CN114019846A - Intelligent ventilation control design method and system for long road tunnel - Google Patents
Intelligent ventilation control design method and system for long road tunnel Download PDFInfo
- Publication number
- CN114019846A CN114019846A CN202111195013.5A CN202111195013A CN114019846A CN 114019846 A CN114019846 A CN 114019846A CN 202111195013 A CN202111195013 A CN 202111195013A CN 114019846 A CN114019846 A CN 114019846A
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- control
- tunnel
- variable
- input
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 118
- 238000009423 ventilation Methods 0.000 title claims abstract description 72
- 238000013461 design Methods 0.000 title claims abstract description 20
- 230000009471 action Effects 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 79
- 230000001105 regulatory effect Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000006866 deterioration Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 14
- 230000006872 improvement Effects 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 11
- 238000013528 artificial neural network Methods 0.000 description 10
- 230000008859 change Effects 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 238000011160 research Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000013139 quantization Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 5
- 239000000779 smoke Substances 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 4
- 230000001276 controlling effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000003344 environmental pollutant Substances 0.000 description 4
- 231100000719 pollutant Toxicity 0.000 description 4
- 238000003786 synthesis reaction Methods 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 239000000356 contaminant Substances 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000011217 control strategy Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000007865 diluting Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0423—Input/output
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21F—SAFETY DEVICES, TRANSPORT, FILLING-UP, RESCUE, VENTILATION, OR DRAINING IN OR OF MINES OR TUNNELS
- E21F1/00—Ventilation of mines or tunnels; Distribution of ventilating currents
- E21F1/003—Ventilation of traffic tunnels
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/25—Pc structure of the system
- G05B2219/25257—Microcontroller
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an intelligent ventilation control design method and system for a long road tunnel, which comprises a measuring device, a fuzzy controller and an actuator, wherein the measuring device is used for detecting information parameters which can be used for ventilation control in the long road tunnel and transmitting the information parameters to the fuzzy controller; the fuzzy controller is used for converting an input accurate quantity into a fuzzy quantity by defining linguistic variables on an input domain, then obtaining a fuzzy control quantity through fuzzy reasoning, converting the fuzzy control quantity into an actual control quantity through defuzzification, and outputting the actual control quantity to the actuator; the actuator is used for exerting a control action on the controlled object so as to regulate and control the air volume in the long road tunnel. By adopting the feed-forward control scheme based on the fuzzy theory, the invention can effectively improve the air circulation efficiency for the tunnel operation management, realizes the rapid ventilation in advance, and has obvious improvement on the energy-saving and security protection effects compared with the traditional control mode.
Description
Technical Field
The invention relates to the technical field of road traffic, in particular to an intelligent ventilation control design method and system for a long road tunnel.
Background
A control method for air quality in long tunnel on highway includes such steps as direct step control method, indirect control method, program control method and combined control method, which includes detecting the concentration values of CO and VI by sensors in tunnel, calculating, controlling, and operating the start-stop state of blower to supplement fresh air for tunnel for diluting CO and VI. The direct stepping control method is a simple and effective control method, is a closed-loop drawing system, has well-defined controlled parameter range, and is widely applied to the currently established tunnels in China. However, the direct stepping control method has the disadvantages that certain delay exists, the controlled quantity is not a fixed value, the control of the fan is discontinuous, the static deviation in the control process is large, and the like.
The indirect control method is an open-loop control system, the input quantity of which is the parameters of vehicle type, traffic quantity, vehicle speed average value and the like in the tunnel, the CO and VI concentration values are calculated after optimization processing, and the operation state of the fan is output by comparing the CO and VI concentration values with a set standard value. The indirect control method uses the traffic volume as the controlled volume, and because the relationship between the traffic volume and the concentration values of CO and VI is changed at any time, a conversion coefficient or a correction coefficient must be added in the calculation process when the method is used, however, the correction coefficient in the algorithm needs to be determined by combining with specific engineering projects and cannot be widely transplanted, so the method is greatly limited in the actual engineering. In view of the current situation in China, the method is not suitable for being used alone, but can still be used as a temporary downshift when a sensor fails or be used together with a combined control method. Based on the relevant data, this method is applied in some developed countries abroad. As China considers some differences among own objective conditions, the method is not simply used for reference. Firstly, the structure of the vehicles in China is complex, the difference of the pollution discharge capacity of the vehicles is large, and the vehicle conditions are poor, so that the relation between the traffic volume and the pollution discharge volume is difficult to determine; secondly, the highway business of China is in the period of high-speed development, but the technical and economic levels do not reach a relatively stable high-level stage, and even if the method is adopted, some correlation coefficients are difficult to determine.
The program control method is established on the basis of empirical data obtained through statistics, controls the starting and stopping states of the fan and is essentially sequential control. The method saves the cost of a detection link and can be used as a downshift standby when the main control system has faults. The method is characterized in that a program is programmed in advance according to the requirement of a time interval to control the change of the starting and stopping states of the fan, and the change of a CO concentration value, a VI concentration value and traffic volume is not considered. The method has a complete control strategy, but needs to correct various parameters of the tunnel ventilation system after the tunnel ventilation system normally operates for a period of time, and is similar to a trial and error method, the method lacks a predictive control function, the change process is complex after the time sequence of the method is determined, but the traffic flow and other parameters are continuously changed in the operation process of the tunnel.
The control idea of the combined control method is to utilize the traffic flow information, the CO concentration value, the VI concentration value and the like measured by the sensors to control the starting and stopping states of the fan through the calculation analysis processing of the master controller. The advantages of this control method are: firstly, the CO concentration value and the VI concentration value detected by the sensor are utilized to complete direct control in a feedback mode, so that the reliable stability of the system is ensured; and secondly, the timeliness and the robustness of the system are ensured by detecting the traffic data and performing predictive control. Although the combined control method has more advantages in theory, when the combined control method is applied to a road tunnel ventilation system with strong nonlinear characteristics, accurate establishment of a mathematical model is difficult, so that the method is greatly limited in practical application. Although the foreign engineering project is also provided with individual success, the method is not suitable for large-scale popularization, and the method is not effectively popularized and utilized in China.
In short, the traditional control method is relatively rarely applied in the ventilation field of tunnel engineering in China due to the hysteresis of the traditional control method. Because the traditional control method cannot make timely and reasonable response according to the change of the external environment to a great extent, the best effect of tunnel ventilation cannot be achieved, and the competitiveness in the aspects of economy, safety and environmental protection is lacked.
The main methods existing in the automatic control of the ventilation of the highway tunnels at home and abroad at present are a feedback control method (FB), a recently proposed feedforward control method (FF) and a modern control method. The feedback control method is that the concentration of CO and the concentration of VI in the tunnel are detected by a sensor, and after calculation and processing, a control instruction is given to control the operation of a fan, supply necessary fresh air quantity and dilute the concentration of VI and CO, so as to reach the sanitary and safety standard of the design requirement. The method is to control according to the deviation of the controlled object and finally eliminate the deviation. Because the control action lags behind the interference action, the static deviation in the control process is large, and the control is not timely. In the seventies, the control method is adopted by the German New Yibei river tunnel.
The feedforward method is to add feedforward control on the basis of feedback control to solve the untimely time in the feedback control. The feed-forward control is to know the traffic volume, the driving speed, the vehicle composition and the like in the tunnel in real time according to the traffic volume information of the front section entering the tunnel and a vehicle detector buried under the road surface, predict and calculate the VI and CO discharge amount of the vehicle in advance by detecting the traffic volume condition, and implement air volume control. The method starts from the polluted traffic flow, changes the number of the fans to compensate the output change caused by disturbance, and keeps the controlled variable basically unchanged. The feedforward control is timely and is not influenced by system delay, and the control precision is improved. The first method used was the japanese tunnel shut-in delivered in 1984, which determined the normal ventilation flow based on the long-term predicted possible traffic flow as the standard control location for the ventilation system, and modified the ventilation flow as a function of the harmful gas concentration and the short-term predicted traffic flow. At present, the method is still widely adopted by developed countries, and the method is also widely adopted by road tunnel ventilation control in China. The feedforward method makes up the defects of the feedback control method, and is suitable for long and large tunnels with a large number of fans and complex ventilation modes.
Modern control methods mainly include fuzzy control, neural network control, expert control, and the like. The road tunnel ventilation system is a typical distributed parameter system and has strong nonlinear characteristics, and if a traditional linear control theory is used, in order to obtain a mathematical model which is convenient for control design, a great error must be introduced in the model simplification process, so research focuses by domestic and foreign scientific research institutions on modern control algorithms such as fuzzy control, neural network control and the like.
The origin of the fuzzy technology is traced back to 1965, when the university of california, berkeley, university, usa, controls theory expert l.a.zadeh, proposed a fuzzy aggregation theory, which mainly includes: the contents of fuzzy set theory, fuzzy logic, fuzzy reasoning, fuzzy control and the like lay the theoretical foundation for the generation of fuzzy technology. In 1974, british scholars e.h.mamdani first realized fuzzy control on steam engines in a laboratory and achieved better effects than the traditional direct digital control algorithm, so that a brand-new control technology, namely fuzzy control, appeared. The structure of the fuzzy control is shown in the figure. The fuzzy control system is an intelligent control system which is based on a fuzzy set theory, fuzzy linguistic variables and fuzzy logic reasoning and combines an expert system and a control theory based on rules, and is a digital control system which is formed by adopting a computer control technology and has a closed loop structure of a feedback channel. Thus, compared with the conventional control system, the following advantages are provided:
firstly, fuzzy control is completely to realize the control of the system on the basis of the control experience of operators, does not need to establish an accurate mathematical model of a control object, and is an effective way to solve the uncertain system.
Secondly, the fuzzy control has stronger robustness, the influence of the change of the controlled object parameter on the fuzzy control is not obvious, and the method is particularly suitable for the control of nonlinear, time-varying and lagging systems.
And thirdly, obtaining a fuzzy control rule query table through off-line calculation, thereby improving the control real-time performance of the control system.
And fourthly, the control mechanism conforms to the intuitive description and thinking logic of people on the process control action, and lays a foundation for intelligent control application.
However, fuzzy control also has the following major drawbacks:
the fuzzy processing with simple information will cause the control precision of the system to be reduced and the dynamic quality to be deteriorated. If the precision is improved, the quantization series is inevitably increased, so that the rule searching range is enlarged, the decision speed is reduced, and even the control cannot be carried out in time.
Secondly, the design of fuzzy control is lack of systematicness, and a control target cannot be defined. The selection of control rules, the selection of discourse domain, the definition of fuzzy set, the selection of quantization factor and the like mostly adopt trial and error method, which is hard to be effective for the control of complex system.
Disclosure of Invention
The invention provides a method and a system for designing intelligent ventilation control of a long road tunnel, aiming at solving the technical problems that: the technical problem of poor air quality control effect in long road tunnels.
In view of the above problems of the prior art, according to one aspect of the present disclosure, the following technical solutions are adopted:
a long tunnel intelligent ventilation control system of highway, it includes:
the measuring device is used for detecting information parameters which can be used for ventilation regulation and control in the long tunnel of the road and transmitting the information parameters to the fuzzy controller;
the fuzzy controller is used for converting the input accurate quantity into a fuzzy quantity by defining linguistic variables on an input domain, then obtaining a fuzzy control quantity by fuzzy reasoning, converting the fuzzy control quantity into an actual control quantity by defuzzification, and outputting the actual control quantity to the actuator;
and the actuator is used for exerting a control action on the controlled object so as to regulate and control the air volume in the long road tunnel.
Further, the controlled object comprises various jet flow fans arranged in the tunnel.
Further, the measuring device comprises a CO/VI detector, a wind speed and direction detector and a vehicle detector.
Further, the fuzzy controller includes:
and the fuzzification module is used for defining a linguistic variable aiming at each input space of the fuzzy controller, then defining the domain of each linguistic variable, defining the linguistic value of each linguistic variable, and defining the domain of each linguistic variable as the membership function of the linguistic value.
A knowledge base containing knowledge in the application domain and required control targets;
the fuzzy reasoning module deduces the implied fuzzy relation from the rules in the rule base, and carries out reasoning according to the fuzzy relation and the input condition to obtain an output language value;
the defuzzification module is used for converting the fuzzy control quantity into a clear quantity which is represented in the range of the domain of discourse after the defuzzification conversion; and then the clear quantity in the range of the domain of interest is converted into an actual control quantity through scaling.
Further, fuzzy reasoning in the fuzzy controller is to obtain the control quantity through a table look-up method.
In order to better realize the invention, the further technical scheme is as follows:
a method for controlling the feedforward fuzzy intelligent ventilation of a long road tunnel comprises the following steps:
step S1: detecting information parameters which can be used for ventilation regulation and control in a long tunnel of a road, and transmitting the information parameters to the fuzzy controller;
step S2: the method comprises the steps of defining linguistic variables on an input domain, converting input accurate quantity into fuzzy quantity, then obtaining fuzzy control quantity through fuzzy reasoning, converting the fuzzy control quantity into actual control quantity through defuzzification, and outputting the actual control quantity to an actuator;
step S3: and applying a control action to the controlled object to regulate and control the air volume in the long tunnel of the road.
Further, in the step S1, the information parameters include the influence parameters of the lighting, ventilation and traffic control in the tunnel, and the traffic flow and the traffic history information in the tunnel, and the traffic flow information of the tunnel group and the adjacent tunnel.
Further, in step S2, two input variables defined are CO and VI, one output variable is FanNum, and a membership function editor is associated with each variable, where the input variables adopt triangular membership functions and the output variables adopt gaussian membership functions.
Further, under the condition that the tunnel pollution condition is deteriorated, the actuator (1) also controls a tunnel entrance signal lamp, and the number of vehicles entering the tunnel is controlled by using the signal lamp.
The invention can also be:
a method of designing a fuzzy controller, comprising:
defining inputs and outputs of the system
Selecting the deviation e and the deviation variable delta e as the input of the system, selecting the amount of direct regulation control as the output of the system, and reducing the deviation amount of the system by regulating the regulating amount;
(ii) determining linguistic value ranges and membership functions
Analyzing the actual condition of the input and output variables of the system, determining the domain of each variable, describing each variable by using a language term, and defining the membership functions of each variable, wherein the membership functions cover the whole value range;
(iii) design control rule base
Formulating rules corresponding to the reality, classifying and sorting the rules, and expressing the rules in a fuzzy variable operation mode;
(iv) determining fuzzy inference and deblurring methods
Fuzzifying an input variable, and performing reasoning according to a fuzzy rule to obtain fuzzy output;
performing fuzzy resolving on the fuzzy output to obtain accurate output;
(v) implementation of fuzzy controller
The method is realized in a discrete mode, and a control lookup table is manufactured according to rules;
(vi) optimizing the fuzzy controller
And optimizing the fuzzy controller according to the control performance.
Compared with the prior art, the invention has the following beneficial effects:
the invention realizes energy saving and emission reduction under low risk by an effective algorithm in cooperation with hardware deployment and software implementation, and the implementation does not influence the safety and stability of tunnel operation and reduce traffic efficiency; the automation and the intellectualization of the tunnel energy efficiency management are realized, the air circulation efficiency can be effectively improved for the tunnel operation management, the rapid ventilation in advance is realized, and the energy-saving and security protection effects are remarkably improved compared with the traditional control mode.
Drawings
For a clearer explanation of the embodiments or technical solutions in the prior art of the present application, the drawings used in the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only references to some embodiments in the present application, and other drawings can be obtained by those skilled in the art without inventive efforts.
FIG. 1 is a schematic diagram of a fuzzy control system according to one embodiment of the present invention.
FIG. 2 is a diagram illustrating the shape and membership function distribution of a Gaussian function according to an embodiment of the present invention.
FIG. 3 is a diagram illustrating fuzzy inference control analysis, according to an embodiment of the present invention.
FIG. 4 shows Δ c according to an embodiment of the inventionCOGraph of membership function for concentration.
FIG. 5 shows Δ c according to an embodiment of the inventionVIAnd (4) a concentration membership function diagram.
FIG. 6 is a graph of membership functions for GFANNum concentration in accordance with one embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to examples, but the embodiments of the present invention are not limited thereto.
As shown in fig. 1, the intelligent ventilation control system for the long road tunnel comprises an actuator 1, a controlled object 2, a measuring device 3 and a fuzzy controller 4; the measuring device 3 is used for detecting information parameters which can be used for ventilation regulation and control in a long road tunnel and transmitting the information parameters to the fuzzy controller 4; the fuzzy controller 4 is used for converting an input accurate quantity into a fuzzy quantity by defining linguistic variables on an input domain, then obtaining a fuzzy control quantity through fuzzy reasoning, converting the fuzzy control quantity into an actual control quantity through defuzzification, and outputting the actual control quantity to the actuator 1; the actuator 1 is used for exerting control action on the controlled object 2 so as to regulate and control air volume in the long road tunnel.
The mathematical basis for fuzzy control is fuzzy linguistic variables, fuzzy set theory, fuzzy logic, and fuzzy inference knowledge. Conceptually, fuzzy logic more closely resembles human thought and natural language than other traditional logic. The approximate and fuzzy characteristics of the research object can be characterized, and the fuzzy control is just to control the system by utilizing the intelligent characteristic of fuzzy logic. For complex objects with parameters difficult to determine, high-order or large time-varying, nonlinear, fuzzy logic control tends to have significant effects, because it can establish a special nonlinear control algorithm using fuzzy logic.
In fig. 1, the controlled object 2 is a device or an ensemble of devices that operate under certain conditions to perform a certain function. The controlled objects 2 of the ventilation control system are all jet fans in the tunnel. The actuator 1 is a device for applying a control action to a controlled object by the fuzzy controller 4. An actuator 1 in the ventilation control system is a controller which executes fuzzy control output logic and controls the start and stop of a fan. The measuring device 3 (sensor) mainly detects various non-electric quantities such as pollutant concentration, visibility, vehicle speed, light intensity, temperature and the like, and amplifies and conditions the non-electric quantities into standard signals or communication digital signals. The sensors in the ventilation control system comprise a CO/VI detector, a wind speed and wind direction detector and a vehicle detector.
The fuzzy controller is generally composed of four parts, namely a fuzzification interface, a knowledge base, a fuzzy inference engine and a defuzzification interface, and the basic functions of each woven part are as follows:
(1) fuzzification
The fuzzification functions to convert the exact quantity of an input into a fuzzy quantity by defining linguistic variables over the input domain. Wherein the input quantity comprises external reference input, system output or state, etc. The specific process comprises the following steps:
one linguistic variable is defined for each input space of the fuzzy controller. In a fuzzy control system, an error value E and an error change rate EC of the system are generally taken as two inputs of a fuzzy controller, then a linguistic variable error E is defined on E, and a linguistic variable error change EC is defined on c;
define the domain of each linguistic variable. Generally, the domains of E and EC are both set to X ═ Y { -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6 }; before the input quantity is fuzzified, the basic discourse domain of E and EC needs to be converted into the discourse domain of E and EC;
defining language value of each language variable. Typically, E and EC take on { positive, negative, positive small, zero, negative small, negative medium, negative large } ═ PB, PM, PS, ZO, NS, NM, NB };
and fourthly, defining the domain of each linguistic variable as a membership function of the linguistic value, so that the input accurate value is converted into a fuzzy linguistic value.
Membership functions may take different shapes such as triangular, trapezoidal, gaussian, bell, Z-shaped, S-shaped, etc. For engineering problems, the shape of the membership function is usually a continuous function of normal distribution, such as a gaussian function, and the formula is as follows:
in the formula, aiIs the center value of the function; biIs the width of the function.
Suppose that the center values of the gaussian functions corresponding to PB, PM, PS, ZO, NS, NM, NB are {6, 4, 2, 0, -2, -4, -6} respectively, and the widths are all 2. The shape of the gaussian function and the distribution of the membership functions are as shown in fig. 2.
In FIG. 2, NM, NS, ZO, PS, PM, PB, etc. are the labels of fuzzy sets in the domain of discourse, with the following meanings:
NB is a large Negative bias (Negative Big);
NM is the deviation in the Negative direction (Negative Medium);
NS is a Small Negative deviation (Negative Small);
ZO-Zero deviation (Zero);
PS (Positive Small) with a Small deviation in the Positive direction;
PM (Positive Medium) deviation in the Positive direction;
PB is a large Positive deviation (Positive Big).
(2) Knowledge base
The knowledge base contains the control objectives of the knowledge and requirements in the application domain. Usually consists of two parts, a database and a rule base.
The database mainly comprises membership functions of all linguistic variables, scale transformation factors, fuzzy space grading numbers and the like.
The rule base includes a series of control rules expressed in fuzzy linguistic variables.
The rule base consists of several control rules, which are derived from the experience summary of human control experts and are expressed in the form of IF... is... and.. is... then.. is …. If the rule base has n rules, it can be written as:
R1：IF E is A1 AND EC is Bl THEN U is Cl
R2：IF E is A2 AND EC is B2 THEN U is C2
…………………………………………………
Rn：IF E is An AND EC is Bn THEN U is Cn
wherein E, EC are linguistic variables "error", "error change rate"; u is the linguistic variable "control quantity" and is generally defined in accordance with E, EC. Ai, Bi, Ci are the linguistic values in rule i corresponding to E, EC, U.
(3) Fuzzy inference
Fuzzy reasoning is the core of a fuzzy controller, and has the capability of simulating human reasoning based on fuzzy concepts, and the reasoning process is carried out based on implication relations and reasoning rules in fuzzy logic. Deducing the implied fuzzy relation according to the rules in the rule base, and carrying out reasoning and synthesis according to the fuzzy relation and the input condition to obtain an output language value. There are over ten methods for deriving their implication fuzzy relationships from rules, the most common of which is the max-min synthesis by Mamdani, as detailed below:
the ith control rule is as follows:
Ri：IF E is Ai AND EC is Bi THEN U is Ci
wherein Ai, Bi and Ci are language values of discourse domain X, Y and Z, and the fuzzy relation implied by the rule is as follows:
Ri＝(Ai×Bi)×Ci
the fuzzy relations corresponding to all fuzzy rules are obtained by taking a 'and' method, namely:
when the input variables E and EC are respectively selected from the fuzzy sets A and B, the control quantity U obtained by fuzzy reasoning can be obtained according to the following formula:
(4) defuzzification
The function of the defuzzification is to transform a control quantity (fuzzy quantity) obtained by fuzzy reasoning into a clear quantity actually used for control, and the defuzzification comprises two parts:
after the fuzzy control quantity is subjected to sharpening transformation, the fuzzy control quantity is changed into a sharpening quantity which is expressed in a domain range;
and 2. converting the clear quantity in the range of the domain into the actual control quantity through scaling.
The defuzzification is to convert the fuzzy output obtained by fuzzy inference into accurate output which can directly control the object according to a certain algorithm. The output u should have its domain of discourse Z translated to a range acceptable to the actuator before it is applied to the actuator, as shown in figure 3.
There are also many defuzzification algorithms, and the commonly used defuzzification methods include:
the gravity center method comprises the following steps:
extreme value averaging method:
weighted average decision method:
(5) fuzzy control look-up table
For a set of inputs (e, ec), the output u of the controller can be obtained by fuzzification, fuzzy inference and defuzzification. We can calculate u corresponding to all (e, ec) combinations off-line to get a fuzzy control look-up table. Assume that the fuzzy control rules are summarized in the following table.
Fuzzy control rule table
And for each possible value of e and ec, fuzzifying, reasoning and defuzzifying to obtain a fuzzy control query table.
Fuzzy control look-up table
The design method of the fuzzy controller comprises the following steps:
the design method of the fuzzy controller is different from that of the classical controller, and is not based on the mathematical analysis of the system, but the parameters and the control rules of the fuzzy controller are determined according to the experience and then are adjusted in the actual system. The general design of a fuzzy controller includes the following items:
(l) Defining inputs and outputs of a system
The detection input and control output of the system are first determined. In a fuzzy control system, a deviation e and a deviation variable delta e are usually selected as system input, a direct adjustment control quantity is selected as system output, and the adjustment quantity is used for reducing the system deviation quantity, which is most intuitive.
(2) Determining linguistic value ranges and membership functions
Then analyzing the actual condition of the input and output variables of the system, determining the domain of discourse (fuzzy value) of each variable, describing each variable by using a language term, defining the membership functions of the variables, covering the whole value range of the membership functions, and simultaneously, in order to ensure the robustness of the algorithm, partially overlapping the membership functions, wherein the overlapping rate is usually 25-50%.
(3) Design control rule base
The control rules are a set of language type rules describing the input and output characteristics of the controller, which are the core of the fuzzy controller, and the quality directly affects the performance of the controller. The formulation of the control rule requires that designers have deeper understanding on the working principle of the control object, the formulated rule corresponds to the reality, and the rule is classified and sorted and is expressed in the operation form of fuzzy variables.
(4) Deterministic fuzzy inference and disambiguation methods
After the fuzzy rule is determined, the fuzzy rule can be used for fuzzy reasoning. And fuzzifying the input variables, and then reasoning according to a similarity reasoning method to obtain fuzzy output. To obtain accurate output from the fuzzy output, the fuzzy solution is performed, and the common methods for solving the fuzzy include a maximum membership method, a median method and a weighted average method. The maximum membership method is simple, but the accuracy is not high, the static performance of the weighted average method is superior to that of the median method, and the dynamic performance of the weighted average method is slightly inferior to that of the median method.
(5) Implementation of fuzzy controller
The software of the fuzzy controller is realized in a continuous mode and a discrete mode. For a system with strong universality and high precision requirement, continuous realization is often adopted, namely output quantity corresponding to input quantity is directly calculated on line; for a system with high calculation time requirement and large storage requirement, a discrete type implementation is often adopted, input and output are scattered to manufacture a look-up table, and corresponding output is obtained by looking up the table for each input during use. The fuzzy controller is realized in a discrete mode, and a control lookup table is made according to rules.
(6) Optimized fuzzy controller
The fuzzy controller may be optimized according to control performance. The common optimization means includes adjusting control rules and scale factors, adjusting the position and shape of membership function, etc.
The feedforward fuzzy control algorithm is realized as follows:
the fuzzy control algorithm can be implemented in various forms, and a system matrix method, a table look-up method and an analysis method based on the Mamdani inference are briefly introduced below. A lookup table is used herein to formulate a fuzzy control strategy for tunnel ventilation systems. The relational matrix method requires input of variables and a relational matrix to perform synthesis operation, and is time-consuming and difficult to meet the time requirement of real-time control, so that the method is only a theoretical method and cannot solve the problem in real-time control.
The table look-up method makes the input and output mapping relation into a table, and reduces the calculation time by looking up the table during operation. This table, also called a control table, combines all the possibilities of the input discourse domain, finds the correspondence between the various possibilities and the elements of the output discourse domain, and then forms a table, the correspondence coming from the control rules. In the actual control, the control amount can be obtained as long as two steps of input amount quantization and table lookup are performed.
There are two methods for generating a control table, direct and indirect. The direct method is to directly obtain and refine the control quantity from the reasoning statement (i.e. control rule) so as to generate a control table; the indirect method needs to calculate the fuzzy relation in advance, synthesize the input quantity and the fuzzy relation to calculate the controlled quantity, and finally refine the controlled quantity to calculate the control table. The analytical formula method requires a corresponding analytical formula, and the operations such as shift addition, discrimination and the like can be realized during computer processing without storing a control table.
Designing a feed-forward fuzzy controller:
simulink is a simulation tool in MATLAB environment, and provides a very convenient graphical function module for a user so as to connect a simulation system, simplify the design flow and reduce the design burden. The Fuzzy Logic Toolbox (Fuzzy Logic Toolbox) is one of the Fuzzy Logic toolboxes, is easy to master and is convenient to use. The embodiment realizes modeling and simulation of fuzzy control of tunnel ventilation by using a fuzzy logic tool box.
Fuzzy control is carried out on the tunnel ventilation system, MATLAB is used for modeling, and the model is shown in a figure.
The fuzzy control system for tunnel ventilation comprises the following parts:
(1) the fuzzy controller is used for controlling the start and stop of the jet fan according to the fuzzy reasoning of the pollutant concentration value detected in real time and given; a set of control rules is made in advance by using the knowledge and experience of experts or operators, and the established rules are adjusted and optimized according to the 'optimal rule sequencing irrelevant' rule.
(2) The system input module is used for providing input for the fuzzy controller according to the difference value of the CO and the smoke concentration detected in real time and given;
(3) the system output module is used for controlling the start and stop of the jet fan in the tunnel;
MATLAB fuzzy logic toolbox:
the Fuzzy logic toolset has 5 major graphical User interfaces (GUI tools for establishing, editing and viewing Fuzzy Inference Systems (FIS), see figure 5 GUI tools including 3 editors, Fuzzy Inference System Editor (FIS Editor), Membership Function Editor (Membership Function Editor) and Fuzzy Rule Editor (Rule Editor), and 2 viewers, Fuzzy Rule Viewer (Rule Viewer) and Surface Viewer (Surface Viewer), which are dynamically connected to each other, so that in use, only if any one GUI parameter and property is modified, the corresponding parameters and properties in the other open GUIs will be automatically changed, greatly facilitating the User to debug their FIS.
(1) Establishment of tunnel ventilation fuzzy inference system
Firstly, establishing a tunnel ventilation fuzzy inference system FzyController.fis, typing 'fuzzy' in an MATLAB command window, calling a fuzzy logic toolbox, directly opening a FIS editor, selecting the type of Mamdani, and saving the Mamdani by using a file name of the FzyController.fis.
Double clicking the icon of the variable in the input variable area can open a membership function editor for defining the membership function of the input variable;
secondly, the fuzzy rule editor can be opened by double clicking the FzyController icon; and in the output variable area, double clicking the icon of the variable to edit the membership function of the output variable.
(2) Establishing variable and membership function
And opening a membership function editor, and defining two input variables and one output variable of the system, namely CO, VI and FanNum. Each variable is associated with a membership function editor, which is opened as shown in the figure:
all the defined input variables and output variables are displayed in the variable area. Clicking a variable to make the variable become a current variable, and editing a membership function of the variable;
secondly, all the membership functions of the current variable are displayed in the drawing area, and the name, the type, the attribute and the parameter of the function can be edited by clicking and selecting one membership function.
(3) Selection of Membership Function (MF)
In addition to the custom membership functions in the fuzzy logic toolbox, there are 11 possible membership functions, which are classified into four categories, respectively: the Simplest membership functions (Simplest MF), the Smooth singularless membership functions (Smooth and Nonzero MF), the Asymmetric membership functions (Asymmetric MF) and the multi-curved membership functions (Polynomial Based curres MF). As shown in the table, each type includes the following specific membership functions.
The simplest membership function shape is composed of straight lines, and the biggest advantage is that the operation is simple and the speed is high; smooth singularity-free membership functions are the most common type in engineering, because the curves of such functions are smooth and have no singularities, and no segmentation is needed in the integration process; while the latter two classes of membership functions are used in special cases.
Common membership functions in the fuzzy logic toolbox are shown in the following table.
Classification of membership functions in fuzzy logic toolsets
The fuzzy subset with a sharper curve shape of the membership function has higher resolution and high control sensitivity; on the contrary, the curve shape of the membership function is relatively smooth, the control characteristic is relatively smooth, and the stability is relatively good. Therefore, when the membership function of the fuzzy variable is selected, the fuzzy set with low resolution is adopted in the area with larger error, the fuzzy set with higher resolution is selected in the area with smaller error, and the fuzzy set with high resolution is selected when the error is close to zero, so that the control effect with high control precision and good stability can be achieved. The input variable of the tunnel ventilation fuzzy inference system adopts a triangular membership function, and the output variable adopts a Gaussian membership function.
Fuzzification of system variables
According to the relevant discussion in chapter two, the CO and smoke concentration errors detected in real time and given are selected as inputs to the fuzzy inference system.
The CO concentration deviation is defined as:
ΔCCO＝δ-CCO
wherein δ is the designed concentration of CO (ppm);
CCOmeasured CO concentration (ppm).
The smoke concentration deviation is defined as:
ΔCVI＝K-CVI
wherein K is the design concentration (m) of the smoke-1)；
CVIIs measured smoke concentration (m)-1)。
Input transformerDeviation of CO concentration by quantity Δ CCOAnd smoke density deviation acVIAll of the fuzzy linguistic variables of (1) are { NB, NM, NS, ZO, PS, PM, PB }, and all of the domains of discourse are [ -6, 6]. For contaminants, NB means that the contaminant concentration is the greatest, much higher than the design concentration, according to the definition of deviation above; and PB means that the contaminant concentration is very small, much lower than the design concentration; while the middle variable indicates that the concentration of the pollutant is from high to low, and ZO indicates that the concentration of the pollutant is not large and is equivalent to the designed concentration.
ΔCCOThe basic domains of discourse of (1) are:
-100ppm≤ΔcCO≤200ppm
ΔCVIthe basic domains of discourse of (1) are:
-0.005m-1≤ΔcVI≤0.007m-1
the transformation formula from the basic domain of discourse to the domain of discourse is respectively:
ΔcVI＝0.001ΔCVI+0.001
the membership function of the two is a triangular function trimf, and the specific setting of the membership function is shown in fig. 4 and fig. 5.
And selecting the number of the jet fans as the output of the fuzzy inference system. The output variable defines CFANNum and GFANNum concentration membership function is shown in FIG. 6, the fuzzy linguistic variable is { NB, NM, NS, ZO, PS, PM, PB }, and the domain of discourse is [ -6, 6 ]. For the number of the starting stations of the jet fan, NB represents the minimum number of the starting stations, PB represents the maximum number of the starting stations, and the middle variable represents the number of the starting stations from small to large.
The basic domain of argument for the output variable CFanNum is:
0≤cFanNum≤24
the transformation formula from the basic domain of discourse to the domain of discourse is respectively:
cFanNum＝2CFanNum+12
the membership function adopts a Gaussian function gausssf.
Fuzzy rules:
it is very easy to construct rules using a fuzzy rule editor by selecting an input variable on the left side of the fuzzy rule editor and selecting one of the language values, then selecting an output variable in the output variable box on the right side of the editor and selecting one of the language values, and then adding the rule to the rule base. For a rule with multiple input variables, a link (and or) is selected.
The fuzzy rule base of the system is established according to a fuzzy control table, and the control table is as follows:
fuzzy rule table
The arrangement and starting strategy of the jet flow fan is as follows:
(1) jet fan arrangement
In a longitudinal ventilation system of a highway tunnel, two jet flow fans are generally connected in parallel to form a group and are symmetrically arranged at the top end of the tunnel along the driving direction.
Longitudinal arrangement of fan
There should be sufficient distance between each set of fans in the tunnel so that there is sufficient gradual deceleration of the jet air flow. If the speed of the jet air flow is not completely reduced, the working performance of the next stage fan is affected. In general, the longitudinal distance between each group of fans is l0 times or l0 times of the equivalent diameter of tunnel section water power, and one tenth of the aerodynamic pressure of the fans can be used as the longitudinal distance of the fans. The jet flow fans in the tunnel are not necessarily arranged at the same interval longitudinally, and the fans can be arranged at positions close to the tunnel opening as far as possible as long as the fans have enough longitudinal intervals. If the axial mounting position of the fans allows a certain inclination, the longitudinal distance between the fans can be reduced appropriately, so that the mounting factor can be improved.
② transverse arrangement of the fan
Experiments and practices show that in order to avoid the mutual interference of the jet air flows and reduce the ventilation efficiency of the system, the central distance between the fans in the same group is at least 2 times of the diameter of each fan.
(2) Jet fan start-stop strategy
The start and stop of the fan in the tunnel meet the following principle:
firstly, when the CO value at a certain point in the tunnel reaches a fan starting value, a fan unit closest to the detector is started firstly;
secondly, the fan with the shortest accumulated running time is started firstly to balance the work and ease degrees of all fans;
the start of each fan should be delayed for a short time, so that the impact of instantaneous current is avoided (the general starting current is 2-10 times of the running current and lasts for 2-15 seconds);
and fourthly, when the pollution condition of the tunnel is deteriorated and the environment-friendly requirement cannot be met only by the operation of the fan, the tunnel is matched with the tunnel entrance lane lamp, and the number of vehicles is controlled by using the signal lamp.
Fuzzy control after adjustment based on the optimal rule:
in the embodiment, the rule base is adjusted by using an 'optimal rule ordering irrelevant' rule, namely, the 'optimal rule ordering irrelevant' rule is that the value of a back-part of one rule is changed without influencing the optimal value of the back-part of the other rule aiming at a highway tunnel ventilation fuzzy control system. The term "irrelevant" does not mean that two rules in strict mathematical meaning are not related and do not act with each other, but are absolutely irrelevant, but is verified from the engineering point of view by simulation analysis, and the optimal values of the back-part parts of the two rules are irrelevant. The optimal index is that the square sum of the errors (the error is the actual concentration value of CO and the set value) is minimum.
The design of the feedforward neural network intelligent ventilation is as follows:
because the selection of fuzzy control rules, the selection of domains of discourse, the definition of fuzzy sets, the selection of quantization factors and the like in the fuzzy control all depend on the experience of experts, and the tunnel ventilation is a time-varying hysteresis system, the effect of the fuzzy control on the tunnel ventilation is not ideal enough. In order to overcome the defects, the prediction of the neural network on the tunnel traffic volume (chapter 1) is researched, the prediction of the neural network on the tunnel traffic volume is added on the basis of a tunnel ventilation fuzzy control system, a tunnel ventilation energy-saving system based on intelligent control is constructed, and the performance of obviously improving the tunnel fuzzy control system is achieved.
The fuzzy control system based on neural network prediction is realized in two intelligent control modes based on a neural network and a fuzzy technology, so the fuzzy control system is called an intelligent control system. For the defects that the establishment of a rule base in the fuzzy control needs to depend on experience and expert guidance, and the tunnel ventilation is a time-varying large-lag system, the introduction and the analysis of neural network prediction are carried out according to the tunnel traffic volume in the chapter, and a tunnel ventilation fuzzy control system established in the third chapter is combined to construct a tunnel ventilation energy-saving system based on intelligent control.
Analyzing the energy-saving effect of each control method:
under the action of different control methods, the number and the time condition of the opened fans of the tunnel in one day are shown as follows.
Quantity and time condition table for one-day fan starting in tunnel under grading control
Quantity and time condition table for one-day fan starting in tunnel under fuzzy control
Number and time condition table for one-day fan starting in tunnel under fuzzy control after adjustment
Intelligent control is down quantity and time condition table of fan start-up of one day in tunnel
If the electric charge is 0.55 yuan per degree, the electric charge consumed by operating the ventilation of the tunnel in one year under intelligent control can be calculated according to the following formula.
The total power consumed in one day W is:
the electricity charge H generated in one year is:
H＝11430×365×0.55＝2294572
the operating costs of the ventilation phase under the action of several other control methods can be calculated in a similar way, and statistics of the energy consumption under the action of the various control methods are shown in the following table.
Statistical table of energy consumption conditions generated by different control modes
It can be seen from the table that compared with the traditional grading control, the energy-saving effect cannot be realized by using the fuzzy control of the light and the fuzzy control of the adjustment rule to control the tunnel ventilation system, because the selection of the fuzzy control rule, the selection of the domain, the definition of the fuzzy set, the selection of the quantization factor and the like depend on the experience of the expert, and a trial and error method is mostly adopted, so that the obvious effect is difficult to obtain on the control of a complex system such as tunnel ventilation; the system is added with a neural network to predict the traffic volume of the tunnel, and after the jet fan is controlled to perform certain pre-starting, the system has obviously improved performance on the tunnel with large hysteresis, so that intelligent control is a preferred scheme of the tunnel ventilation control technology in the future.
The invention discloses a feedforward type fuzzy intelligent ventilation control model algorithm for a long road tunnel, which is invented by analyzing the characteristics and implementation processes of various control methods based on the investigation of common ventilation control technology, and researching the theory of fuzzy control, fuzzy control based on most regular adjustment, feedforward type neural network intelligent ventilation design and energy-saving effect analysis of various control methods.
Under the condition that the research of the energy efficiency control scheme and the algorithm is completed, simulation test and drilling application can be carried out by combining the characteristics of the tunnel, the deviation of each test data and theoretical prediction in the actual operation of the system is considered, and the further inspection and adjustment are carried out, so that more effective intelligent energy-saving control is realized.
The algorithm can convert the input accurate quantity into the fuzzy quantity according to the language variable defined on the input domain. The input quantity includes external reference input, system output or state, etc. to make advance intelligent ventilation control, and it has the inference ability based on fuzzy concept of analog person, and the inference process is based on the implication relation and inference rule in fuzzy logic. Deducing the implied fuzzy relation according to the rules in the rule base, and carrying out reasoning and synthesis according to the fuzzy relation and the input condition to obtain an output language value. The feedforward control based on the fuzzy theory is adopted to effectively improve the air circulation efficiency for the tunnel operation management, realize the forward quick ventilation, and compared with the traditional control mode, the method has obvious improvement on the energy-saving and security protection effects.
The invention discloses a feedforward intelligent fuzzy control, which is a pre-judgment control, analyzes and researches traffic flow and traffic history information in a tunnel on the basis of analyzing influence parameters of illumination, ventilation and traffic control in the tunnel, uniformly analyzes and brings traffic flow of a tunnel group and adjacent tunnels into a research range, researches and forms a feedforward intelligent fuzzy control scheme suitable for the tunnel on the basis of traffic flow pre-judgment analysis of the tunnel, establishes an intelligent fuzzy control DLL dynamic library model, implants control software, and develops intelligent control of ventilation mainly saving the service life of a fan and energy according to the starting frequency and the accumulated running time of the fan.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
Reference throughout this specification to "one embodiment," "another embodiment," "an embodiment," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment described generally in this application. The appearances of the same phrase in various places in the specification are not necessarily all referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with any embodiment, it is submitted that it is within the scope of the invention to effect such feature, structure, or characteristic in connection with other embodiments.
Although the invention has been described herein with reference to a number of illustrative embodiments thereof, it should be understood that numerous other modifications and embodiments can be devised by those skilled in the art that will fall within the spirit and scope of the principles of this disclosure. More specifically, various variations and modifications are possible in the component parts and/or arrangements of the subject combination arrangement within the scope of the disclosure and claims of this application. In addition to variations and modifications in the component parts and/or arrangements, other uses will also be apparent to those skilled in the art.
Claims (10)
1. The utility model provides a long tunnel intelligence ventilation control system of highway which characterized in that includes:
the measuring device (3) is used for detecting information parameters which can be used for ventilation control in the long tunnel of the road and transmitting the information parameters to the fuzzy controller (4);
the fuzzy controller (4) is used for converting an input accurate quantity into a fuzzy quantity by defining linguistic variables on an input domain, then obtaining a fuzzy control quantity through fuzzy reasoning, converting the fuzzy control quantity into an actual control quantity through defuzzification, and outputting the actual control quantity to the actuator (1);
and the actuator (1) is used for exerting a control action on the controlled object (2) so as to regulate and control the air volume in the long road tunnel.
2. Intelligent ventilation control system for long road tunnels according to claim 1, characterized in that the controlled object (2) comprises jet fans arranged in the tunnel.
3. Intelligent ventilation control system for long road tunnels according to claim 1, characterized in that said measuring means (3) comprise a CO/VI detector, a wind speed and direction detector and a vehicle detector.
4. The intelligent ventilation control system for long road tunnels according to claim 1, characterized in that the fuzzy controller (4) comprises:
and the fuzzification module is used for defining a linguistic variable aiming at each input space of the fuzzy controller (4), then defining the domain of each linguistic variable, defining the linguistic value of each linguistic variable, and defining the domain of each linguistic variable as the membership function of the linguistic value.
A knowledge base containing knowledge in the application domain and required control targets;
the fuzzy reasoning module deduces the implied fuzzy relation from the rules in the rule base, and carries out reasoning according to the fuzzy relation and the input condition to obtain an output language value;
the defuzzification module is used for converting the fuzzy control quantity into a clear quantity which is represented in the range of the domain of discourse after the defuzzification conversion; and then the clear quantity in the range of the domain of interest is converted into an actual control quantity through scaling.
5. The intelligent ventilation control system for long road tunnels according to claim 1, characterized in that the fuzzy inference in the fuzzy controller (4) is to obtain the control quantity by table look-up.
6. An intelligent ventilation control method for a long road tunnel is characterized by comprising the following steps:
step S1: detecting information parameters which can be used for ventilation regulation and control in a long road tunnel and transmitting the information parameters to the fuzzy controller (4);
step S2: the method comprises the steps of defining linguistic variables on an input domain, converting input accurate quantity into fuzzy quantity, then obtaining fuzzy control quantity through fuzzy reasoning, converting the fuzzy control quantity into actual control quantity through defuzzification, and outputting the actual control quantity to an actuator (1);
step S3: and applying a control action to the controlled object (2) to regulate and control the air volume in the long tunnel of the road.
7. The intelligent ventilation control method for long road tunnel according to claim 6, wherein in step S1, the information parameters include the influence parameters of lighting, ventilation and traffic control in the tunnel, the traffic flow and traffic history information in the tunnel, and the traffic flow information of the tunnel group and the adjacent tunnels.
8. The intelligent ventilation control method for long road tunnels as claimed in claim 6, wherein in step S2, two input variables are defined as CO and VI, one output variable is FanNum, and a membership function editor is associated with each variable, wherein the input variables adopt triangle membership functions, and the output variables adopt gaussian membership functions.
9. The method for the fuzzy intelligent ventilation control of the long road tunnel according to claim 6, wherein the actuator (1) further controls a signal light of an entrance lane to control the number of vehicles entering the tunnel by using the signal light in case of the deterioration of the pollution condition of the tunnel.
10. A method of designing a fuzzy controller, comprising:
defining inputs and outputs of the system
Selecting the deviation e and the deviation variable delta e as the input of the system, selecting the amount of direct regulation control as the output of the system, and reducing the deviation amount of the system by regulating the regulating amount;
(ii) determining linguistic value ranges and membership functions
Analyzing the actual condition of the input and output variables of the system, determining the domain of each variable, describing each variable by using a language term, and defining the membership functions of each variable, wherein the membership functions cover the whole value range;
(iii) design control rule base
Formulating a rule corresponding to the reality, classifying and sorting the rule, and expressing the rule in an operation form of a fuzzy variable;
(iv) determining fuzzy inference and deblurring methods
Fuzzifying an input variable, and performing reasoning according to a fuzzy rule to obtain fuzzy output;
performing fuzzy resolving on the fuzzy output to obtain accurate output;
(v) implementation of fuzzy controller
The method is realized in a discrete mode, and a control lookup table is manufactured according to rules;
(vi) optimizing the fuzzy controller
And optimizing the fuzzy controller according to the control performance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111195013.5A CN114019846A (en) | 2021-10-11 | 2021-10-11 | Intelligent ventilation control design method and system for long road tunnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111195013.5A CN114019846A (en) | 2021-10-11 | 2021-10-11 | Intelligent ventilation control design method and system for long road tunnel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114019846A true CN114019846A (en) | 2022-02-08 |
Family
ID=80056099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111195013.5A Pending CN114019846A (en) | 2021-10-11 | 2021-10-11 | Intelligent ventilation control design method and system for long road tunnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114019846A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114995272A (en) * | 2022-04-28 | 2022-09-02 | 中铁九局集团电务工程有限公司 | Intelligent centralized control system and method for blasting and air exhaust in tunnel construction |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101235724A (en) * | 2008-02-02 | 2008-08-06 | 西南交通大学 | Express highway adjoining tunnel linkage aeration control method |
| CN101509390A (en) * | 2009-02-25 | 2009-08-19 | 湖南大学 | Tunnel ventilation control method based on fuzzy control |
| CN202196324U (en) * | 2011-08-31 | 2012-04-18 | 成都金隧自动化工程有限责任公司 | Intelligent area controller |
| CN103543697A (en) * | 2012-07-16 | 2014-01-29 | 上海宝信软件股份有限公司 | Clustered intelligent control method for traffic tunnel devices |
| CN104154019A (en) * | 2014-08-04 | 2014-11-19 | 昆明联诚科技股份有限公司 | Tunnel ventilation energy-saving control system based on fuzzy control and control method thereof |
| CN105569707A (en) * | 2015-12-11 | 2016-05-11 | 中铁第四勘察设计院集团有限公司 | Highway tunnel ventilation feedforward control method based on environmental forecasting |
| CN107091534A (en) * | 2017-04-27 | 2017-08-25 | 扬州大学 | A kind of solar water heater fuzzy control device |
| CN109426148A (en) * | 2017-08-25 | 2019-03-05 | 中核兰州铀浓缩有限公司 | A method of realizing the automatic adjustment of coal-burning boiler ash disposal process circulation time |
| CN111535845A (en) * | 2020-05-06 | 2020-08-14 | 东华大学 | Tunnel ventilation energy-saving optimization control method based on PSO and fuzzy control |
-
2021
- 2021-10-11 CN CN202111195013.5A patent/CN114019846A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101235724A (en) * | 2008-02-02 | 2008-08-06 | 西南交通大学 | Express highway adjoining tunnel linkage aeration control method |
| CN101509390A (en) * | 2009-02-25 | 2009-08-19 | 湖南大学 | Tunnel ventilation control method based on fuzzy control |
| CN202196324U (en) * | 2011-08-31 | 2012-04-18 | 成都金隧自动化工程有限责任公司 | Intelligent area controller |
| CN103543697A (en) * | 2012-07-16 | 2014-01-29 | 上海宝信软件股份有限公司 | Clustered intelligent control method for traffic tunnel devices |
| CN104154019A (en) * | 2014-08-04 | 2014-11-19 | 昆明联诚科技股份有限公司 | Tunnel ventilation energy-saving control system based on fuzzy control and control method thereof |
| CN105569707A (en) * | 2015-12-11 | 2016-05-11 | 中铁第四勘察设计院集团有限公司 | Highway tunnel ventilation feedforward control method based on environmental forecasting |
| CN107091534A (en) * | 2017-04-27 | 2017-08-25 | 扬州大学 | A kind of solar water heater fuzzy control device |
| CN109426148A (en) * | 2017-08-25 | 2019-03-05 | 中核兰州铀浓缩有限公司 | A method of realizing the automatic adjustment of coal-burning boiler ash disposal process circulation time |
| CN111535845A (en) * | 2020-05-06 | 2020-08-14 | 东华大学 | Tunnel ventilation energy-saving optimization control method based on PSO and fuzzy control |
Non-Patent Citations (2)
| Title |
|---|
| 彭家寅, 李洪兴, 侯健, 尤飞, 王加银: "基于逐点优化模糊推理的模糊控制器及其插值机理", ***科学与数学, no. 03, 26 July 2005 (2005-07-26) * |
| 欧进萍, 张吉礼: "模糊控制基本推理方法及其效果分析", 哈尔滨建筑大学学报, no. 02, 25 April 2000 (2000-04-25) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114995272A (en) * | 2022-04-28 | 2022-09-02 | 中铁九局集团电务工程有限公司 | Intelligent centralized control system and method for blasting and air exhaust in tunnel construction |
| WO2023165633A1 (en) * | 2022-04-28 | 2023-09-07 | 中铁九局集团电务工程有限公司 | Intelligent centralized control system and method for tunnel construction blasting and exhaust |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104534507B (en) | A kind of boiler combustion optimization control method | |
| Ng et al. | Classification of capacitor allocation techniques | |
| WO2020015466A1 (en) | Boiler coal saving control method | |
| CN112066355B (en) | Self-adaptive adjusting method of waste heat boiler valve based on data driving | |
| CN114019846A (en) | Intelligent ventilation control design method and system for long road tunnel | |
| CN108657232A (en) | A kind of multi objective control method of municipal rail train | |
| CN112836920A (en) | Coal electric unit energy efficiency state evaluation method and device and coal electric unit system | |
| CN107664948A (en) | Photovoltaic cell MPPT asymmetric Varied scope fuzzy control method | |
| CN113048807A (en) | Air cooling unit backpressure abnormity detection method | |
| CN109992844A (en) | A kind of boiler flyash carbon content prediction technique based on ADQPSO-SVR model | |
| Bonissone et al. | Fuzzy logic controllers: from development to deployment | |
| CN111535845A (en) | Tunnel ventilation energy-saving optimization control method based on PSO and fuzzy control | |
| CN111336828A (en) | Heating furnace temperature controller based on FCM fuzzy time sequence | |
| Welch et al. | Comparison of two optimal control strategies for a grid independent photovoltaic system | |
| Jerry et al. | The optimal strategy for a bioeconomical model of a harvesting renewable resource problem | |
| Sharma et al. | Minimizing uncertainties with improved power system stability using wide area fuzzy-2 logic based damping controller | |
| CN112633494A (en) | Automatic neural network structure searching method based on automatic machine learning | |
| TWI420278B (en) | Solar energy system having fuzzy sliding controller | |
| Chen et al. | The application of intelligent integral realized by fuzzy logic for hydroturbine governing system | |
| CN111541245A (en) | Intelligent household energy management system control method | |
| Xin et al. | Genetic based fuzzy Q-learning energy management for smart grid | |
| Zhang et al. | The relationship between energy consumption and economic growth in china based on ANFIS | |
| CN117470300B (en) | Environment monitoring method and system for finished copper pipe storage workshop | |
| CN115573819A (en) | Gas turbine T-S model optimization method based on multi-model predictive control algorithm | |
| Singh et al. | A hybrid approach for temperature and humidity control in HVAC system and optimization with fuzzy logic |
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 |