CN105550774A - Facility feed delivery prediction method and prediction system - Google Patents
Facility feed delivery prediction method and prediction system Download PDFInfo
- Publication number
- CN105550774A CN105550774A CN201510917855.5A CN201510917855A CN105550774A CN 105550774 A CN105550774 A CN 105550774A CN 201510917855 A CN201510917855 A CN 201510917855A CN 105550774 A CN105550774 A CN 105550774A
- Authority
- CN
- China
- Prior art keywords
- data
- layer
- neuron node
- neural network
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The invention discloses a facility feed delivery prediction method and prediction system and belongs to the Internet of things field. The method includes the following steps that: a BP neural network model is built; data to be predicted and sample data are read from a database, and normalization processing is performed on the data to be predicted and the sample data; the normalized sample data are input into the BP neural network model, so that learning can be carried out, and therefore, connection weight parameters between each layer in the BP neural network can be determined; the normalized data to be predicted are inputted to the BP neural network model, so that the BP neural network model can calculate the normalized data to be predicted according to the connection weight parameters between each layer, so that predicted feed delivery quantity can be obtained. According to the facility feed delivery prediction method and prediction system of the invention, the BP neural network model is utilized to predict the optimal delivery quantity of facility breeding in a certain period, and delivery and detection can be carried out based on the optimal delivery quantity, and therefore, facility feed delivery techniques can be optimized, feed delivery cost can be decreased, labor cost can be reduced, and the quality of facility breeding can be improved.
Description
Technical field
The present invention relates to Internet of Things field, particularly a kind of facility feeds intake Forecasting Methodology and system.
Background technology
Along with cost of labor go up gradually and intelligent sensing equipment in the continuous infiltration of enterprise's production field, technology of Internet of things and decision support method come into one's own all the more in facility cultivation field.
At present, in conventional facilities cultivation, the input of feed follows cultivation experience and science data instruct lower semi-automatic input always, and the control essence of feed injected volume determines also practical operation by artificial.Fig. 1 is the control schematic diagram that feeds intake of the prior art.Wherein, to be fed intake by timing and manual batch to feed intake demand, when there is actual deviation, by manually carrying out patrolling and examining correction to meet facility cultivation.
Under common situation, the actual conditions that business facility breeding feed is thrown in are that usual injected volume departs from real demand.Injected volume too much causes cost of idleness, very fewly can not meet again animal normal growth demand.The precision increase cost of labor that repeatedly manual inspection is extra in a large number with throwing in operation generation that enterprise throws in control feed.
Summary of the invention
The embodiment of the present invention provides a kind of facility to feed intake Forecasting Methodology and system, by building BP neural network model, determine the connection weight of each interlayer of BP neural network model, thus BP Neural Network model predictive can be utilized to go out the best injected volume of facility cultivation in some cycles, carry out accordingly throwing in and detecting, can reach and optimize facility charging technology, save the cost that feeds intake, reduce the object of cost of labor and lifting facility cultivation quality.
According to an aspect of the present invention, provide a kind of facility to feed intake Forecasting Methodology, comprising:
Build back-propagating BP neural network model;
Read data to be predicted and sample data from database, and be normalized, wherein data to be predicted and the temperature in facility cultivation environment, quality, time, cultivation quantity and the unit mass cost that feeds intake is relevant;
Sample data input BP neural network model through normalized is learnt, to determine the connection weight parameter in BP neural network between each layer;
By the data input BP neural network model to be predicted through normalized, so that BP neural network model calculates the data to be predicted through normalized according to the connection weight parameter of each interlayer, thus obtain predicting inventory.
In one embodiment, BP neural network model comprises input layer, hidden layer and output layer, wherein in hidden layer, and being input as of a jth neuron node:
Wherein 1≤j≤m, m is the number of neuron node in hidden layer, and 1≤i≤n, n is the number of neuron node in input layer, x
ifor the input data that i-th neuron node in input layer provides, ω
ijfor the connection weight of i-th neuron node in the neuron node of jth in hidden layer and input layer, θ
jfor the threshold value of the neuron node of jth in hidden layer.
In one embodiment, in hidden layer, the output of a jth neuron node is:
O
j=f(I
j)
Wherein f is transport function.
In one embodiment, transport function is:
In one embodiment, the neuron node number n in input layer is 5;
In hidden layer, the number m of neuron node is 6;
Output layer comprises a neuron node.
In one embodiment, the output of output layer neuron node is:
Wherein v
jfor the connection weight of a jth neuron node in output layer neuron node and hidden layer.
In one embodiment, in input layer, the data that the data that data represent the facility cultivation time, fourth nerve unit node receives represent facility cultivation quantity, fifth nerve unit node receives that the data that the data that peripheral sensory neuron node receives represent temperature in facility cultivation environment, nervus opticus unit node receives represent the quality of facility cultivation environment, third nerve unit node receives represent unit mass and to feed intake cost.
According to a further aspect in the invention, provide a kind of facility to feed intake prognoses system, comprise model construction unit, pretreatment unit, parameter learning unit and predicting unit, wherein:
Model construction unit, for building back-propagating BP neural network model;
Pretreatment unit, for reading data to be predicted and sample data from database, and is normalized, and wherein data to be predicted and the temperature in facility cultivation environment, quality, time, cultivation quantity and the unit mass cost that feeds intake is relevant;
Parameter learning unit, for learning the sample data input BP neural network model through normalized, to determine the connection weight parameter in BP neural network between each layer;
Predicting unit, for by the data input BP neural network model to be predicted through normalized, so that BP neural network model calculates the data to be predicted through normalized according to the connection weight parameter of each interlayer, thus obtains predicting inventory.
In one embodiment, BP neural network model comprises input layer, hidden layer and output layer, wherein in hidden layer, and being input as of a jth neuron node:
Wherein 1≤j≤m, m is the number of neuron node in hidden layer, and 1≤i≤n, n is the number of neuron node in input layer, x
ifor the input data that i-th neuron node in input layer provides, ω
ijfor the connection weight of i-th neuron node in the neuron node of jth in hidden layer and input layer, θ
jfor the threshold value of the neuron node of jth in hidden layer.
In one embodiment, in hidden layer, the output of a jth neuron node is:
O
j=f(I
j)
Wherein f is transport function.
In one embodiment, transport function is:
In one embodiment, the neuron node number n in input layer is 5;
In hidden layer, the number m of neuron node is 6;
Output layer comprises a neuron node.
In one embodiment, the output of output layer neuron node is:
Wherein v
jfor the connection weight of a jth neuron node in output layer neuron node and hidden layer.
In one embodiment, in input layer, the data that the data that data represent the facility cultivation time, fourth nerve unit node receives represent facility cultivation quantity, fifth nerve unit node receives that the data that the data that peripheral sensory neuron node receives represent temperature in facility cultivation environment, nervus opticus unit node receives represent the quality of facility cultivation environment, third nerve unit node receives represent unit mass and to feed intake cost.
By referring to the detailed description of accompanying drawing to exemplary embodiment of the present invention, further feature of the present invention and advantage thereof will become clear.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the control schematic diagram that feeds intake of the prior art.
Fig. 2 is that facility of the present invention feeds intake the schematic diagram of a Forecasting Methodology embodiment.
Fig. 3 is the schematic diagram of BP neural network model.
Fig. 4 is the schematic diagram of a BP neural network model backward learning of the present invention embodiment.
Fig. 5 is that facility of the present invention feeds intake the schematic diagram of a prognoses system embodiment.
Fig. 6 is the control schematic diagram that feeds intake of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Illustrative to the description only actually of at least one exemplary embodiment below, never as any restriction to the present invention and application or use.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Unless specifically stated otherwise, otherwise positioned opposite, the numerical expression of the parts of setting forth in these embodiments and step and numerical value do not limit the scope of the invention.
Meanwhile, it should be understood that for convenience of description, the size of the various piece shown in accompanying drawing is not draw according to the proportionate relationship of reality.
May not discuss in detail for the known technology of person of ordinary skill in the relevant, method and apparatus, but in the appropriate case, described technology, method and apparatus should be regarded as a part of authorizing instructions.
In all examples with discussing shown here, any occurrence should be construed as merely exemplary, instead of as restriction.Therefore, other example of exemplary embodiment can have different values.
It should be noted that: represent similar terms in similar label and letter accompanying drawing below, therefore, once be defined in an a certain Xiang Yi accompanying drawing, then do not need to be further discussed it in accompanying drawing subsequently.
Fig. 2 is that facility of the present invention feeds intake the schematic diagram of a Forecasting Methodology embodiment.Wherein:
Step 201, builds BP (BackPropagation, back-propagating) neural network model.
Such as, BP neural network model can comprise input layer, hidden layer and output layer, and each layer is provided with corresponding neuron node.
Step 202, reads data to be predicted and sample data from database, and is normalized, and wherein data to be predicted and the temperature in facility cultivation environment, quality, time, cultivation quantity and the unit mass cost that feeds intake is relevant.
By normalization, data are arranged between 0 to 1.Such as, for data x, utilize formula
(x-x
mim)/(x
max-x
mim)
X is normalized, wherein x
minfor the minimum value of x, x
maxfor the maximal value of x.
Step 203, learns the sample data input BP neural network model through normalized, to determine the connection weight parameter in BP neural network between each layer.
Step 204, by the data input BP neural network model to be predicted through normalized, so that BP neural network model calculates the data to be predicted through normalized according to the connection weight parameter of each interlayer, thus obtains predicting inventory.
The facility provided based on the above embodiment of the present invention feeds intake Forecasting Methodology, by building BP neural network model, determine the connection weight of each interlayer of BP neural network model, thus BP Neural Network model predictive can be utilized to go out the best injected volume of facility cultivation in some cycles, carry out accordingly throwing in and detecting, can reach and optimize facility charging technology, save the cost that feeds intake, reduce the object of cost of labor and lifting facility cultivation quality.
Fig. 3 is the schematic diagram of BP neural network model involved in the present invention, is wherein equipped with corresponding neuron node at each layer.Wherein in hidden layer, being input as of a jth neuron node:
Wherein 1≤j≤m, m is the number of neuron node in hidden layer, and 1≤i≤n, n is the number of neuron node in input layer, x
ifor the input data that i-th neuron node in input layer provides, ω
ijfor the connection weight of i-th neuron node in the neuron node of jth in hidden layer and input layer, θ
jfor the threshold value of the neuron node of jth in hidden layer.
Accordingly, in hidden layer, the output of a jth neuron node is:
O
j=f(I
j)
Wherein f is transport function.
Preferably, transport function is:
Wherein, the connection weight vector matrix W between input layer and hidden layer between each neuron node is:
Such as, ω
mnfor the connection weight of the n-th neuron node in m neuron node in hidden layer and input layer.
In addition, the input information structure vector X that in input layer, each neuron node receives, wherein:
X={x
1,x
2,…,x
n}
T
In one embodiment, the neuron node number n in input layer is 5, and in hidden layer, the number m of neuron node is 6, and output layer comprises a neuron node.
Preferably, in input layer, the data that the data that data represent the facility cultivation time, fourth nerve unit node receives represent facility cultivation quantity, fifth nerve unit node receives that the data that the data that peripheral sensory neuron node receives represent temperature in facility cultivation environment, nervus opticus unit node receives represent the quality of facility cultivation environment, third nerve unit node receives represent unit mass and to feed intake cost.
In this case, the connection weight vector matrix V between hidden layer between each neuron node and output layer neuron node is:
V={v
1,v
2,…,v
m}
T
Accordingly, the output of output layer neuron node is:
Wherein v
jfor the connection weight of a jth neuron node in output layer neuron node and hidden layer.
In addition, learn for by the sample data input BP neural network model through normalized, to determine the connection weight parameter in BP neural network between each layer, many algorithms can be adopted realize, be described for L-M (Levenberg-Marquardt) algorithm below, as shown in Figure 4.
Step 401, setting training error permissible value ε, and set initialization weight vector W
k, wherein k=0.
Step 402, by the sample data input BP neural network model through normalized, to obtain Output rusults, according to result determination error vector E (W
k) and E (W
k+1).
Wherein,
Y (k) and O (k) is that network output layer exports and desired output respectively, and k represents kth time iterative computation.
Step 403, judges E (W
k) and E (W
k+1) size.If E is (W
k+1) <E (W
k), then perform step 405, otherwise perform step 404.
Step 404, carries out weight vector iteration, W
k+1=W
k+ Δ W
k.
Step 405, judges || J
(k+1) Te
k+1|| whether≤ε sets up.If || J
(k+1) Te
k+1||≤ε sets up, then show to reach minimal value, performs step 406; Otherwise perform step 407.
Wherein J represents Jacobian matrix, and carrying out owing to utilizing Jacobian matrix calculating is that those skilled in the art understand, and does not therefore launch here to describe.
Step 406, by W
kas the weight vector that model uses.And exit this circulation.
Step 407, upgraded by k, i.e. k=k+1, then returns step 402 and circulates.
Fig. 5 is that facility of the present invention feeds intake the schematic diagram of a prognoses system embodiment.As shown in Figure 5, the facility prognoses system that feeds intake comprises model construction unit 501, pretreatment unit 502, parameter learning unit 503 and predicting unit 504, wherein:
Model construction unit 501, for building back-propagating BP neural network model.
Pretreatment unit 502, for reading data to be predicted and sample data from database, and is normalized, and wherein data to be predicted and the temperature in facility cultivation environment, quality, time, cultivation quantity and the unit mass cost that feeds intake is relevant.
Parameter learning unit 503, for learning the sample data input BP neural network model through normalized, to determine the connection weight parameter in BP neural network between each layer.
Predicting unit 504, for by the data input BP neural network model to be predicted through normalized, so that BP neural network model calculates the data to be predicted through normalized according to the connection weight parameter of each interlayer, thus obtains predicting inventory.
The facility provided based on the above embodiment of the present invention feeds intake prognoses system, by building BP neural network model, determine the connection weight of each interlayer of BP neural network model, thus BP Neural Network model predictive can be utilized to go out the best injected volume of facility cultivation in some cycles, carry out accordingly throwing in and detecting, can reach and optimize facility charging technology, save the cost that feeds intake, reduce the object of cost of labor and lifting facility cultivation quality.
Preferably, BP neural network model comprises input layer, hidden layer and output layer, wherein in hidden layer, and being input as of a jth neuron node:
Wherein 1≤j≤m, m is the number of neuron node in hidden layer, and 1≤i≤n, n is the number of neuron node in input layer, x
ifor the input data that i-th neuron node in input layer provides, ω
ijfor the connection weight of i-th neuron node in the neuron node of jth in hidden layer and input layer, θ
jfor the threshold value of the neuron node of jth in hidden layer.
Preferably, in hidden layer, the output of a jth neuron node is:
O
j=f(I
j)
Wherein f is transport function.
Preferably, transport function is:
In one embodiment, the neuron node number n in input layer is 5, and in hidden layer, the number m of neuron node is 6, and output layer comprises a neuron node.
In this case, the output of output layer neuron node is:
Wherein v
jfor the connection weight of a jth neuron node in output layer neuron node and hidden layer.
Preferably, in input layer, the data that the data that data represent the facility cultivation time, fourth nerve unit node receives represent facility cultivation quantity, fifth nerve unit node receives that the data that the data that peripheral sensory neuron node receives represent temperature in facility cultivation environment, nervus opticus unit node receives represent the quality of facility cultivation environment, third nerve unit node receives represent unit mass and to feed intake cost.
Owing to determining that each interlayer connection weights are that those skilled in the art understood by backward learning in BP neural network, therefore do not launch here to describe.
Fig. 6 is the control schematic diagram that feeds intake of the present invention.By based on BP neural network algorithm, to feed intake cost (q) parameter in conjunction with temperature (t), quality (M), time (T), cultivation quantity (P), unit mass in the facilities environment obtained, build three layers of BP neuroid, and adopt L-M backward learning algorithm to carry out connecting the calculating of weight vector, finally go out the best injected volume of feed of facility cultivation in some cycles with this model computational prediction, and carry out automatic switching and put and monitor.Reach reduction to feed intake cost, save artificial and promote the object of cultivation quality.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can have been come by hardware, the hardware that also can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium mentioned can be ROM (read-only memory), disk or CD etc.
Description of the invention provides in order to example with for the purpose of describing, and is not exhaustively or limit the invention to disclosed form.Many modifications and variations are obvious for the ordinary skill in the art.Selecting and describing embodiment is in order to principle of the present invention and practical application are better described, and enables those of ordinary skill in the art understand the present invention thus design the various embodiments with various amendment being suitable for special-purpose.
Claims (14)
1. facility feeds intake a Forecasting Methodology, it is characterized in that, comprising:
Build back-propagating BP neural network model;
Read data to be predicted and sample data from database, and be normalized, wherein data to be predicted and the temperature in facility cultivation environment, quality, time, cultivation quantity and the unit mass cost that feeds intake is relevant;
Sample data input BP neural network model through normalized is learnt, to determine the connection weight parameter in BP neural network between each layer;
By the data input BP neural network model to be predicted through normalized, so that BP neural network model calculates the data to be predicted through normalized according to the connection weight parameter of each interlayer, thus obtain predicting inventory.
2. method according to claim 1, is characterized in that,
BP neural network model comprises input layer, hidden layer and output layer, wherein in hidden layer, and being input as of a jth neuron node:
Wherein 1≤j≤m, m is the number of neuron node in hidden layer, and 1≤i≤n, n is the number of neuron node in input layer, x
ifor the input data that i-th neuron node in input layer provides, ω
ijfor the connection weight of i-th neuron node in the neuron node of jth in hidden layer and input layer, θ
jfor the threshold value of the neuron node of jth in hidden layer.
3. method according to claim 2, is characterized in that,
In hidden layer, the output of a jth neuron node is:
O
j=f(I
j)
Wherein f is transport function.
4. method according to claim 3, is characterized in that,
Transport function is:
5. method according to claim 4, is characterized in that,
Neuron node number n in input layer is 5;
In hidden layer, the number m of neuron node is 6;
Output layer comprises a neuron node.
6. method according to claim 5, is characterized in that,
The output of output layer neuron node is:
Wherein v
jfor the connection weight of a jth neuron node in output layer neuron node and hidden layer.
7. method according to claim 5, is characterized in that,
In input layer, the data that the data that data represent the facility cultivation time, fourth nerve unit node receives represent facility cultivation quantity, fifth nerve unit node receives that the data that the data that peripheral sensory neuron node receives represent temperature in facility cultivation environment, nervus opticus unit node receives represent the quality of facility cultivation environment, third nerve unit node receives represent unit mass and to feed intake cost.
8. facility feeds intake a prognoses system, it is characterized in that, comprises model construction unit, pretreatment unit, parameter learning unit and predicting unit, wherein:
Model construction unit, for building back-propagating BP neural network model;
Pretreatment unit, for reading data to be predicted and sample data from database, and is normalized, and wherein data to be predicted and the temperature in facility cultivation environment, quality, time, cultivation quantity and the unit mass cost that feeds intake is relevant;
Parameter learning unit, for learning the sample data input BP neural network model through normalized, to determine the connection weight parameter in BP neural network between each layer;
Predicting unit, for by the data input BP neural network model to be predicted through normalized, so that BP neural network model calculates the data to be predicted through normalized according to the connection weight parameter of each interlayer, thus obtains predicting inventory.
9. system according to claim 8, is characterized in that,
BP neural network model comprises input layer, hidden layer and output layer, wherein in hidden layer, and being input as of a jth neuron node:
Wherein 1≤j≤m, m is the number of neuron node in hidden layer, and 1≤i≤n, n is the number of neuron node in input layer, x
ifor the input data that i-th neuron node in input layer provides, ω
ijfor the connection weight of i-th neuron node in the neuron node of jth in hidden layer and input layer, θ
jfor the threshold value of the neuron node of jth in hidden layer.
10. system according to claim 9, is characterized in that,
In hidden layer, the output of a jth neuron node is:
O
j=f(I
j)
Wherein f is transport function.
11. systems according to claim 10, is characterized in that,
Transport function is:
12. methods according to claim 11, is characterized in that,
Neuron node number n in input layer is 5;
In hidden layer, the number m of neuron node is 6;
Output layer comprises a neuron node.
13. systems according to claim 12, is characterized in that,
The output of output layer neuron node is:
Wherein v
jfor the connection weight of a jth neuron node in output layer neuron node and hidden layer.
14. systems according to claim 12, is characterized in that,
In input layer, the data that the data that data represent the facility cultivation time, fourth nerve unit node receives represent facility cultivation quantity, fifth nerve unit node receives that the data that the data that peripheral sensory neuron node receives represent temperature in facility cultivation environment, nervus opticus unit node receives represent the quality of facility cultivation environment, third nerve unit node receives represent unit mass and to feed intake cost.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510917855.5A CN105550774A (en) | 2015-12-11 | 2015-12-11 | Facility feed delivery prediction method and prediction system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510917855.5A CN105550774A (en) | 2015-12-11 | 2015-12-11 | Facility feed delivery prediction method and prediction system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105550774A true CN105550774A (en) | 2016-05-04 |
Family
ID=55829955
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510917855.5A Pending CN105550774A (en) | 2015-12-11 | 2015-12-11 | Facility feed delivery prediction method and prediction system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105550774A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106408085A (en) * | 2016-08-31 | 2017-02-15 | 天津南大通用数据技术股份有限公司 | BP neural network classification method for solving nonlinear problem through single hidden layer |
CN106875034A (en) * | 2016-12-29 | 2017-06-20 | 中国农业大学 | A kind of pig-breeding multivariable feedstuff feeding decision-making technique and its system |
CN107480395A (en) * | 2017-08-29 | 2017-12-15 | 燕山大学 | A kind of construction method and system of vehicle steering knuckle loading spectrum forecast model |
CN117275615A (en) * | 2023-10-31 | 2023-12-22 | 源康(东阿)健康科技有限公司 | Intelligent treatment method and system for gelatin production wastewater |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080256017A1 (en) * | 2007-04-12 | 2008-10-16 | Kabushiki Kaisha Toshiba | Information evaluation system and method for evaluating information |
CN103942229A (en) * | 2013-01-22 | 2014-07-23 | 日电(中国)有限公司 | Destination prediction device and method |
-
2015
- 2015-12-11 CN CN201510917855.5A patent/CN105550774A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080256017A1 (en) * | 2007-04-12 | 2008-10-16 | Kabushiki Kaisha Toshiba | Information evaluation system and method for evaluating information |
CN103942229A (en) * | 2013-01-22 | 2014-07-23 | 日电(中国)有限公司 | Destination prediction device and method |
Non-Patent Citations (1)
Title |
---|
宗跃阳 等: "基于BP神经网络的纺纱投料预测", 《工业控制计算机》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106408085A (en) * | 2016-08-31 | 2017-02-15 | 天津南大通用数据技术股份有限公司 | BP neural network classification method for solving nonlinear problem through single hidden layer |
CN106875034A (en) * | 2016-12-29 | 2017-06-20 | 中国农业大学 | A kind of pig-breeding multivariable feedstuff feeding decision-making technique and its system |
CN107480395A (en) * | 2017-08-29 | 2017-12-15 | 燕山大学 | A kind of construction method and system of vehicle steering knuckle loading spectrum forecast model |
CN107480395B (en) * | 2017-08-29 | 2019-12-13 | 燕山大学 | Method and system for constructing vehicle steering knuckle load spectrum prediction model |
CN117275615A (en) * | 2023-10-31 | 2023-12-22 | 源康(东阿)健康科技有限公司 | Intelligent treatment method and system for gelatin production wastewater |
CN117275615B (en) * | 2023-10-31 | 2024-04-09 | 源康(东阿)健康科技有限公司 | Intelligent treatment method and system for gelatin production wastewater |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20200279149A1 (en) | Method for reinforcement learning using virtual environment generated by deep learning | |
Lu et al. | Generalized radial basis function neural network based on an improved dynamic particle swarm optimization and AdaBoost algorithm | |
Jiang et al. | Prediction of house price based on the back propagation neural network in the keras deep learning framework | |
CN108665106A (en) | A kind of aquaculture dissolved oxygen prediction method and device | |
CN105550774A (en) | Facility feed delivery prediction method and prediction system | |
Han et al. | Hierarchical extreme learning machine for feedforward neural network | |
CN104662526A (en) | Apparatus and methods for efficient updates in spiking neuron networks | |
Huang et al. | Orthogonal least squares algorithm for training cascade neural networks | |
CN111612125B (en) | Novel HTM time pool method and system for online learning | |
CN110794308B (en) | Method and device for predicting train battery capacity | |
CN106095812A (en) | Intelligent test paper generation method based on similarity measurement | |
CN113902131B (en) | Updating method of node model for resisting discrimination propagation in federal learning | |
CN113592144A (en) | Medium-and-long-term runoff probability forecasting method and system | |
CN114692310A (en) | Virtual-real integration-two-stage separation model parameter optimization method based on Dueling DQN | |
CN112231839A (en) | Intelligent exploration method for peak-tracking sampling of aircraft aiming at high time-consuming constraint | |
CN112397199A (en) | Big data disease prediction system based on 5G and block chain | |
CN112163671A (en) | New energy scene generation method and system | |
Zhu et al. | Splicing process inspired cuckoo search algorithm based ENNs for modeling FCCU reactor-regenerator system | |
Gai et al. | A water quality assessment method based on an improved grey relational analysis and particle swarm optimization multi-classification support vector machine | |
CN111210347A (en) | Transaction risk early warning method, device, equipment and storage medium | |
CN111178110B (en) | Bar code anomaly detection method based on artificial intelligence | |
CN109507989A (en) | A kind of method of unmanned plane sensor fault diagnosis | |
Lu et al. | Multi-objective optimization for improving machining benefit based on WOA-BBPN and a Deep Double Q-Network | |
Qin et al. | The balanced loss curriculum learning | |
CN111079995A (en) | Power load nonlinear harmonic comprehensive prediction method, device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160504 |