CN108334714A - Oil water separator oil exit pipe control system based on fuzzy neural network and method - Google Patents
Oil water separator oil exit pipe control system based on fuzzy neural network and method Download PDFInfo
- Publication number
- CN108334714A CN108334714A CN201810174436.0A CN201810174436A CN108334714A CN 108334714 A CN108334714 A CN 108334714A CN 201810174436 A CN201810174436 A CN 201810174436A CN 108334714 A CN108334714 A CN 108334714A
- Authority
- CN
- China
- Prior art keywords
- oil
- exit pipe
- water separator
- oil exit
- neural network
- 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.)
- Granted
Links
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
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/40—Devices for separating or removing fatty or oily substances or similar floating material
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a kind of oil water separator oil exit pipe control system and method based on fuzzy neural network, acquire oil exit pipe current detection data, utilize the oil water separator oil exit pipe Controlling model of structure, oil exit pipe current detection data are diagnosed, oil extraction to export oil exit pipe controls current value, controls oil drain pump on-off action and the electric heating tube work of oil water separator oil exit pipe.Advantage of the present invention is：Coordinate the measurement result of temperature sensor to be precisely controlled time and the temperature of heating in oil exit pipe carries out heating process, and using Fuzzy Neural-network Control algorithm, improves heating effect, save the energy；And the operating status that can judge oil water separator according to testing result, encounters failure and alarm.
Description
Technical field
The present invention relates to oil exit pipe control technology fields, and in particular to a kind of oil water separator based on fuzzy neural network
Oil exit pipe control system and method.
Background technology
Restaurant or family, which mix swill after dining, will produce swill, throws out swill without care and not only pollutes
Environment, and the chance that refinement gutter oil can be provided to illegal retailer will damage people's once gutter oil returns on dining table
Health.However if separating and being refined the oil in swill, so that it may to be converted into the raw material of industry, realize waste
It utilizes.Therefore, some companies develop swill separator for the water-oil separating problem in swill.But swill detaches at present
The oil exit pipe control system of device is defective, and defect is as follows：
1. for traditional swill separator oil exit pipe control system, control whether oil exit pipe is arranged according to setting time
Oil, even if can be opened if draining valve in the few oil exit pipe of oil in oil exit pipe, causes the energy if setting time arrives
Loss；When there are many oil in oil exit pipe, if weather is cold, oily viscosity increases, if opening draining valve at this time, oily nothing
Method is discharged；
2. for traditional swill separator oil exit pipe control system, the oil drain quantity of oil exit pipe can not be measured, therefore
If the oil drum for being responsible for connecing oil below is full, oil exit pipe, which continues oil extraction, to cause fluid to overflow；
3. break down for traditional oily water separating equipment, if failure can not obtain detection and investigation, oil in time
Water separating effect is deteriorated, and water content is excessive in the liquid of oil exit pipe discharge.
Invention content
(1) the technical issues of solving
In view of the deficiencies of the prior art, the present invention provides a kind of oil water separator oil exit pipe based on fuzzy neural network
Control system and method, Fuzzy Neural-network Control algorithm coordinate temperature sensor measurement result, be precisely controlled heating when
Between and temperature, improve heating effect, save the energy, while can find the failure in oil water separator in time, enable failure
It is investigated in time.
(2) technical solution
In order to achieve the above object, the present invention is achieved by the following technical programs：It is a kind of based on fuzzy neural network
Oil water separator oil exit pipe control method, includes the following steps：
Step 1 is based on fuzzy neural network algorithm, builds the oil water separator oil exit pipe control based on fuzzy neural network
Model；
Step 2, the oil water separator oil exit pipe Controlling model established to step 1 are trained, and determine the mould of Controlling model
Shape parameter；
Step 3, acquisition oil exit pipe current detection data, the oil water separator oil exit pipe Controlling model determined using step 2,
Oil exit pipe current detection data are diagnosed, the oil extraction to export oil exit pipe controls current value, and oil extraction control current value includes
Fluid releases the time current value t and heating temperature current value T of curdled appearance；
Step 4 judges whether current liquid temperature reaches liquid melt temperature TMeltIf judging result is no, step is returned
Rapid 3；If the determination result is YES, then stop heating and recording current heating time tIt is real；
Step 5 judges | t-tIt is real| whether it is more than given threshold t'；If the determination result is YES, then fault alarm is sent out；If sentencing
Disconnected result is no, then return to step 3.
Preferably, above-mentioned steps 1 establish the step of oil water separator oil exit pipe Controlling model and are：
Step 1.1 determines the input variable x of oil water separator oil exit pipe Controlling model1x2x3, x1For fluid temperature in pipe
TLiquid, x2For liquid level V in pipeLiquid,x3For the time interval t heated apart from last timeEvery；
Step 1.2 is by input variable x1x2x3According to multi-level carry out Fuzzy processing, variable after being blurred
Variable after step 1.3 is blurred step 1.2Fuzzy reasoning is carried out, fitting per rule after fuzzy reasoning is obtained
Response αj；
Step 1.4 is to the relevance grade α per rule after fuzzy reasoningjIt is normalized, obtains every after fuzzy reasoning
Relevance grade after rule normalization
Step 1.5 is to the relevance grade per rule after normalization after fuzzy reasoningSharpening calculating is carried out, to obtain oil
Lyolysis removes the time actual value t of curdled appearancekWith the heating temperature actual value T of electric heating tubeAdd k, to realize oil water separator oil extraction
Management and control simulation is built.
Preferably, determine that the detailed process of the model parameter of Controlling model is in the step 2：
Step 2.1 set error cost function, with calculate fuzzy neural network real output value and desired output it
Between gap；
The error cost function that step 2.2 is obtained based on step 2.1 utilizes the learning algorithm and gradient of error back propagation
Descent method adjusts model parameter, so that the real output value of fuzzy neural network, close to desired output, model parameter includes net
Network consequent connection weight wijWith the central point c of membership functionijWith the width δ of membership functionij。
Present invention simultaneously discloses a kind of oil water separator oil exit pipe control system of above-mentioned control method, the control systems
Including STM32 modules, STM32 module inputs are electrically connected the liquid level sensor for liquid level signal in collection tube, Yi Ji electricity
Property temperature sensor of the connection for temperature signal in collection tube；STM32 module output ends are electrically connected light emitting diode, oil extraction
Pump and electric heating tube.
(3) advantageous effect
The present invention has following advantageous effect：
1) compared with traditional swill separator oil exit pipe control system, oil water separator oil exit pipe controlling party of the invention
Method is not to depend on the time, but depend on liquid level for the control of oil drain pump with system, this, which means that, only works as oil mass
When reaching discharge standard amount, oil drain pump can just be opened, and save the energy；
2) traditional swill separator oil exit pipe control system can not measure oil exit pipe has arranged how much oil, if be responsible for below
The oil drum for connecing oil is full, and oil exit pipe still can carry out oil extraction in required time, causes the spilling of oil；And oil water separator of the present invention
Oil exit pipe control system is able to detect that the oil drain quantity of oil exit pipe, STM32 modules can count the work times of oil drain pump,
When number reaches certain value, illustrate that oil drain quantity has arrived at the oil drum limit, STM32 modules do not retransmit drive signal drive at this time
Dynamic oil drain pump, while alarm signal is sent to light emitting diode, so that light emitting diode is always on alarm, staff is reminded more to change oil
Bucket；
3) when weather cold, the oil being stored in traditional oil pipe can solidify, if opening valve at this time, oil can not
Discharge；And oil water separator oil exit pipe control method of the present invention and system can heat oil exit pipe, and utilize fuzzy god
Measurement result through network control algorithm cooperation temperature sensor is precisely controlled time and the temperature of heating, the heating not only having had
Effect, and save the energy；
4) due to the specific heat capacity of different liquids difference, the time for being heated to same temperature is different, according to this
One characteristic, present system and method according to liquid in oil exit pipe be heated to a certain temperature used in the time judge this liquid
Water content size judges whether equipment occurs event indirectly by comparing the size of difference DELTA t and given threshold t' that is, in step 5
Barrier, if breaking down, alarms.
Description of the drawings
Fig. 1 is oil water separator oil exit pipe control method schematic diagram；
Fig. 2 is oil water separator oil exit pipe control system schematic diagram.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The present invention provides a kind of oil water separator oil exit pipe control method based on fuzzy neural network, control method master
To use oil drain pump on-off action and the electric heating tube work of Fuzzy Neural-network Control oil water separator oil exit pipe.
Referring to Fig. 1, the oil water separator oil exit pipe control method based on fuzzy neural network specifically includes following methods step
Suddenly：
Step 1 is based on fuzzy neural network algorithm, builds the oil water separator oil exit pipe control based on fuzzy neural network
Model；
In the algorithm, fuzzy neural network is divided into five layers, i.e., input layer, hidden layer, fuzzy reasoning layer, normalization layer and
Output layer realizes building for oil exit pipe Controlling model by above-mentioned five layers, in step 1, builds the oil based on fuzzy neural network
The detailed process of separator oil exit pipe Controlling model is：
Step 1.1 sets the input layer of fuzzy neural network, determines that the input of oil water separator oil exit pipe Controlling model becomes
Amount；
The input layer of fuzzy neural network is x=[x1,x2,x3]T, wherein x1For fluid temperature T in pipeLiquid, x2For liquid in pipe
Position VLiquid,x3For the time interval t heated apart from last timeEvery, the effect of input layer is to receive input variable x1x2x3And by above-mentioned input
Hidden layer of the variable transferring to fuzzy neural network.
Step 1.2 is in hidden layer by input variable x1x2x3According to multi-level carry out Fuzzy processing, after obtaining blurring
Variable
The hidden layer of fuzzy neural network, is also referred to as blurred layer.
Calculate input variable x1x2x3Affiliated linguistic variable membership functionVariable after being blurredWherein, i=1,2,3；J=1,2 ..., 7；Fluid temperature T in the pipe that input layer is passed overLiquid, liquid level V in pipeLiquidWith
Time interval t apart from last time heatingEveryCarry out Fuzzy processing.
Such as：Respectively by input variable x1x2x3It is fuzzy to turn to seven ranks, fuzzy set be NB, NM, NS, Z, PS, PM,
PB}.Therefore, it obscures when turning to seven ranks, the network node of hidden layer has 21.
Select Gaussian membership function pairIt is solved, solution formula is：
In formula (1)：cijIndicate the center of membership function, δijIndicate the width of membership function.
Step 1.3 is in fuzzy reasoning layer, variable after being blurred to hidden layerFuzzy reasoning is carried out, fuzzy reasoning is obtained
Fitness α per rule afterwardsj。
The effect of fuzzy reasoning layer is variable after being blurred to hidden layerCarry out fuzzy reasoning, such as three input variables
x1x2x3It is fuzzy to turn to seven ranks, therefore the number of network node m=343 of fuzzy reasoning layer, the fuzzy rule of each node on behalf one
Then, effect is network former piece for matching fuzzy rule, and the relevance grade after fuzzy reasoning per rule is：
J=1 in formula, 2 ... m, i1∈ { 1,2 ... 7 }, i2∈ { 1,2 ... 7 }, i3∈{1,2…7}。
Step 1.4 is normalized the relevance grade per rule after fuzzy reasoning, obtains mould in normalizing layer
Relevance grade after paste reasoning per rule after normalization
Herein, normalization layer is identical as the number of network node of fuzzy reasoning layer, equal m=343, and normalization layer is accomplished that
Normalization calculates, and obtains the relevance grade per rule after normalization after fuzzy reasoning
Step 1.5 is in output layer, to the relevance grade per rule after normalization after fuzzy reasoningCarry out sharpening meter
It calculates, to obtain the time actual value t that fluid releases curdled appearancekWith the heating temperature actual value T of electric heating tubeAdd k, to realize oil
Separator oil exit pipe Controlling model is built.Wherein, fluid releases the time actual value t of curdled appearancekRefer to oil water separator not
In the case of breaking down, fluid releases the actual value of curdled appearance time.
Formula is used by above-mentioned sharpening calculates：
Wherein t is that fluid releases setting time, i.e., when the oil in oil pipe is free from foreign meter, liquid is heated to from curdled appearance
State need time, such as set when fluid temperature as 20 degrees Celsius when release curdled appearance completely, oil extraction will not be caused
It influences；TAddFor the heating temperature of electric heating tube.
By above formula (4) and (5) it can be seen that the output of system is the weighted sum of network consequent (Consequent), and weights
Item is the relevance grade per rule after normalization after fuzzy reasoningWhat fuzzy neural network mainly learnt is the company of network consequent
Connect weight wijWith the central point c of membership functionijWith the width δ of membership functionij。
Step 2, the oil water separator oil exit pipe Controlling model established to step 1 are trained, and determine above-mentioned Controlling model
Model parameter, model parameter includes network consequent connection weight wijWith the central point c of membership functionijAnd membership function
Width δij。
In fuzzy neural network to network consequent connection weight wijWith the central point c of membership functionijAnd membership function
Width δijTraining process in, include the following steps；
Step 2.1 sets error cost function；
Herein, error cost function includes the first error cost function E, the second error cost function E1With third error generation
Valence function E2, fluid is established by above 3 error cost functions and releases setting time desired value tdk, electric heating tube heating temperature
Spend desired value TAdd dk, fluid release curdled appearance time actual value tkWith the heating temperature actual value T of electric heating tubeAdd kPass
System, to calculate the gap between the reality output of fuzzy neural network and desired output.Above-mentioned 3 error cost functions are specifically public
Formula is：
E=0.5 [(tdk-tk)2+(TAdd dk-TAdd k)2] (6)
E1=0.5 (tdk-tk)2 (7)
E2=0.5 (TAdd dk-TAdd k)2 (8)
Wherein, tdkFor oil-water separator failsafe when, fluid release setting time desired value；
TAdd dkFor the heating temperature desired value of electric heating tube；
tkFor oil-water separator failsafe when, fluid release curdled appearance time actual value；
TAdd kFor the heating temperature actual value of electric heating tube；
The error cost function that step 2.2 is obtained based on step 2.1 utilizes the learning algorithm and gradient of error back propagation
Descent method adjusts model parameter, so that the real output value of fuzzy neural network, close to desired output, model parameter includes net
Network consequent connection weight wijWith the central point c of membership functionijWith the width δ of membership functionij.Utilize error back propagation
Learning algorithm calculateW is adjusted using gradient descent methodij,WithThen network consequent connects
Weight wijWith the central point c of membership functionijWith the width δ of membership functionijAdjustment algorithm be：
I=1,2,3 in formula (9)；J=1,2 ... m；β1,β2,β3,β4For learning rate.
In training process, by error cost function so that the above-mentioned actual value of fuzzy neural network is more close to expectation
Value.I.e. when fuzzy neural network actually enters numerical value, network consequent connection weight w is changed by trainingijAnd membership function
Central point cijWith the width δ of membership functionij, keep error cost function smaller and smaller, final actual value reaches desired value.
The process can pass through the oil exit pipe Oil-temperature control being programmed to based on fuzzy neural network to STM32 modules.
Step 3, acquisition oil exit pipe current detection data, the oil water separator oil exit pipe Controlling model determined using step 2,
Oil exit pipe current detection data are diagnosed, the oil extraction to export oil exit pipe controls current value.
Herein, oil exit pipe current detection data include current level in current liquid temperature and pipe in pipe.Using liquid level
Current level in sensor collection tube, using current liquid temperature in temperature sensor collection tube, and using in STM32 modules
Timer calculates the current time interval heated apart from last time.Current value, including fluid are controlled by the way that oil extraction is calculated above
Release the heating temperature current value T of the time current value t and electric heating tube of curdled appearance, wherein fluid releases curdled appearance
Time current value t is to be heated to the time that liquid condition needs from curdled appearance when the oil in oil pipe is free from foreign meter.
In step 4, the fluid heating process in oil exit pipe, the current liquid temperature in oil extraction control current value is constantly judged
Whether degree reaches liquid melt temperature TMeltIf judging result is no, return to step 3；If the determination result is YES, then stop heating
And record current heating time tIt is real。
Herein it should be noted that in above-mentioned deterministic process, if whether current liquid temperature reaches liquid melt temperature
TMelt, such as liquid melt temperature TMeltWhen being 20 DEG C, show that solidification phenomenon has released, stops heating at this time.
Step 5 judges | t-tIt is real| whether it is more than given threshold t'；If the determination result is YES, then fault alarm is sent out；If sentencing
Disconnected result is no, then return to step 3.
In steps of 5, it needs to calculate the time current value t of fluid releasing curdled appearance and current heating time t realities first
Between difference DELTA t, i.e.,：
Δ t=| t-tIt is real| (10)
Further judge, the size of difference DELTA t and given threshold t', if Δ t ＜ t', return to step 3 continue with
The oil water separator oil exit pipe Controlling model that step 2 determines, diagnoses oil exit pipe current detection data.If Δ t ＞ t', say
Bright water-oil separating efficiency is too low, and the liquid water content in oil pipe is larger, since water is different with the specific heat capacity of oil, in liquid
Water content can influence the time that liquid in pipe is heated to some temperature, as Δ t ＞ t', show that equipment needs repairing, at this time
Equipment blinking light emitting diode, sends out alarm signal.
By above-mentioned steps 2 it is found that the oil water separator oil exit pipe Controlling model that the present invention is built, input parameter is oil exit pipe
Current detection data, output parameter are that oil extraction controls current value.More than, it is controlled by oil water separator oil exit pipe shown in Fig. 2
System realizes that core, STM32 module inputs electrically connect oil water separator oil exit pipe control system in order to control with STM32 modules
The liquid level sensor for liquid level signal in collection tube is connect, and is electrically connected the temperature sensing for temperature signal in collection tube
Device；STM32 module output ends are electrically connected light emitting diode, oil drain pump and electric heating tube, to control light emitting diode alarm, with
And control oil drain pump on-off action and electric heating tube work.
Above-mentioned control system, by receiving current level in liquid level sensor collection tube, liquid level sensor passes sequentially through the
One signal amplifier, the first A/D converter and STM32 module inputs are electrically connected.Control system is by receiving level sensing
Current level in device collection tube, temperature sensor pass sequentially through second signal amplifier, the second A/D converter and STM32 modules
Input terminal is electrically connected.STM32 module output ends pass sequentially through the first D/A converter, the first signal amplifier connection oil drain pump,
To control oil drain pump oil extraction work.The second D/A converter, second signal amplifier connection electricity add STM32 modules output end successively
Heat pipe, to control electric heating tube work.
The specific work process of oil water separator oil exit pipe control system is combined with Figure 1 and Figure 2,：
Liquid level signal in collected pipe is converted to voltage signal by liquid level sensor, after the amplification of the first signal amplifier
Incoming first A/D converter is converted to liquid level digital quantity and is transmitted to STM32 modules.STM32 modules are to transmitting the liquid level number come
Word amount is identified, and when liquid level digital quantity reaches level set value, STM32 modules send out drive signal and converted to the first D/A
Drive signal is converted into analog quantity by device, the first D/A converter from digital quantity again, and the final signal is put by the first signal amplifier
Greatly and input oil drain pump driving oil extraction pump work oil extraction.STM32 modules can count the work times of oil drain pump, work as number
When reaching certain value, illustrate that oil drain quantity has arrived at the oil drum limit, STM32 modules do not retransmit drive signal driving oil extraction at this time
Pump, while alarm signal is sent to light emitting diode, so that light emitting diode is always on alarm, staff is reminded to replace oil drum, with
Oil spill in anti-oil drum goes out.
Fluid temperature signal in collected pipe is converted into voltage signal by temperature sensor, is put through second signal amplifier
Incoming 2nd A/D sensors are converted to temperature digital amount and are transmitted to STM32 modules after big.Liquid in STM32 module combination pipes
In temperature, pipe liquid level signal and apart from last time heating time interval with above-mentioned steps 1- steps 5 fuzzy neural network into
Row calculates, to control the heating time of electric heating tube.Output quantity is in the heating temperature and oil pipe of temperature-controllable electric heating pipe
When oil is free from foreign meter, fluid releases the time current value of curdled appearance.After operation, STM32 modules start timing, and will calculate
The heating temperature of gained exports to the 2nd D/A conversion modules and is converted to analog quantity.Then, the 2nd D/A conversion modules are by temperature
Signal transmission is amplified to second signal amplifier, gives amplified rear signal transmission to temperature-controllable electric heating pipe, electrical heating
Pipe heats liquid according to input signal, and fluid temperature is regulated and controled to liquid melt temperature TMelt, liquid melt temperature TMeltReason
Think that value is 20 degrees Celsius.After heating, STM32 modules cut off the signal for giving temperature sensor, and judge that fluid releases
The time current value t and current heating time t of curdled appearanceIt is realBetween difference DELTA t whether exceed given threshold t', if it exceeds
Given threshold t' then illustrates that failure has occurred in equipment, and STM32 modules control light emitting diode alarm, if being not above setting
Threshold value t', then timer start reclocking, for next time heating prepare.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
Understanding without departing from the principles and spirit of the present invention can carry out these embodiments a variety of variations, modification, replace
And modification, the scope of the present invention is defined by the appended.
Claims (4)
1. a kind of oil water separator oil exit pipe control method based on fuzzy neural network, it is characterised in that include the following steps：
Step 1 is based on fuzzy neural network algorithm, builds the oil water separator oil exit pipe based on fuzzy neural network and controls mould
Type；
Step 2, the oil water separator oil exit pipe Controlling model established to step 1 are trained, and determine the model ginseng of Controlling model
Number；
Step 3, acquisition oil exit pipe current detection data, the oil water separator oil exit pipe Controlling model determined using step 2, to row
Oil pipe current detection data are diagnosed, and the oil extraction to export oil exit pipe controls current value, and it includes fluid that oil extraction, which controls current value,
Release the time current value t and heating temperature current value T of curdled appearance；
Step 4 judges whether current liquid temperature reaches liquid melt temperature TMeltIf judging result is no, return to step 3；
If the determination result is YES, then stop heating and recording current heating time tIt is real；
Step 5 judges | t-tIt is real| whether it is more than given threshold t'；If the determination result is YES, then fault alarm is sent out；If judging knot
Fruit is no, then return to step 3.
2. the oil water separator oil exit pipe control method according to claim 1 based on fuzzy neural network, feature exist
In：The step 1 establishes the step of oil water separator oil exit pipe Controlling model and is：
Step 1.1 determines the input variable x of oil water separator oil exit pipe Controlling model1x2x3, x1For fluid temperature T in pipeLiquid, x2For
Liquid level V in pipeLiquid,x3For the time interval t heated apart from last timeEvery；
Step 1.2 is by input variable x1x2x3According to multi-level carry out Fuzzy processing, variable after being blurred
Variable after step 1.3 is blurred step 1.2Fuzzy reasoning is carried out, the fitness of every rule after fuzzy reasoning is obtained
αj；
Step 1.4 is to the relevance grade α per rule after fuzzy reasoningjIt is normalized, obtains every rule after fuzzy reasoning
Relevance grade after normalization
Step 1.5 is to the relevance grade per rule after normalization after fuzzy reasoningSharpening calculating is carried out, to obtain fluid solution
Except the time actual value t of curdled appearancekWith the heating temperature actual value T of electric heating tubeAdd k, to realize oil water separator oil extraction management and control
Simulation is built.
3. the oil water separator oil exit pipe control method according to claim 1 based on fuzzy neural network, feature exist
In：Determine that the detailed process of the model parameter of Controlling model is in the step 2：
Step 2.1 sets error cost function, to calculate the gap between the reality output of fuzzy neural network and desired output；
The error cost function that step 2.2 is obtained based on step 2.1 is declined using the learning algorithm and gradient of error back propagation
Method adjusts model parameter, so that the real output value of fuzzy neural network is close to desired output.
4. a kind of oil water separator oil exit pipe control system of control method described in claim 1, it is characterised in that：The control
System includes STM32 modules, and STM32 module inputs are electrically connected the liquid level sensor for liquid level signal in collection tube, with
And it is electrically connected the temperature sensor for temperature signal in collection tube；STM32 module output ends electric connection light emitting diode,
Oil drain pump and electric heating tube.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810174436.0A CN108334714B (en) | 2018-03-02 | 2018-03-02 | Oil-water separator oil discharge pipe control system and method based on fuzzy neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810174436.0A CN108334714B (en) | 2018-03-02 | 2018-03-02 | Oil-water separator oil discharge pipe control system and method based on fuzzy neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108334714A true CN108334714A (en) | 2018-07-27 |
| CN108334714B CN108334714B (en) | 2021-08-17 |
Family
ID=62930223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810174436.0A Active CN108334714B (en) | 2018-03-02 | 2018-03-02 | Oil-water separator oil discharge pipe control system and method based on fuzzy neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108334714B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111007750A (en) * | 2018-10-08 | 2020-04-14 | 上海洁鹿环保科技有限公司 | Oil-water separation system data processing method and device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3928788B2 (en) * | 2002-07-19 | 2007-06-13 | エネビー・カワテック株式会社 | Oil / water separation and recovery equipment |
| WO2014168996A1 (en) * | 2013-04-09 | 2014-10-16 | Schlumberger Canada Limited | Simulation of production systems |
| CN104280430A (en) * | 2014-10-14 | 2015-01-14 | 西安理工大学 | Device and method for measuring water content in crude oil |
| CN107352593A (en) * | 2017-08-21 | 2017-11-17 | 谢建新 | A kind of kitchen garbage separation for preventing and treating gutter oil and monitoring system and method |
-
2018
- 2018-03-02 CN CN201810174436.0A patent/CN108334714B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3928788B2 (en) * | 2002-07-19 | 2007-06-13 | エネビー・カワテック株式会社 | Oil / water separation and recovery equipment |
| WO2014168996A1 (en) * | 2013-04-09 | 2014-10-16 | Schlumberger Canada Limited | Simulation of production systems |
| CN104280430A (en) * | 2014-10-14 | 2015-01-14 | 西安理工大学 | Device and method for measuring water content in crude oil |
| CN107352593A (en) * | 2017-08-21 | 2017-11-17 | 谢建新 | A kind of kitchen garbage separation for preventing and treating gutter oil and monitoring system and method |
Non-Patent Citations (2)
| Title |
|---|
| ALI RABBANI 等: "Estimating temperature of the outlet water of cooling system of gas turbine V94.2 using fuzzy neural network", 《2015 INTERNATIONAL CONGRESS ON ELECTRIC INDUSTRY AUTOMATION (ICEIA 2015)》 * |
| 王勇 等: "电动提升模板系统关键零部件参数分析与优化", 《机械工程师》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111007750A (en) * | 2018-10-08 | 2020-04-14 | 上海洁鹿环保科技有限公司 | Oil-water separation system data processing method and device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108334714B (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105095963B (en) | A kind of Precise Diagnosis and the method for prediction wind-tunnel facilities failure | |
| CN105512448B (en) | A kind of appraisal procedure of power distribution network health index | |
| CN110335270A (en) | Transmission line of electricity defect inspection method based on the study of hierarchical regions Fusion Features | |
| Sun et al. | Multiple model combination methods for annual maximum water level prediction during river ice breakup | |
| CN102013148B (en) | Multi-information fusion fire hazard detection method | |
| CN104318347A (en) | Power transmission line icing state assessment method based on information fusion of multiple sensors | |
| CN102866321A (en) | Self-adaptive stealing-leakage prevention diagnosis method | |
| CN104318485A (en) | Power transmission line fault identification method based on nerve network and fuzzy logic | |
| CN1683254A (en) | Intelligent monitoring and control method for coagulation process based on multisource information fusion technology | |
| CN107247653A (en) | A kind of Fault Classification and device of data center's monitoring system | |
| CN107784395A (en) | A kind of electric power line ice-covering thickness Forecasting Methodology based on LSTM artificial neural networks | |
| CN106600509A (en) | Method for determining water-mixed sewage discharge behavior of enterprise based on basic data analysis | |
| CN108510072A (en) | A kind of discharge of river monitoring data method of quality control based on chaotic neural network | |
| CN105182141A (en) | Transformer fault detection method and system | |
| CN108334714A (en) | Oil water separator oil exit pipe control system based on fuzzy neural network and method | |
| CN108090677A (en) | A kind of critical infrastructures reliability assessment method | |
| CN110738429A (en) | electric energy meter state evaluation method and device | |
| CN104536970A (en) | Fault determining and classifying system and method for remote communication data device | |
| CN115423301A (en) | Intelligent electric power energy management and control method, device and system based on Internet of things | |
| CN105568732A (en) | Disc mill control method | |
| CN115470850A (en) | Water quality abnormal event recognition early warning method based on pipe network water quality time-space data | |
| CN117277958B (en) | Intelligent operation and maintenance management method and system for photovoltaic power station based on big data | |
| CN106998064B (en) | A kind of cascading failure fault chains searching method | |
| CN107808209A (en) | Abnormal data of wind power plant discrimination method based on weighting kNN distances | |
| CN107423811A (en) | The streamflow change attribution recognition methods combined based on BP artificial neural networks and Scene Simulation |
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 |