CN115959933A - Intelligent control method and system for aerobic composting - Google Patents
Intelligent control method and system for aerobic composting Download PDFInfo
- Publication number
- CN115959933A CN115959933A CN202310137870.2A CN202310137870A CN115959933A CN 115959933 A CN115959933 A CN 115959933A CN 202310137870 A CN202310137870 A CN 202310137870A CN 115959933 A CN115959933 A CN 115959933A
- Authority
- CN
- China
- Prior art keywords
- historical
- data set
- oxygen concentration
- relational expression
- aerobic composting
- 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
- 238000009264 composting Methods 0.000 title claims abstract description 109
- 238000000034 method Methods 0.000 title claims abstract description 53
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims abstract description 89
- 229910052760 oxygen Inorganic materials 0.000 claims abstract description 89
- 239000001301 oxygen Substances 0.000 claims abstract description 89
- 230000014509 gene expression Effects 0.000 claims abstract description 64
- 238000005457 optimization Methods 0.000 claims abstract description 60
- 238000013528 artificial neural network Methods 0.000 claims abstract description 57
- 238000009423 ventilation Methods 0.000 claims abstract description 53
- 238000005265 energy consumption Methods 0.000 claims abstract description 48
- 238000010564 aerobic fermentation Methods 0.000 claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 31
- CKUAXEQHGKSLHN-UHFFFAOYSA-N [C].[N] Chemical compound [C].[N] CKUAXEQHGKSLHN-UHFFFAOYSA-N 0.000 claims abstract description 29
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 claims description 54
- 229910021529 ammonia Inorganic materials 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 7
- 230000010354 integration Effects 0.000 claims description 5
- 230000004069 differentiation Effects 0.000 claims description 4
- 229910052757 nitrogen Inorganic materials 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 239000007788 liquid Substances 0.000 claims description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N nitrogen Substances N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 2
- 238000005325 percolation Methods 0.000 claims description 2
- 230000033228 biological regulation Effects 0.000 abstract description 4
- 239000002910 solid waste Substances 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 21
- 239000007789 gas Substances 0.000 description 15
- 230000008569 process Effects 0.000 description 15
- 230000008859 change Effects 0.000 description 11
- 230000000694 effects Effects 0.000 description 10
- 239000002361 compost Substances 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 5
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 4
- 238000000855 fermentation Methods 0.000 description 4
- 230000004151 fermentation Effects 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 241000894006 Bacteria Species 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 229910002092 carbon dioxide Inorganic materials 0.000 description 2
- 239000001569 carbon dioxide Substances 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 244000005700 microbiome Species 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 239000002028 Biomass Substances 0.000 description 1
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000005273 aeration Methods 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000005422 blasting Methods 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 239000003864 humus Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 239000005416 organic matter Substances 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 229910052700 potassium Inorganic materials 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000010902 straw Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- 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
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W30/00—Technologies for solid waste management
- Y02W30/40—Bio-organic fraction processing; Production of fertilisers from the organic fraction of waste or refuse
Landscapes
- Feedback Control In General (AREA)
- Processing Of Solid Wastes (AREA)
- Fertilizers (AREA)
Abstract
The invention discloses an intelligent control method and system for aerobic composting, which relate to the technical field of resource utilization of agricultural and forestry solid wastes, and the method comprises the following steps: training the first TS fuzzy neural network to determine a ventilation prediction relational expression; training the second TS fuzzy neural network to determine a blower energy consumption prediction relational expression; training the third TS fuzzy neural network to determine a leachate pH prediction relational expression; training the fourth TS fuzzy neural network to determine a pile carbon-nitrogen ratio prediction relational expression; establishing an aerobic composting multi-objective optimization model based on a ventilation prediction relational expression, a blower energy consumption prediction relational expression, a percolate pH prediction relational expression and a pile carbon-nitrogen ratio prediction relational expression, and solving to obtain a Pareto optimal solution; and inputting the Pareto optimal solution into a PID controller to realize the tracking control of the oxygen concentration and the temperature in the aerobic fermentation tank. The invention realizes the automatic and accurate regulation and control of aerobic composting.
Description
Technical Field
The invention relates to the technical field of resource utilization of agricultural and forestry solid wastes, in particular to an intelligent control method and system for aerobic composting.
Background
In recent years, the yield of main agricultural and forestry wastes in China is continuously increased, and crop straws have rich N, P, K and organic matter nutrients and are important renewable biomass resources in the agricultural production process. The agricultural and forestry waste resource utilization gradually forms a development pattern of mainly fertilizing, stably propelling feed and fuel, and secondarily fertilizing and preparing raw materials, and the aerobic composting technology is an important technical means for realizing fertilizing and basification of agricultural solid wastes.
Aerobic composting is generally divided into static stacking fermentation, bar-shaped turning fermentation, tank-type turning fermentation and stirred container composting fermentation. The standard composting process comprises the links of pretreatment, batching, turning and blasting, environmental control and the like, and has large occupied area and complex operation. In the composting process, stack state indexes such as temperature and humidity, pH value, TC (Total Carbon), and the like need to be measured for a long time by means of chemical analysis, and it is difficult to obtain real-time data and sufficient data amount. And because the aeration system has uncertainty and instantaneity in the composting process, and physical change, chemical change and microorganism change simultaneously occur in the compost, the reaction changes are interwoven together to enable the aerobic composting process to form a multivariable and strong-coupling complex system, the coupling relation in the complex reaction process is difficult to infer depending on the traditional manual single-index detection, the adjustment and judgment cannot be made in time and in real time, and the accurate regulation and control in the aerobic composting process cannot be achieved.
Disclosure of Invention
The invention aims to provide an intelligent control method and system for aerobic composting, which are used for realizing automatic and accurate regulation and control of an aerobic composting process based on multivariable real-time monitoring.
In order to achieve the purpose, the invention provides the following scheme:
the invention provides an intelligent control method of aerobic composting, which is applied to an aerobic composting device, wherein the aerobic composting device comprises an aerobic fermentation tank, a percolate tank, an air blower and a PID (proportion integration differentiation) controller;
the intelligent control method for aerobic composting comprises the following steps:
acquiring a historical ventilation volume data set, a historical blower energy consumption data set, a historical leachate pH data set, a historical oxygen concentration data set, a historical ammonia concentration data set, a historical temperature data set and a historical pile carbon-nitrogen ratio data set in the aerobic fermentation tank;
training a first TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set and the historical ventilation data set to determine a ventilation prediction relational expression; training a second TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set and the historical blower energy consumption data set to determine a blower energy consumption prediction relational expression; training a third TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical leachate pH data set to determine a leachate pH prediction relational expression; training a fourth TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical reactor carbon-nitrogen ratio data set to determine a reactor carbon-nitrogen ratio prediction relational expression;
establishing an aerobic composting multi-objective optimization model based on the ventilation prediction relational expression, the blower energy consumption prediction relational expression, the percolate pH prediction relational expression and the pile carbon-nitrogen ratio prediction relational expression;
solving the aerobic composting multi-target optimization model to obtain a Pareto optimal solution; the Pareto optimal solution comprises an oxygen concentration optimization set value and a temperature optimization set value in the aerobic fermentation tank;
and inputting the Pareto optimal solution to the PID controller to realize the tracking control of the oxygen concentration and the temperature in the aerobic fermentation tank.
Optionally, the first TS fuzzy neural network includes an input layer, a fuzzy rule calculation layer, and an output layer;
the input layer is used for inputting the historical oxygen concentration data set, the historical temperature data set and the historical ventilation data set; the historical oxygen concentration data set and the historical temperature data set form optimization variables;
the fuzzy layer is used for carrying out fuzzy processing on the optimized variable through a membership degree generating function so as to obtain fuzzy membership degree;
the fuzzy rule calculation layer is used for calculating fuzzy rules on the fuzzy membership degree;
and the output layer is used for receiving all the data output by the fuzzy rule calculation layer and correcting the received data according to the historical ventilation data corresponding to the optimized variables so as to determine a ventilation predicted value.
Optionally, solving the aerobic composting multi-objective optimization model to obtain a Pareto optimal solution, specifically including:
processing the constraint function by adopting a penalty function method;
solving the aerobic composting multi-target optimization model processed by the penalty function method by adopting an NSGA-II algorithm to obtain a group of Pareto optimization solutions;
and selecting a Pareto optimal solution from a group of Pareto optimal solutions based on a preset decision.
Optionally, the aerobic composting apparatus further comprises an agitator; the stirrer is arranged in the aerobic fermentation tank;
the intelligent control method for aerobic composting further comprises the following steps:
and adjusting the rotating speed of the air blower and the rotating speed of the stirrer based on Pareto optimal solution by adopting the PID controller so as to realize the tracking control of the oxygen concentration and the temperature in the aerobic fermentation tank.
The invention also provides an aerobic composting intelligent control system which is applied to an aerobic composting device, wherein the aerobic composting device comprises an aerobic fermentation tank, a percolate tank, an air blower and a PID controller;
the aerobic composting intelligent control system comprises:
the data acquisition module is used for acquiring a historical ventilation volume data set, a historical blower energy consumption data set, a historical leachate pH data set, a historical oxygen concentration data set, a historical ammonia concentration data set, a historical temperature data set and a historical pile carbon-nitrogen ratio data set in the aerobic fermentation tank;
a relational expression determination module for training a first TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set and the historical ventilation data set to determine a ventilation prediction relational expression; training a second TS fuzzy neural network based on the historical oxygen concentration dataset, the historical temperature dataset, and the historical blower energy consumption dataset to determine a blower energy consumption prediction relationship; training a third TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical leachate pH data set to determine a leachate pH prediction relational expression; training a fourth TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical reactor carbon-nitrogen ratio data set to determine a reactor carbon-nitrogen ratio prediction relational expression;
the multi-objective optimization model building module is used for building an aerobic composting multi-objective optimization model based on the air volume prediction relational expression, the air blower energy consumption prediction relational expression, the percolate pH prediction relational expression and the pile carbon-nitrogen ratio prediction relational expression;
the multi-objective optimization model solving module is used for solving the aerobic composting multi-objective optimization model to obtain a Pareto optimal solution; the Pareto optimal solution comprises an oxygen concentration optimal set value and a temperature optimal set value in the aerobic fermentation tank;
and the PID control module is used for inputting the Pareto optimal solution to the PID controller so as to realize the tracking control of the oxygen concentration and the temperature in the aerobic fermentation tank.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the embodiment of the invention discloses an aerobic composting intelligent control method and system, which are applied to an aerobic composting device, and the method comprises the following steps: based on the collected historical data, a plurality of TS fuzzy neural networks are respectively trained to obtain corresponding air volume prediction relational expressions, blower energy consumption prediction relational expressions, percolate pH prediction relational expressions and pile carbon-nitrogen ratio prediction relational expressions, so that performance index optimization is realized based on the TS fuzzy neural networks, and more accurate prediction relational expressions in an aerobic composting process are obtained. Then establishing an aerobic composting multi-objective optimization model based on a ventilation prediction relational expression, a blower energy consumption prediction relational expression, a percolate pH prediction relational expression and a pile carbon-nitrogen ratio prediction relational expression, solving the model to obtain a Pareto optimal solution, and thus realizing multivariable-based optimization control; wherein, the Pareto optimal solution comprises an oxygen concentration optimal set value and a temperature optimal set value in the aerobic fermentation tank. And finally, inputting the Pareto optimal solution into a PID controller to realize the tracking control of the oxygen concentration and the temperature in the aerobic fermentation tank, thereby realizing the automatic and accurate regulation and control of the aerobic composting process. The oxygen concentration and the temperature in the aerobic fermentation tank can be determined by the energy consumption of the air blower and the ventilation quantity generated by the air blower, the oxygen concentration and the temperature are accurately controlled, namely the ventilation quantity of the energy consumption of the air blower is optimally controlled, and the problem of low energy and resource utilization rate caused by the ventilation quantity in the aerobic composting process can be solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic flow chart of an intelligent control method of aerobic composting according to the invention;
FIG. 2 is a schematic structural diagram of a TS fuzzy neural network according to the present invention;
FIG. 3 is a schematic diagram of a PID control structure according to the invention;
FIG. 4 is a schematic structural diagram of an intelligent control system for aerobic composting according to the present invention;
FIG. 5 is a diagram showing the overall control structure of an intelligent control system for aerobic composting in an embodiment of the present invention;
FIG. 6 is a schematic diagram of the overall architecture of an intelligent control system for aerobic composting in an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides an aerobic composting intelligent control method and system, wherein an air blower energy consumption prediction model, a pile C/N ratio function model and the like are established based on a TS fuzzy neural network, and performance indexes are optimized; and obtaining a Pareto optimal solution according to a multi-objective optimization algorithm model, intelligently deciding to optimize the oxygen concentration and the temperature set value, and realizing dynamic optimization and tracking control on the rotating speed set value of the blower and the rotating speed set value of the stirrer, thereby constructing a multi-objective optimization intelligent control method taking energy consumption and ventilation as optimization targets.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Example one
As shown in figure 1, the invention provides an intelligent control method for aerobic composting, which is applied to an aerobic composting device, wherein the aerobic composting device comprises an aerobic fermentation tank, a percolation liquid tank, an air blower and a PID (proportion integration differentiation) controller.
The principle of the invention is as follows: under the conditions of good ventilation and sufficient oxygen, organic matters are degraded by means of the metabolism process of aerobic microorganisms to form new humus. In the initial stage of the composting reaction, the decomposition of the substances depends on mesophilic bacteria (30-40 DEG COptimum growth temperature) is gradually replaced by thermophilic bacteria with optimum temperature of 45-65 ℃ along with the increase of the composting temperature, most organic matters are degraded after a period of time, and the temperature of the compost begins to decrease. Compost proceeding stage and effect, compost body temperature and CH generated in reaction process 4 、O 2 、CO 2 、NH 3 The ratio of the components has a direct relation with the concentration. The aerobic composting device is a closed reaction device, the judgment of the composting reaction stage and the composting effect is realized by collecting gas components and concentration parameters in the composting device and at the gas outlet, the parameters of pH, EC, turbidity and the like of percolate are monitored, and the intelligent control of ventilation is realized by regulating and controlling the rotating speed of a stirrer and the rotating speed of a blower, so that the energy consumption is saved and the composting effect is improved.
Specifically, the intelligent control method for aerobic composting comprises the following steps:
Specifically, monitoring oxygen concentration data, ammonia concentration data and temperature data in real time by using a sensor arranged in an aerobic fermentation tank, and correspondingly adopting an oxygen sensor, an ammonia sensor and a temperature sensor; in addition, can also set up the methane sensor and detect the methane concentration of the gas outlet department of aerobic fermentation jar, set up the carbon dioxide concentration of the gas outlet department of carbon dioxide sensor detection aerobic fermentation jar to the realization detects and each component concentration parameter measurement to the gas composition of the gas outlet of aerobic fermentation jar.
And monitoring the pH value, EC and turbidity parameters of the percolate tank by using an online water quality analyzer. The gas mass flow meter is used for measuring the amount of gas blown into the aerobic fermentation tank by the blower, namely the ventilation quantity, and the ventilation quantity can influence the oxygen concentration and the temperature in the aerobic fermentation tank. Further, the amount of gas blown into the aerobic fermentation tank by the blower is related to the energy consumption of the blower, so that the energy consumption data of the blower needs to be measured. Namely, the set value of a certain gas mass flow meter can correspond to different rotating speeds of the blower, and the energy consumption is minimum through model selection. For example, the required oxygen concentration is 21%, the temperature is 60 ℃, 100 oxygen is required, the gas mass flow meter is set to be 100, the blower can rotate 2000-4000, but the energy consumption can be set to be the minimum at 2500 rotations by comprehensively considering various resistances.
Generally, in aerobic composting processes, two goals are desired: the blower consumes the least energy and the best composting effect. Due to the complex nonlinearity of the composting process, it is difficult to build accurate models of blower energy consumption and composting effects. Therefore, a model of the energy consumption of the blower and the composting effect (the composting effect is represented by the heap C/N and the pH ratio) is established by means of the fuzzy neural network. Through correlation analysis, the input variables of the blower rotating speed prediction model are temperature, humidity, oxygen concentration and a gas mass flow meter set value, and because the humidity is constantly changed under the influence of the temperature and ventilation quantity, and the temperature and the oxygen concentration can be controlled by adjusting the rotating speed of the blower and the rotating speed of the stirrer, the multi-objective optimization problem is the optimization problem of two targets. The decision variables are temperature, oxygen concentration, and the target is blower energy consumption and pile C/N ratio. In the reactor reaction process, the oxygen concentration and the temperature are detected in real time, when the environment changes, the set values of the temperature and the oxygen concentration are optimized, and then a fuzzy controller is used for tracking and controlling the set values.
Based on this, step 200 is: training a first TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set and the historical ventilation data set to determine a ventilation prediction relational expression; training a second TS fuzzy neural network based on the historical oxygen concentration dataset, the historical temperature dataset, and the historical blower energy consumption dataset to determine a blower energy consumption prediction relationship; training a third TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical leachate pH data set to determine a leachate pH prediction relational expression; and training a fourth TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical reactor carbon-nitrogen ratio data set so as to determine a reactor carbon-nitrogen ratio prediction relational expression.
The first TS fuzzy neural network, the second TS fuzzy neural network, the third TS fuzzy neural network, and the fourth TS fuzzy neural network have the same structure, and each of the first TS fuzzy neural network, the second TS fuzzy neural network, the third TS fuzzy neural network, and the fourth TS fuzzy neural network includes an input layer, a fuzzy rule calculation layer, and an output layer, as shown in fig. 2.
For a first TS fuzzy neural network, the input layer is configured to input the historical oxygen concentration data set, the historical temperature data set, and the historical ventilation data set; the historical oxygen concentration data set and the historical temperature data set constitute optimization variables. I.e. z (k) = [ x ] 1 (k) x 2 (k)] T 。
For a second TS fuzzy neural network, the input layer is to input the historical oxygen concentration dataset, the historical temperature dataset, and the historical blower energy consumption dataset; the historical oxygen concentration data set and the historical temperature data set constitute optimization variables. I.e. z (k) = [ x ] 1 (k) x 2 (k)] T 。
For a third TS fuzzy neural network, the input layer is used for inputting the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical leachate pH data set; the historical oxygen concentration data set, the historical temperature data set, and the historical ammonia concentration data set constitute optimization variables. I.e. z (k) = [ x ] 1 (k) x 2 (k) x 3 (k)] T 。
For a fourth TS fuzzy neural network, the input layer is configured to input the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set, and the historical heap carbon-to-nitrogen ratio data set; the historical oxygen concentration data set, the historical temperature data set, and the historical ammonia concentration data set constitute optimization variables. I.e. z (k) = [ x ] 1 (k) x 2 (k) x 3 (k)] T 。
Wherein x is 1 (k) Oxygen concentration data at time k, x 2 (k) Temperature data at time k, x 3 (k) Ammonia concentration data at time k.
In one embodiment, the input layer is connected to the input vector, and each node is connected to the input component z i And connecting, and setting the number of network input nodes to be 4.
For the four TS fuzzy neural networks, the fuzzy layer is used for carrying out fuzzification processing on the optimized variable through a membership degree generating function so as to obtain fuzzy membership degrees; specifically, parameters influencing the rotating speed of the blower are selected, and fuzzification processing is carried out on the parameters through a membership degree generating function (Gaussian function) to obtain the fuzzy membership degree of each input component. Parameters that affect blower speed include: the temperature, the humidity, the oxygen concentration of the pile body and the air outlet and the set value of the gas mass flowmeter in the aerobic fermentation tank.
The fuzzy rule calculation layer is used for calculating fuzzy rules on the fuzzy membership degree; specifically, each node in the neural network is connected with a circuit to form a corresponding jth rule; a multiplication operation is employed.
The output layer is used for receiving all data output by the fuzzy rule calculation layer and correcting the received data according to historical ventilation data/historical blower energy consumption data/historical ammonia concentration data/historical leachate pH data corresponding to the optimization variables so as to determine a ventilation predicted value/blower energy consumption predicted value/ammonia concentration predicted value/leachate pH predicted value. Specifically, the number of output nodes is 1, the network structure is determined to be 4-9-1, the prediction result is corrected, the data are normalized, the mean value of parameter variables is set to be 0, and the standard difference value is set to be 1.0, so that the deviation of different characteristic factors or calculation dimensions on the prediction result of the rotating speed of the air blower is eliminated.
For the first TS fuzzy neural network, the air volume prediction relation is as follows:
h j (z，θ j )＝[1 z T ]·θ j ；
wherein, the first and the second end of the pipe are connected with each other,
the predicted value of the ventilation volume is; n is the number of fuzzy rules, and>
output for the fuzzy layer corresponding to the jth rule, h j Outputting the back piece corresponding to the jth rule; z = [ z ] 1 z 2 z 3 ... z r ] x Is the input of a first TS fuzzy neural network, namely the input of a ventilation prediction relation, r is the number of input optimization variables, theta j J =1, 2.., n, a back-part parameter of the network; a. The jk (z (k)) represents a membership matrix obtained by fuzzifying network input z (k), and z (k) = [ x ] by adopting a Gaussian function 1 (k) x 2 (k)] T ，x 1 (k) Oxygen concentration data at time k, x 2 (k) For the temperature data at time k, z (k) is the optimization variable and is abbreviated as z k 。
And obtaining the corresponding prediction relational expressions of the other three TS fuzzy neural networks in the same way.
In the training process of the fuzzy neural network, 75% of historical data sets corresponding to the neural networks are collected to serve as training samples, and the rest 25% of historical data sets are collected to serve as testing samples. The training parameters are set as follows: 100 times; the activation mode is as follows: relu-Identity activation function, network learning rate: 0.25; training attenuation coefficient: 0.90 to 0.95; regularization coefficient: 0.005, to finally obtain a high-precision prediction model or a prediction relational expression.
In the composting process, the pH and the C/N ratio can be used for representing the humification degree of the compost, the humification degree is used as a constraint condition of the composting characteristic, a functional relation between an optimized set value and an optimized performance index and a model between the energy consumption of a blower and the humification index of the compost and the optimized set value are established, and the prediction and evaluation of the performance index are obtained.
Based on this, step 300 is: establishing an aerobic composting multi-objective optimization model based on the ventilation prediction relational expression, the blower energy consumption prediction relational expression, the percolate pH prediction relational expression and the pile carbon-nitrogen ratio prediction relational expression; the aerobic composting multi-objective optimization model comprises an objective function and a constraint function.
The objective function is:
MinF(x)＝{f ae (x)，f le (x)}；
the constraint function is:
wherein MinF (x) is a function f ae (x) Is a function f of le (x) Are all at a minimum, f ae (x) For the prediction of the blower energy consumption relation, f le (x) For the prediction of the relationship of the ventilation, b 1 、b 2 、b 3 Are all preset constant threshold values, g 1 (x) Prediction of the relationship for the pH of the percolate, g 2 (x) For the prediction of the relation, x, for the carbon-to-nitrogen ratio of the stack 1 (k) Oxygen concentration data at time k, x 2 (k) Is temperature data at time k, x' 1 、x′ 2 Lower limits are set for the oxygen concentration data and the temperature data respectively,
the upper limits are set for the oxygen concentration data and the temperature data, respectively.
1) Processing the constraint function by adopting a penalty function method; specifically, the following penalty function is constructed:
G(x)＝F(x)+Cφ(x)
wherein C is a penalty factor, and when all the feasible solutions are available, C is 0; when the feasible solutions are less, C takes a relatively large value; phi (x) is a penalty term.
After adding the penalty term:
2) And solving the aerobic compost multi-objective optimization model treated by the penalty function method by adopting an NSGA-II algorithm to obtain a group of Pareto optimization solutions.
3) And selecting a Pareto optimal solution from a group of Pareto optimal solutions based on a preset decision. Wherein the preset decision is the oxygen concentration and temperature value required in the actual composting treatment.
Further, solving the aerobic compost multi-target optimization model processed by the penalty function method by adopting an NSGA-II algorithm, and specifically comprising the following steps:
1) Initializing a population P (0), setting the population number N, the evolution algebra Gen =0, the maximum evolution algebra MAX, generating an initial population consisting of individuals of which the population number is 1.5 times by parameters, and solving the fitness of the individuals.
2) And (4) performing non-dominant sorting on the initial population, selecting a high crowding coefficient if the non-dominant grades are the same, and selecting excellent individuals with the number of the population for subsequent iteration, namely generating a parent population.
3) And carrying out cross and mutation operations on the generated parent population to generate an offspring population.
4) And combining the parent and the offspring into a new temporary population.
5) And carrying out rapid non-dominant sorting on the new population.
6) And calculating the dynamic crowding degree and each performance index value of the new temporary population.
7) And selecting the best N individuals as the next generation of evolution population by adopting a guarantee strategy.
8) And (5) repeating the steps (4) - (8) until the evolution algebra reaches the maximum evolution algebra MAX.
Specifically, basic parameters of the multi-objective optimization algorithm are set as follows: the population scale N =60, the maximum evolution algebra MAX =300, the basic cross probability is 0.9, the basic mutation probability is 0.2, and the energy consumption performance index of the blower is calculated by using the functional relation between the performance index and the optimization variable established by the fuzzy neural network, and corresponds to the oxygen concentration optimization set value and the temperature optimization set value in the aerobic fermentation tank.
And 500, inputting the Pareto optimal solution to the PID controller to realize the tracking control of the oxygen concentration and the temperature in the aerobic fermentation tank.
Preferably, the aerobic composting device further comprises a stirrer; the stirrer is arranged in the aerobic fermentation tank. The intelligent control method for aerobic composting further comprises the following steps: the PID controller is adopted to perform self-adaptive adjustment on the rotating speed of the air blower and the rotating speed of the stirrer based on Pareto optimal solution so as to realize the tracking control on the oxygen concentration and the temperature in the aerobic fermentation tank and also realize the closed-loop control on the ventilation quantity, so that the ventilation quantity is always kept in the optimal state and the optimal composting effect is realized.
Specifically, as shown in fig. 3, 2 optimized set values are obtained as input variables according to an aerobic composting optimization model; the input variable is adjusted through the parameter correction module to obtain the proportional coefficient K of the input variable of the PID control module P Integral coefficient K i And a differential coefficient K d (ii) a And then through PID control module, carry out tracking control to gas mass flow meter and agitator rotational speed respectively, and gas mass flow meter can adjust the air-blower rotational speed again to realize real-time tracking control. In FIG. 3, e c (t) represents a blower rotational speed error variation, and e (t) represents a blower rotational speed error.
In a specific embodiment, the intelligent control method for the aerobic composting is realized based on App Designer in Matlab, and an intelligent control visual interface for the aerobic composting is constructed. In this embodiment, when a Matlab design graphical monitoring interface is used to preprocess and model data, the steps include: initialization, sensor data acquisition, real-time data display, predicted data display, storage and transportation, specifically as follows:
after the system is initialized, the system enters a main control interface, calculates the data acquired by each sensor according to a specified parameter reading mode, stores the data in a database, and presents the data on an upper computer interface through a communication protocol and a wireless serial port module, so that real-time monitoring of each index and certain data volume are realized.
The interface design comprises controls such as a selection button, a sliding block, an editing frame and a coordinate axis frame. The specific design comprises the following steps: data display graphics area, control panel and parameter settings. The data display graph area comprises temperature change curve drawing, humidity change curve drawing, oxygen concentration change curve drawing, pH value change curve drawing, EC change curve drawing and turbidity change curve drawing. Wherein, temperature and humidity change curve divide into upper, middle and lower three sensor, and 2 coordinate axle frames show temperature and humidity respectively, and oxygen concentration, pH, EC, turbidity change curve, a coordinate axle frame of every index shows. The control panel is provided with 6 buttons for selecting real-time recording, stopping recording, emptying, copying pictures, saving pictures and setting parameters, 2 pull-down menus are set, and scanning intervals and data types are selected.
The layout of the visual components of the Graphical User Interface (GUI) in the MATLAB running mode and the model interface of the aerobic fermentation intelligent system for composting constructed by the app behavior programming are operated, so that the running index parameters and the model of the composting are expressed more simply and intuitively, the experimental teaching can be applied, the integration level is high, and the operation is simple and convenient.
Example two
As shown in fig. 4, in order to achieve the effect of the technical solution in the first embodiment, the present embodiment further provides an intelligent control system for aerobic composting, which is applied to an aerobic composting device, where the aerobic composting device includes an aerobic fermentation tank, a percolate tank, an air blower, and a PID controller.
The aerobic composting intelligent control system comprises:
the data acquisition module 101 is configured to acquire a historical ventilation volume data set, a historical blower energy consumption data set, a historical leachate pH data set, a historical oxygen concentration data set, a historical ammonia concentration data set, a historical temperature data set, and a historical heap carbon-nitrogen ratio data set in the aerobic fermentation tank.
A relation determination module 201, configured to train a first TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, and the historical ventilation data set to determine a ventilation prediction relation; training a second TS fuzzy neural network based on the historical oxygen concentration dataset, the historical temperature dataset, and the historical blower energy consumption dataset to determine a blower energy consumption prediction relationship; training a third TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical leachate pH data set to determine a leachate pH prediction relational expression; and training a fourth TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical reactor carbon-nitrogen ratio data set so as to determine a reactor carbon-nitrogen ratio prediction relational expression.
And the multi-objective optimization model building module 301 is used for building an aerobic composting multi-objective optimization model based on the ventilation prediction relational expression, the blower energy consumption prediction relational expression, the leachate pH prediction relational expression and the pile carbon-nitrogen ratio prediction relational expression.
The multi-objective optimization model solving module 401 is used for solving the aerobic composting multi-objective optimization model to obtain a Pareto optimal solution; the Pareto optimal solution comprises an oxygen concentration optimal set value and a temperature optimal set value in the aerobic fermentation tank.
And the PID control module 501 is used for inputting the Pareto optimal solution to the PID controller so as to realize the tracking control of the oxygen concentration and the temperature in the aerobic fermentation tank.
In one embodiment, as shown in fig. 5, the aerobic composting intelligent control system comprises a multi-objective optimization module, a bottom layer tracking control module and a composting process. In the multi-objective optimization module, a neural network is constructed through data acquired by an offline data acquisition submodule; performing online optimization by combining real-time data and NSGAII to obtain a predicted value of ventilation volume, a predicted value of energy consumption of a blower, a predicted value of pH of percolate and a predicted value of carbon-nitrogen ratio of a pile body; and then the oxygen concentration and the temperature in the air blower and the aerobic fermentation tank are optimally controlled through the corresponding PID controller so as to realize high-precision aerobic composting control. And fig. 6 is a schematic diagram of the overall architecture of the aerobic composting intelligent control system.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the description of the method part.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the foregoing, the description is not to be taken in a limiting sense.
Claims (8)
1. An intelligent control method for aerobic composting is characterized by being applied to an aerobic composting device, wherein the aerobic composting device comprises an aerobic fermentation tank, a percolate liquid tank, an air blower and a PID (proportion integration differentiation) controller;
the intelligent control method for aerobic composting comprises the following steps:
acquiring a historical ventilation volume data set, a historical blower energy consumption data set, a historical leachate pH data set, a historical oxygen concentration data set, a historical ammonia concentration data set, a historical temperature data set and a historical pile carbon-nitrogen ratio data set in the aerobic fermentation tank;
training a first TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set and the historical ventilation data set to determine a ventilation prediction relational expression; training a second TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set and the historical blower energy consumption data set to determine a blower energy consumption prediction relational expression; training a third TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical leachate pH data set to determine a leachate pH prediction relational expression; training a fourth TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical carbon-nitrogen ratio data set of the pile body to determine a pile body carbon-nitrogen ratio prediction relational expression;
establishing an aerobic composting multi-objective optimization model based on the ventilation prediction relational expression, the blower energy consumption prediction relational expression, the percolate pH prediction relational expression and the pile carbon-nitrogen ratio prediction relational expression;
solving the aerobic composting multi-target optimization model to obtain a Pareto optimal solution; the Pareto optimal solution comprises an oxygen concentration optimal set value and a temperature optimal set value in the aerobic fermentation tank;
and inputting the Pareto optimal solution to the PID controller to realize the tracking control of the oxygen concentration and the temperature in the aerobic fermentation tank.
2. The intelligent control method for aerobic composting according to claim 1 wherein the first TS fuzzy neural network comprises an input layer, a fuzzy rule calculation layer and an output layer;
the input layer is used for inputting the historical oxygen concentration data set, the historical temperature data set and the historical ventilation data set; the historical oxygen concentration data set and the historical temperature data set form optimization variables;
the fuzzy layer is used for carrying out fuzzy processing on the optimized variable through a membership degree generating function so as to obtain fuzzy membership degree;
the fuzzy rule calculation layer is used for calculating fuzzy rules on the fuzzy membership degree;
and the output layer is used for receiving all the data output by the fuzzy rule calculation layer and correcting the received data according to the historical ventilation data corresponding to the optimized variables so as to determine a ventilation predicted value.
3. An intelligent control method for aerobic composting according to claim 2 wherein the predicted ventilation is as follows:
wherein the content of the first and second substances,
the predicted value of the ventilation volume is obtained; n is the number of fuzzy rules, and>
output for the fuzzy layer corresponding to the jth rule, h j Outputting the back piece corresponding to the jth rule; z = [ z ] 1 z 2 z 3 … z r ] T Is the input of a first TS fuzzy neural network, namely the input of a ventilation prediction relation, r is the number of input optimization variables, theta j J =1,2, \ 8230;, n; a. The jk (z (k)) means the network input z (k) is fuzzifiedMembership matrix, z (k) = [ x ] 1 (k) x 2 (k)] T ，x 1 (k) Oxygen concentration data at time k, x 2 (k) For the temperature data at time k, z (k) is the optimization variable and is abbreviated as z k 。
4. The intelligent control method for aerobic composting according to claim 1, wherein the multi-objective optimization model for aerobic composting comprises an objective function and a constraint function;
the objective function is:
MinF(k)＝{f ae (x),f le (x)}；
the constraint function is:
wherein MinF (x) is a function f ae (x) Is a function of f le (x) Are all at a minimum, f ae (x) For the prediction of the blower energy consumption relation, f le (x) For the prediction of the relationship of the ventilation, b 1 、b 2 、b 3 Are all preset constant thresholds, g 1 (x) Prediction of leachate pH relationship, g 2 (x) For predicting the relation, x, of the carbon-to-nitrogen ratio of the stack 1 (k) Oxygen concentration data at time k, x 2 (k) Is temperature data at time k, x' 1 、x' 2 Lower limits are set for the oxygen concentration data and the temperature data respectively,
set upper limits for oxygen concentration data and temperature data, respectively.
5. The intelligent control method for aerobic composting according to claim 4, wherein solving the aerobic composting multi-objective optimization model to obtain a Pareto optimal solution specifically comprises:
processing the constraint function by adopting a penalty function method;
solving the aerobic composting multi-target optimization model processed by the penalty function method by adopting an NSGA-II algorithm to obtain a group of Pareto optimization solutions;
and selecting a Pareto optimal solution from a group of Pareto optimal solutions based on a preset decision.
6. The intelligent control method for aerobic composting according to claim 1, wherein the aerobic composting apparatus further comprises a stirrer; the stirrer is arranged in the aerobic fermentation tank;
the intelligent control method for aerobic composting further comprises the following steps:
and adjusting the rotating speed of the air blower and the rotating speed of the stirrer based on Pareto optimal solution by adopting the PID controller so as to realize the tracking control of the oxygen concentration and the temperature in the aerobic fermentation tank.
7. The intelligent control method for aerobic composting according to claim 1, wherein the intelligent control method for aerobic composting is realized based on App Designer in Matlab, and an intelligent control visual interface for aerobic composting is constructed.
8. An aerobic composting intelligent control system is characterized by being applied to an aerobic composting device, wherein the aerobic composting device comprises an aerobic fermentation tank, a percolation liquid tank, an air blower and a PID (proportion integration differentiation) controller;
the aerobic composting intelligent control system comprises:
the data acquisition module is used for acquiring a historical ventilation volume data set, a historical blower energy consumption data set, a historical leachate pH data set, a historical oxygen concentration data set, a historical ammonia concentration data set, a historical temperature data set and a historical pile carbon-nitrogen ratio data set in the aerobic fermentation tank;
a relational expression determination module for training a first TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set and the historical ventilation data set to determine a ventilation prediction relational expression; training a second TS fuzzy neural network based on the historical oxygen concentration dataset, the historical temperature dataset, and the historical blower energy consumption dataset to determine a blower energy consumption prediction relationship; training a third TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical leachate pH data set to determine a leachate pH prediction relational expression; training a fourth TS fuzzy neural network based on the historical oxygen concentration data set, the historical temperature data set, the historical ammonia concentration data set and the historical reactor carbon-nitrogen ratio data set to determine a reactor carbon-nitrogen ratio prediction relational expression;
the multi-objective optimization model building module is used for building an aerobic composting multi-objective optimization model based on the air volume prediction relational expression, the air blower energy consumption prediction relational expression, the percolate pH prediction relational expression and the pile carbon-nitrogen ratio prediction relational expression;
the multi-objective optimization model solving module is used for solving the aerobic composting multi-objective optimization model to obtain a Pareto optimal solution; the Pareto optimal solution comprises an oxygen concentration optimal set value and a temperature optimal set value in the aerobic fermentation tank;
and the PID control module is used for inputting the Pareto optimal solution to the PID controller so as to realize the tracking control of the oxygen concentration and the temperature in the aerobic fermentation tank.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310137870.2A CN115959933B (en) | 2023-02-20 | 2023-02-20 | Intelligent control method and system for aerobic composting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310137870.2A CN115959933B (en) | 2023-02-20 | 2023-02-20 | Intelligent control method and system for aerobic composting |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115959933A true CN115959933A (en) | 2023-04-14 |
| CN115959933B CN115959933B (en) | 2024-05-28 |
Family
ID=87358589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310137870.2A Active CN115959933B (en) | 2023-02-20 | 2023-02-20 | Intelligent control method and system for aerobic composting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115959933B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117976081A (en) * | 2024-04-02 | 2024-05-03 | 北京市农林科学院 | Composting formula method, system, equipment and medium based on model predictive optimization |
| CN117976081B (en) * | 2024-04-02 | 2024-07-16 | 北京市农林科学院 | Composting formula method, system, equipment and medium based on model predictive optimization |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106950824A (en) * | 2016-01-07 | 2017-07-14 | 及长城 | Stalk fermentation alcohol fuel process feeding prediction control system and method based on fuzzy neural network |
| CN110991756A (en) * | 2019-12-09 | 2020-04-10 | 北京工业大学 | MSWI furnace temperature prediction method based on TS fuzzy neural network |
| CN112299893A (en) * | 2020-12-24 | 2021-02-02 | 南京斯酷环境科技有限公司 | Remote monitoring type kitchen garbage fermentation bin intelligent control system and method thereof |
-
2023
- 2023-02-20 CN CN202310137870.2A patent/CN115959933B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106950824A (en) * | 2016-01-07 | 2017-07-14 | 及长城 | Stalk fermentation alcohol fuel process feeding prediction control system and method based on fuzzy neural network |
| CN110991756A (en) * | 2019-12-09 | 2020-04-10 | 北京工业大学 | MSWI furnace temperature prediction method based on TS fuzzy neural network |
| CN112299893A (en) * | 2020-12-24 | 2021-02-02 | 南京斯酷环境科技有限公司 | Remote monitoring type kitchen garbage fermentation bin intelligent control system and method thereof |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117976081A (en) * | 2024-04-02 | 2024-05-03 | 北京市农林科学院 | Composting formula method, system, equipment and medium based on model predictive optimization |
| CN117976081B (en) * | 2024-04-02 | 2024-07-16 | 北京市农林科学院 | Composting formula method, system, equipment and medium based on model predictive optimization |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115959933B (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Han et al. | Dynamic MOPSO-based optimal control for wastewater treatment process | |
| Dochain | Automatic control of bioprocesses | |
| Chen et al. | Modelling and optimization of fed-batch fermentation processes using dynamic neural networks and genetic algorithms | |
| US9747544B2 (en) | Method and system for wastewater treatment based on dissolved oxygen control by fuzzy neural network | |
| CN112661259A (en) | Self-adaptive control method and system for aeration process | |
| Chen et al. | A case study of adaptive nonlinear regulation of fed-batch biological reactors | |
| CN113139342B (en) | Aerobic compost monitoring system and result prediction method | |
| CN101763036A (en) | Lysine fermentation process feeding prediction control system and method based on fuzzy neural network | |
| CN108319150B (en) | Full-running state information sensing and optimal control system and method for biogas system | |
| Li et al. | An effective integrated control with intelligent optimization for wastewater treatment process | |
| CN101748186A (en) | FSVM-based lysine fermentation process key state variable soft measuring method and system | |
| CN113189881A (en) | Multi-objective optimization control method and system for sewage treatment | |
| Baishan et al. | Using genetic algorithms coupling neural networks in a study of xylitol production: medium optimisation | |
| Gao et al. | Modeling and parameter identification of microbial batch fermentation under environmental disturbances | |
| CN115356930A (en) | Multi-objective optimization control system and method in sewage treatment process | |
| Li et al. | An effective dynamic immune optimization control for the wastewater treatment process | |
| CN110705752A (en) | Sewage BOD real-time prediction method based on ANFIS and mechanism model | |
| CN115959933B (en) | Intelligent control method and system for aerobic composting | |
| Nicoletti et al. | Computational intelligence techniques as tools for bioprocess modelling, optimization, supervision and control | |
| Venkateswarlu | Advances in monitoring and state estimation of bioreactors | |
| Flores et al. | Dissolved oxygen regulation by logarithmic/antilogarithmic control to improve a wastewater treatment process | |
| CN101419216B (en) | Fermentation pharmacy product quality soft measurement method based on GP learning model building | |
| Zhang et al. | Reliable multi-objective on-line re-optimisation control of a fed-batch fermentation process using bootstrap aggregated neural networks | |
| Dacosta et al. | Estimation of inaccessible fermentation states with variable inoculum sizes | |
| CN113221436A (en) | Soft measurement method for sewage suspended matter concentration based on improved RBF neural network |
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 |