 230000002159 abnormal effect Effects 0.000 claims abstract description 52
- 238000004458 analytical method Methods 0.000 claims abstract description 35
- 238000013500 data storage Methods 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000005065 mining Methods 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 230000008901 benefit Effects 0.000 abstract description 9
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000002405 diagnostic procedure Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000005273 aeration Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000011524 similarity measure Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000011221 initial treatment Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- Water Supply & Treatment (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Public Health (AREA)
- Biochemistry (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a sewage treatment multi-fault diagnosis system and a method, comprising the following steps: the sewage index collection subsystem, the sewage index receiving and transmitting subsystem, the data storage subsystem, the data processing subsystem, the cloud database, the query subsystem, the comparison subsystem, the abnormal index data processing subsystem and the fault alarm display subsystem are combined with a variable clustering analysis algorithm and a weighted entropy model to calculate and analyze sewage index data, so that the redundancy of the data is reduced, the overall quality of the data is improved, the advantages of high flexibility, good expansibility, high processing efficiency and low error rate are reflected when the data processing subsystem processes the index data, the sewage index is monitored in real time by utilizing a threshold alarm mode, and the sewage index data can be accurately mastered. The invention not only can carry out detailed data analysis and fault analysis on multiple faults, but also has the advantage of quickly and accurately finding out multiple fault positions.
Description
Technical Field
The invention relates to the technical field of sewage treatment fault diagnosis, in particular to a sewage treatment multi-fault diagnosis system and a sewage treatment multi-fault diagnosis method.
Background
With the rapid development of economy, the living standard and the social production capacity of people are greatly improved, but sewage brought in the development process brings a great deal of pollution to the environment. Sewage is generally divided into two types, namely production sewage and domestic sewage, and corresponding sewage treatment is also divided into production sewage treatment and domestic sewage treatment. In the sewage treatment process, the quality of sewage treatment equipment directly influences the sewage treatment efficiency. When the sewage treatment equipment has multiple faults, the accurate positions of the faults are difficult to find, so that the faults cannot be maintained in time.
Sewage can be classified into primary treatment, secondary treatment and tertiary treatment according to the flow of treatment, and secondary treatment of sewage is of great importance in sewage treatment, wherein an aeration tank of secondary treatment is the most likely device to fail. The sewage treatment system has continuity and irreplaceability in operation, and once failure occurs, the sewage treatment process is seriously affected. Therefore, the system and the method for diagnosing the multiple faults of the sewage treatment are rapid and effective in research and have very important practical significance.
Currently, there are many fault diagnosis methods on the market, for example: deep learning technology-based diagnostic methods, knowledge comprehensive diagnostic methods, mathematical simulation diagnostic methods, statistical diagnostic methods, artificial intelligent diagnostic methods, integrated diagnostic methods, expert system diagnostic methods and the like, but these methods have a number of disadvantages:
(1) The diagnosis method based on the deep learning technology has the problems of consuming a great deal of time, computing resources and the like when performing model training;
(2) In the artificial intelligent diagnosis method, the existing artificial intelligent diagnosis technologies such as expert systems, neural networks and the like have defects and limitations, and the problems of poor autonomous learning ability, weak numerical calculation ability, insufficient empirical reasoning ability and the like are mainly represented;
(3) Most of the existing single fault diagnosis methods or diagnosis systems monitor or diagnose single faults, and when multiple faults occur in the sewage treatment process, the accuracy of diagnosis results of the existing single fault diagnosis methods or diagnosis systems is low due to chained reflection among the multiple faults.
Therefore, the traditional sewage fault diagnosis technology has many problems in aspects of multi-fault classification analysis, sewage data processing and the like, and when a plurality of faults occur simultaneously, the traditional technology has low diagnosis efficiency and weak stability, and can not meet the requirements of good reliability, strong stability, high accuracy and the like of fault diagnosis in the sewage treatment process.
Therefore, a sewage treatment multi-fault diagnosis system and method are a urgent problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the invention uses the variable clustering analysis algorithm and the weighted entropy method to carry out multi-fault diagnosis on the sewage treatment process, and has the advantages of good reliability, strong stability, high accuracy and the like.
A first object of the present invention is to provide a sewage treatment multi-fault diagnosis system, which overcomes the disadvantages of the prior diagnosis techniques, comprising: the system comprises a sewage index acquisition subsystem, a sewage index receiving and transmitting subsystem, a data storage subsystem, a data processing subsystem, a cloud database, a query subsystem, a comparison subsystem, an abnormal index data processing subsystem and a fault alarm display subsystem; the sewage index receiving and transmitting subsystem comprises a sewage index receiving module and a sewage index transmitting module; the data processing subsystem comprises a data preprocessing module, a distributed processing module and a data calculating and analyzing module.
The sewage index acquisition subsystem is connected with the sewage index receiving and transmitting subsystem; the sewage index receiving module is connected with the sewage index transmission module; the sewage index receiving and transmitting subsystem is connected with the data storage subsystem; the data storage subsystem is connected with the data processing subsystem; the data preprocessing module is connected with the distributed processing module; the distributed processing module is connected with the data calculation and analysis module; the data processing subsystem is connected with the comparison subsystem; the cloud database is connected with the query subsystem; the inquiring subsystem is connected with the comparing subsystem; the comparison subsystem is connected with the abnormal index data processing subsystem; the abnormal index data processing subsystem is connected with the fault alarm display subsystem.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a sewage treatment multiple fault diagnosis system comprising:
the sewage index acquisition subsystem adopts a sensor to acquire sewage index data;
the sewage index receiving and transmitting subsystem is used for receiving and transmitting sewage index data of the sewage index collecting subsystem;
the data storage subsystem is used for storing the sewage index data of the sewage index receiving and transmitting subsystem;
the data processing subsystem is used for carrying out data processing and analysis on the sewage index data in the data storage subsystem;
the cloud database is used for acquiring a sewage index data threshold value;
the query subsystem is used for sorting and analyzing various sewage index data thresholds of the cloud database;
the comparison subsystem is used for receiving the sewage index data of the data processing subsystem, receiving the sewage index data threshold value of the query subsystem, and comparing the two data;
the abnormal index data processing subsystem is used for processing and analyzing the abnormal index data of the comparison subsystem;
and the fault alarm display subsystem is used for carrying out visual processing and fault position display on the abnormal index data of the abnormal index data processing subsystem and sending out an alarm.
Preferably, the sewage index receiving and transmitting subsystem further comprises:
the sewage index receiving module is used for receiving sewage index data of the sewage index collecting subsystem;
and the sewage index transmission module is used for transmitting the sewage index data of the sewage index receiving module to the data storage subsystem.
Preferably, the data processing subsystem further comprises:
the data preprocessing module is used for preprocessing the received sewage index data and clearing some wrong data information so as to improve the fault tolerance of the system. In addition, as the received sewage index data are more dispersed, the data preprocessing module also needs to integrate the sewage index data, and then reduce the sewage index data and convert the sewage index data;
the distributed processing module is used for realizing the next processing of the preprocessed index data by utilizing MATLAB software;
and the data calculation and analysis module is used for calculating and analyzing the sewage index data after the distributed treatment so as to further realize the mining and analysis of the abnormal condition of the sewage data.
The second object of the invention is to provide a sewage treatment multi-fault diagnosis method, which solves the defects of the existing single fault diagnosis technology.
The above object of the present invention is achieved by the following technical solutions:
the sewage treatment multi-fault diagnosis method is based on the sewage treatment multi-fault diagnosis system and comprises the following steps of:
s1, acquiring sewage indexes by adopting a sensor to obtain sewage index data;
s2, receiving and transmitting the sewage index data obtained in the step S1;
s3, storing the sewage index data obtained in the step S2 by adopting a data storage subsystem;
s4, adopting a variable clustering analysis and weighted entropy method to process and analyze the sewage index data obtained in the step S3 to obtain processed sewage index data;
s5, acquiring a sewage index data threshold value from a cloud database;
s6, receiving the sewage index data threshold value obtained in the step S5, and sorting and analyzing the sewage index data threshold value to form a new sewage index data threshold value;
s7, receiving the sewage index data obtained in the step S4, receiving a sewage index data threshold in the step S6, and comparing the two data to obtain abnormal index data;
s8, receiving the abnormal index data obtained in the step S7, and processing and analyzing the abnormal index data;
s9, receiving the abnormal index data processed in the step S8, displaying the position of the fault after visual processing, and alarming.
Preferably, the step S2 further includes the steps of:
step S21: receiving sewage indexes, namely receiving the sewage index data acquired in the step S1;
step S22: and (3) transmitting the sewage index data obtained in the step (S21) to the data storage subsystem in the step (S3).
Preferably, the step S4 further includes the steps of:
step S41: the data preprocessing adopts a method of integrating the sewage index data and then reducing the sewage index data and converting the sewage index data because the received sewage index data are more dispersed, so as to solve the problems of inconsistent original index data, missing numerical values and the like;
step S42: and (3) carrying out distributed processing, namely coordinating each index data by using a Zookeeper to ensure that each index data is kept smooth during processing, then processing the data by combining the data of the whole system, and summarizing the data through a final stage to realize data classification. The process can accurately process the data to ensure the accuracy of index data;
step S43: and calculating and analyzing data, namely calculating the distributed sewage index data by utilizing MATLAB software according to a variable clustering analysis algorithm and a weighted entropy model, extracting data characteristics and analyzing, so as to realize mining and analyzing abnormal conditions of the sewage data.
Compared with the prior art, the sewage treatment multi-fault diagnosis system and method provided by the invention have the beneficial effects that:
(1) Compared with the traditional sewage treatment fault diagnosis method, the system and the method not only can carry out detailed data analysis and fault analysis on multiple faults, but also have the advantage of quickly and accurately finding out multiple fault positions;
(2) The data processing of the system and the method adopts a database management mode, thereby not only greatly reducing the labor of people, but also improving the sewage processing speed and the fault tolerance of the system. In the data preprocessing module, data cleaning, data integration, data reduction and data conversion are carried out, so that the problems of inconsistent data, missing numerical values and the like of original data are solved, and meanwhile, noise existing in the data is eliminated, so that the overall quality of the data is improved. In the data calculation and analysis module, a variable clustering analysis algorithm and a weighted entropy are used for calculating sewage index data. In the distributed processing module, the Zookeeper is used for coordinating the sewage index data in the processing process, so that the method has the advantages of fast data processing and strong data fault tolerance in the process of processing massive sewage index data. The whole data processing is performed in three parts, so that the data processing has the advantages of high flexibility, good expansibility, high processing efficiency and low error rate when index data processing is performed;
(3) And a threshold value alarm mode is adopted to achieve the real-time monitoring of sewage indexes. Compared with the traditional fault diagnosis method or fault diagnosis system, when the sewage index data is abnormal, the system and the method can intervene in the sewage treatment process in advance, so that the fault is solved in time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a system architecture of the present invention;
FIG. 2 is a flow chart of the sewage index data processing according to the present invention.
In fig. 1, the components represented by the respective reference numerals are as follows:
the system comprises a 1-sewage index acquisition subsystem, a 2-sewage index receiving and transmitting subsystem, a 21-sewage index receiving module, a 22-sewage index transmitting module, a 3-data storage subsystem, a 4-data processing subsystem, a 41-data preprocessing module, a 42-distributed processing module, a 43-data calculating and analyzing module, a 5-cloud database, a 6-query subsystem, a 7-comparison subsystem, an 8-abnormal index data processing subsystem and a 9-fault alarm display subsystem.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1:
referring to fig. 1, an embodiment of the present invention discloses a sewage treatment multi-fault diagnosis system, including:
the sewage index acquisition subsystem 1 is connected with the sewage index receiving and transmitting subsystem 2; the sewage index receiving and transmitting subsystem 2 is connected with the data storage subsystem 3; the data storage subsystem 3 is connected with the data processing subsystem 4; the data processing subsystem 4 is connected with the comparison subsystem 7; the cloud database 5 is connected with the query subsystem 6; the query subsystem 6 is connected with the comparison subsystem 7; the comparison subsystem 7 is connected with the abnormal index data processing subsystem 8; the abnormal index data processing subsystem 8 is connected with the fault alarm display subsystem 9; the sewage index receiving module 21 is connected with the sewage index transmission module 22; the data preprocessing module 41 is connected with the distributed processing module 42; the distributed processing module 42 is connected to a data calculation and analysis module 43.
The sewage index acquisition subsystem 1 acquires sewage index data by adopting a sensor;
the sewage index receiving and transmitting subsystem 2 is used for receiving and transmitting sewage index data of the sewage index collecting subsystem 1;
a data storage subsystem 3 for storing sewage index data of the sewage index receiving and transmitting subsystem 2;
the data processing subsystem 4 is used for processing and analyzing the sewage index data in the data storage subsystem 3;
the cloud database 5 is used for acquiring a sewage index data threshold value;
the query subsystem 6 is used for sorting and analyzing various sewage index data thresholds of the cloud database 5;
the comparison subsystem 7 is configured to receive the sewage index data of the data processing subsystem 4, and simultaneously receive the sewage index data threshold value of the query subsystem 6, and then compare the two data, and when the index data exceeds the threshold value range, it indicates that the sewage index is abnormal, and specifically includes three cases: wherein, let threshold r=3, let sewage index data w, first case: the absolute value of the difference between the abnormal index data and the threshold value is |w-r| <0.5, and the absolute value indicates that no fault occurs in the sewage treatment process; second case: the absolute value of the difference between the abnormal index data and the threshold value is |w-r| <1, wherein the absolute value is 0.5< |w-r| <1, and the abnormal index data and the threshold value indicate that slight faults occur in the sewage treatment process; third case: the absolute value of the difference between the abnormal index data and the threshold value is |w-r| >1, and the serious fault occurs in the sewage treatment process. The abnormal index data is then transmitted to the abnormal index data processing subsystem 8;
the abnormal index data processing subsystem 8 is used for processing and analyzing the abnormal index data of the comparison subsystem 7. Wherein, let threshold r=3, let sewage index data w, first case: absolute value of difference between abnormal index data and threshold value is |w-r| <0.5, abnormal index data processing subsystem 8 does not alarm; second case: the absolute value of the difference between the abnormal index data and the threshold value is 0.5< -w-r <1 >, the abnormal index data processing subsystem 8 automatically alarms and sends a fault notification to the fault alarm display subsystem 9; third case: the absolute value of the difference between the abnormal index data and the threshold value is |w-r| >1, the abnormal index data processing subsystem 8 automatically alarms, and an emergency fault notification is sent to the fault alarm display subsystem 9;
the fault alarm display subsystem 9 is used for displaying the position where the fault occurs after the visual processing of the abnormal index data processing subsystem 8. For the first case, the fault alarm display subsystem 9 does not issue a fault notification; for the second case, the fault alarm display subsystem 9 sends out a fault notification, and the fault position is displayed; for the third case, the fault alarm display subsystem 9 issues an emergency fault notification and issues an emergency treatment command, and displays the fault location and timely shuts down the sewage treatment process.
Specifically, the sewage indicator receiving and transmitting subsystem 2 further includes:
a sewage index receiving module 21, configured to receive sewage index data of the sewage index collecting subsystem 1;
the sewage index transmission module 22 is configured to transmit the sewage index data of the sewage index receiving module 21 to the data storage subsystem 3.
Specifically, the data processing subsystem 4 further includes:
the data preprocessing module 41 is configured to preprocess the received sewage index data, and clean some erroneous data information, so as to improve the fault tolerance of the system. In addition, since the received sewage index data are relatively distributed, the data preprocessing module 41 also needs to integrate the sewage index data, and then perform sewage index data reduction and sewage index data conversion;
the distributed processing module 42 utilizes MATLAB software to realize the next processing of the preprocessed index data;
the data calculation and analysis module 43 is configured to calculate and analyze the sewage index data after distributed processing, so as to further implement mining and analysis of abnormal situations of the sewage data.
Specifically, the principle of the calculation mechanism in the data calculation and analysis module 43 is as follows: the method comprises the steps of firstly processing multiple faults occurring in the sewage treatment process by using a variable clustering analysis algorithm, further obtaining relations among the faults, then processing abnormal index data by using variable clustering analysis, further obtaining relations among the abnormal index data, and finally performing weight analysis on the abnormal index data with the relations by using a weighted entropy, so as to obtain the duty ratio of the abnormal index data, and further achieve the effects of data calculation and analysis.
Example 2:
referring to fig. 2, a sewage treatment multi-fault diagnosis method specifically comprises the following steps:
s1, acquiring sewage indexes by adopting a sensor to obtain sewage index data;
s2, receiving and transmitting the sewage index data obtained in the step S1;
s3, storing the sewage index data obtained in the step S2;
s4, adopting a variable clustering analysis and weighted entropy method to process and analyze the sewage index data obtained in the step S3 to obtain processed sewage index data;
s5, acquiring a sewage index data threshold value from the cloud database 5;
s6, receiving the sewage index data threshold value obtained in the step S5, and sorting and analyzing the sewage index data threshold value to form a new sewage index data threshold value;
s7, receiving the sewage index data obtained in the step S4, receiving a sewage index data threshold in the step S6, and comparing the two data to obtain abnormal index data;
s8, receiving the abnormal index data in the step S7, and processing, analyzing and alarming the abnormal index data;
s9, receiving the abnormal index data processed in the step S8, and displaying the position of the fault after visual processing.
In a specific embodiment, step S2 specifically includes the following steps:
step S21: receiving sewage indexes and receiving sewage index data acquired by the sewage index acquisition subsystem 1;
step S22: and the sewage index transmission is used for transmitting the sewage index data obtained by the sewage index receiving module 21 to the data storage subsystem 3.
In a specific embodiment, the step S4 of data processing is mainly used for processing and analyzing the sewage index data in the data storage subsystem 3, and specifically includes the following steps:
step S41: the data preprocessing adopts a method of integrating the sewage index data and then reducing the sewage index data and converting the sewage index data because the received sewage index data are more dispersed, so as to solve the problems of inconsistent original index data, missing numerical values and the like;
step S42: and (3) carrying out distributed processing, namely coordinating each index data during processing by using a Zookeeper to ensure that each index data is kept smooth during processing, then processing the data by combining the data of the whole system, and summarizing the data through a final stage to realize data classification. The process can accurately process the data and ensure the accuracy of index data;
step S43: and calculating and analyzing data, namely calculating the distributed sewage index data by utilizing MATLAB software according to a variable clustering analysis algorithm and a weighted entropy model, extracting data characteristics and analyzing, so as to further realize mining and analyzing abnormal conditions of the sewage data.
Specifically, the clustering algorithm for the variables is as follows:
the correlation coefficient expression is shown in the formula (1):
record sewage index variable x j Is the value of (x) 1j ,x 2j ,…,x nj ) T ∈R n (j=1, 2, …, m) (i=1, 2, …, n). Then two variables x can be used j And x k As their similarity measure:
in the method, in the process of the invention,and->Is of two variables x j And x k Mean value of the sample data of r jk Is of two variables x j And x k In the clustering analysis of sewage index variables, the correlation coefficient of the sample of (a) is represented by x ij And forming a correlation coefficient matrix.
Specifically, in the variable clustering analysis, the longest distance method is adopted from the fault problem in the sewage treatment process:
in the longest distance method, a distance expression defining two variables is shown in formula (2):
wherein d jk ＝1-|r jk I or d jk 2 ＝1-r jk 2 ，G 1 ，G 2 Is of two sewage index sample types, R (G 1 ,G 2 ) Related to the similarity measure of the variable of the two classes with the smallest similarity.
Specifically, the weighted entropy model is as follows:
assuming that e objects and n indexes exist in the sewage index data system, the formed original index data matrix is x= (x) ij ) en In (c), probability (p i ) The larger H (x) is, the smaller H (x) is, the weight coefficient (w i ) The larger. Thus, the weight of each sewage index can be calculated by using the weighted entropy.
Let the source be X, its model is shown as formula (3):
wherein p is 0.ltoreq.p i Less than or equal to 1 (i=1, 2, …, q), andin addition, for each event a i Designating a non-negative real number b i Gtoreq 0 (i=1, 2, …, q), this set of real numbers being called weights of events. The weight establishment method comprises the following steps:
for example, the sewage index in the experimental aeration tank is taken as a research object, a test data containing m×n orders is listed, and the listed test data of m×n orders is subjected to a normalized decision matrix r= (R) ij ) m×n The expression is shown as formula (4):
wherein: m is the batch of sewage index experiment samples; n is the index number of each batch of sewage. Order the
The entropy expression of the index is shown as the formula (6):
the expression of the coefficient of variation degree of the calculated sewage index is shown as the formula (7):
c j ＝1-h j ,j＝1,2,…,n (7)
the expression of the weighting coefficient of each sewage index is calculated as shown in the formula (8):
it can be concluded that the invention relates to a sewage treatment multi-fault diagnosis system and method, in the data processing subsystem, the sewage index data is calculated and analyzed by combining a variable clustering analysis algorithm and a weighted entropy model, the redundancy of the data is reduced, the overall quality of the data is improved, and the advantages of high flexibility, good expansibility, high processing efficiency and low error rate are reflected when the index data processing is carried out by the data processing subsystem; in the abnormal index data processing subsystem, the threshold value alarming mode is utilized to achieve the real-time monitoring of the sewage index, and the sewage index data processing subsystem has the advantage of being capable of accurately mastering the sewage index data. In combination with the whole, the method can not only perform detailed data analysis and fault analysis on multiple faults, but also has the advantage of quickly and accurately finding out multiple fault positions.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. The apparatus disclosed in the embodiment corresponds to the method disclosed in the embodiment.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (4)
1. A sewage treatment multiple fault diagnosis system, comprising: the system comprises a sewage index acquisition subsystem, a sewage index receiving and transmitting subsystem, a data storage subsystem, a data processing subsystem, a cloud database, a query subsystem, a comparison subsystem, an abnormal index data processing subsystem and a fault alarm display subsystem; the sewage index collecting subsystem is connected with a sewage index receiving module in the sewage index receiving and transmitting subsystem; the sewage index receiving and transmitting module in the sewage index receiving and transmitting subsystem is connected with the data storage subsystem; the data storage subsystem is connected with a data preprocessing module in the data processing subsystem; the data calculation and analysis module in the data processing subsystem is connected with the comparison subsystem; the cloud database is connected with the query subsystem; the inquiring subsystem is connected with the comparing subsystem; the comparison subsystem is connected with the abnormal index data processing subsystem; the abnormal index data processing subsystem is connected with the fault alarm display subsystem;
the sewage index receiving and transmitting subsystem comprises a sewage index receiving module and a sewage index transmitting module; the sewage index receiving module is connected with the sewage index transmission module; the data processing subsystem comprises a data preprocessing module, a distributed processing module and a data calculating and analyzing module; the data preprocessing module is connected with the distributed processing module; the distributed processing module is connected with the data calculation and analysis module.
2. A sewage treatment multiple fault diagnosis method, applying the sewage treatment multiple fault diagnosis system according to claim 1, characterized by comprising the steps of:
s1, acquiring sewage indexes by adopting a sensor to obtain sewage index data;
s2, transmitting the sewage index data obtained in the step S1 to a sewage index receiving module in the sewage index receiving and transmitting subsystem, and transmitting the sewage index data in the sewage index receiving module to a data storage subsystem through the sewage index transmitting module;
s3, storing the sewage index data obtained in the step S2 by adopting the data storage subsystem;
s4, firstly, carrying out data preprocessing on the sewage index data stored in the step S3, namely integrating the sewage index data with the sewage index data after the error is cleared, then carrying out distributed processing on the sewage index data after the data preprocessing is completed so that the sewage index data is more concentrated, then adopting a variable clustering analysis and weighted entropy method, carrying out clustering analysis algorithm calculation and data characteristic analysis on the sewage index data after the distributed processing is completed, and finally transmitting the sewage index data after the calculation analysis is completed to a comparison subsystem for comparison analysis;
s5, acquiring a sewage index data threshold value from the cloud database;
s6, receiving the sewage index data threshold value obtained in the step S5, and sorting and analyzing the sewage index data threshold value to form a new sewage index data threshold value;
s7, receiving the sewage index data obtained in the step S4, receiving a sewage index data threshold in the step S6, and comparing the two data to obtain abnormal sewage index data;
s8, receiving the abnormal sewage index data obtained in the step S7, and processing and analyzing the abnormal sewage index data;
s9, receiving the abnormal sewage index data processed in the step S8, displaying the position of the fault after visual processing, and alarming.
3. The method for diagnosing multiple faults in sewage treatment according to claim 2, wherein the step S2 further comprises the steps of:
step S21: receiving sewage indexes, namely receiving the sewage index data acquired in the step S1;
step S22: and (3) transmitting the sewage index data obtained in the step (S21) to the data storage subsystem in the step (S3).
4. A multi-fault diagnosis method for sewage treatment according to claim 3, wherein said step S4 further comprises the steps of:
step S41: the data preprocessing, because the received sewage index data are more scattered, the sewage index data in the data storage subsystem in the step S3 are required to be integrated, and the sewage index data are reduced and converted to solve the problems of inconsistent original sewage index data and missing numerical values;
step S42: the distributed treatment, coordinate each sewage index data by using the Zookeeper, so as to ensure that each sewage index data is kept smooth during treatment, then the data of the whole system are combined for treatment, and the data classification is realized by summarizing in the final stage, so that the data can be accurately treated in the process, and the accuracy of the sewage index data is ensured;
step S43: and calculating and analyzing data, namely calculating the sewage index data after the distributed processing is completed and analyzing the extracted data characteristics by utilizing MATLAB software according to a variable clustering analysis algorithm and a weighted entropy model, so that the mining and analysis of the abnormal condition of the sewage data can be realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011081813.XA CN112305184B (en) | 2020-10-12 | 2020-10-12 | Sewage treatment multi-fault diagnosis system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011081813.XA CN112305184B (en) | 2020-10-12 | 2020-10-12 | Sewage treatment multi-fault diagnosis system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112305184A CN112305184A (en) | 2021-02-02 |
| CN112305184B true CN112305184B (en) | 2023-10-13 |
Family
ID=74488300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011081813.XA Active CN112305184B (en) | 2020-10-12 | 2020-10-12 | Sewage treatment multi-fault diagnosis system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112305184B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090078502A (en) * | 2008-01-15 | 2009-07-20 | 부산대학교 산학협력단 | Apparatus and method for diagnosis of operating states in municipal wastewater treatment plant |
| CN103812727A (en) * | 2014-01-27 | 2014-05-21 | 中国电子科技集团公司第十研究所 | Diagnostic method for automatically analyzing and positioning equipment failure of deep space measurement and control station |
| KR20160038597A (en) * | 2014-09-30 | 2016-04-07 | 조남희 | Inspecting, measuring and preventing method for possible risk situation |
| CN106630476A (en) * | 2016-12-31 | 2017-05-10 | 马鞍山立信汽车零部件有限公司 | Sewage treatment system |
| CN107741738A (en) * | 2017-10-20 | 2018-02-27 | 重庆华绿环保科技发展有限责任公司 | A kind of sewage disposal process monitoring intelligent early warning cloud system and sewage disposal monitoring and pre-alarming method |
| CN110134096A (en) * | 2019-06-13 | 2019-08-16 | 瑞安市浙工大创新创业研究院 | A kind of multipoint mode sewage treatment monitoring system and method based on cloud |
| CN110320892A (en) * | 2019-07-15 | 2019-10-11 | 重庆邮电大学 | The sewage disposal device fault diagnosis system and method returned based on Lasso |
| CN110825041A (en) * | 2019-10-25 | 2020-02-21 | 北京首创股份有限公司 | Centralized control type intelligent sewage treatment plant operation system |
-
2020
- 2020-10-12 CN CN202011081813.XA patent/CN112305184B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090078502A (en) * | 2008-01-15 | 2009-07-20 | 부산대학교 산학협력단 | Apparatus and method for diagnosis of operating states in municipal wastewater treatment plant |
| CN103812727A (en) * | 2014-01-27 | 2014-05-21 | 中国电子科技集团公司第十研究所 | Diagnostic method for automatically analyzing and positioning equipment failure of deep space measurement and control station |
| KR20160038597A (en) * | 2014-09-30 | 2016-04-07 | 조남희 | Inspecting, measuring and preventing method for possible risk situation |
| CN106630476A (en) * | 2016-12-31 | 2017-05-10 | 马鞍山立信汽车零部件有限公司 | Sewage treatment system |
| CN107741738A (en) * | 2017-10-20 | 2018-02-27 | 重庆华绿环保科技发展有限责任公司 | A kind of sewage disposal process monitoring intelligent early warning cloud system and sewage disposal monitoring and pre-alarming method |
| CN110134096A (en) * | 2019-06-13 | 2019-08-16 | 瑞安市浙工大创新创业研究院 | A kind of multipoint mode sewage treatment monitoring system and method based on cloud |
| CN110320892A (en) * | 2019-07-15 | 2019-10-11 | 重庆邮电大学 | The sewage disposal device fault diagnosis system and method returned based on Lasso |
| CN110825041A (en) * | 2019-10-25 | 2020-02-21 | 北京首创股份有限公司 | Centralized control type intelligent sewage treatment plant operation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112305184A (en) | 2021-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287552B (en) | Motor bearing fault diagnosis method and system based on improved random forest algorithm | |
| CN113156917B (en) | Power grid equipment fault diagnosis method and system based on artificial intelligence | |
| US8868985B2 (en) | Supervised fault learning using rule-generated samples for machine condition monitoring | |
| CN111830408A (en) | Motor fault diagnosis system and method based on edge calculation and deep learning | |
| CN109086470A (en) | A kind of method for diagnosing faults based on fuzzy preference relation and D-S evidence theory | |
| CN113762329A (en) | Method and system for constructing state prediction model of large rolling mill | |
| CN110636066B (en) | Network security threat situation assessment method based on unsupervised generative reasoning | |
| CN113339204B (en) | Wind driven generator fault identification method based on hybrid neural network | |
| CN115409131B (en) | Production line abnormity detection method based on SPC process control system | |
| CN114201374A (en) | Operation and maintenance time sequence data anomaly detection method and system based on hybrid machine learning | |
| CN117421994A (en) | Edge application health monitoring method and system | |
| CN111583592A (en) | Experimental environment safety early warning method based on multidimensional convolution neural network | |
| CN117556347A (en) | Power equipment fault prediction and health management method based on industrial big data | |
| CN115442212A (en) | Intelligent monitoring analysis method and system based on cloud computing | |
| CN115822943A (en) | Hydraulic pump leakage fault diagnosis method | |
| CN113593605B (en) | Industrial audio fault monitoring system and method based on deep neural network | |
| CN115062686A (en) | Multi-KPI (Key performance indicator) time sequence abnormity detection method and system based on multi-angle features | |
| CN114280383A (en) | Health detection device and health detection method for large ground station antenna | |
| CN112305184B (en) | Sewage treatment multi-fault diagnosis system and method | |
| CN110160781B (en) | Test set reconstruction and prediction method for rotary machine fault classification | |
| CN114167837B (en) | Intelligent fault diagnosis method and system for railway signal system | |
| CN110837953A (en) | Automatic abnormal entity positioning analysis method | |
| CN116127324A (en) | Fault detection method and device for key components in uninterruptible power supply | |
| CN109492705A (en) | Method for diagnosing faults of the one kind based on mahalanobis distance (MD) area measurement | |
| CN116224950A (en) | Intelligent fault diagnosis method and system for self-organizing reconstruction of unmanned production line |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20210202 Assignee: Guangxi Taiyao Technology Co.,Ltd. Assignor: GUILIN University OF TECHNOLOGY Contract record no.: X2023980044021 Denomination of invention: A multi fault diagnosis system and method for sewage treatment Granted publication date: 20231013 License type: Common License Record date: 20231020 |