CN114626635A - Steel logistics cost prediction method and system based on hybrid neural network - Google Patents
Steel logistics cost prediction method and system based on hybrid neural network Download PDFInfo
- Publication number
- CN114626635A CN114626635A CN202210349735.XA CN202210349735A CN114626635A CN 114626635 A CN114626635 A CN 114626635A CN 202210349735 A CN202210349735 A CN 202210349735A CN 114626635 A CN114626635 A CN 114626635A
- Authority
- CN
- China
- Prior art keywords
- neural network
- logistics cost
- hybrid neural
- data
- steel
- 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
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 129
- 239000010959 steel Substances 0.000 title claims abstract description 129
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000005457 optimization Methods 0.000 claims abstract description 28
- 239000011159 matrix material Substances 0.000 claims description 57
- 238000012549 training Methods 0.000 claims description 54
- 238000012545 processing Methods 0.000 claims description 33
- 238000012360 testing method Methods 0.000 claims description 27
- 238000007781 pre-processing Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 4
- 229910052742 iron Inorganic materials 0.000 claims description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method and a system for predicting steel logistics cost based on a hybrid neural network, wherein the method comprises the steps of obtaining steel logistics cost data to be tested; inputting the steel logistics cost data to be measured into a trained prediction model to obtain the predicted steel logistics cost; wherein the predictive model is a trained and optimized hybrid neural network. The method improves the randomness in the traditional logistics cost prediction method, improves the accuracy degree of the prediction result by using the hybrid neural network, simultaneously optimizes the problems of local optimization and excessive iteration times in the traditional hybrid neural network, and has high prediction accuracy and high feasibility.
Description
Technical Field
The invention relates to the technical field of logistics information, in particular to a method and a system for predicting steel logistics cost based on a hybrid neural network.
Background
With the economic development, the logistics industry has increasingly important in various industries, and is therefore important for predicting logistics cost.
Logistics also plays an important role in the field of steel industry. However, because the traditional steel logistics cost prediction mode is usually based on experience for prediction, the complicated prediction of the influence factors such as steel logistics cost prediction is often extremely inaccurate, and a plurality of defects exist, so that the logistics cost prediction and accounting of the steel enterprises are difficult, and the economic development of the steel enterprises and the progress of the steel logistics management level are not facilitated.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a method and a system for predicting the logistics cost of steel based on a hybrid neural network.
In order to achieve the purpose, the invention provides the following scheme:
a method for predicting steel logistics cost based on a hybrid neural network comprises the following steps:
acquiring steel logistics cost data to be detected;
inputting the steel logistics cost data to be measured into a trained prediction model to obtain the predicted steel logistics cost;
the determination method of the prediction model comprises the following steps:
acquiring trained steel logistics cost data;
preprocessing the trained steel logistics cost data to obtain a training set and a testing set;
initializing a preset hybrid neural network, and training the initialized hybrid neural network according to the training set to obtain a trained hybrid neural network;
and performing parameter iteration on the trained hybrid neural network based on a global optimal optimization method to obtain the trained prediction model.
Preferably, the method further comprises the following steps:
and performing model test on the trained prediction model according to the test set.
Preferably, the expression of the trained steel logistics cost data is S ═ { x ═ x1，x2，...，xnY, wherein S is a historical data set of the trained steel logistics cost data, xnAnd y is the cost value of the steel logistics as the nth influencing factor.
Preferably, the influence factors include a departure starting point of the vehicle, a transportation destination of the vehicle, a type of the vehicle, a transportation day weather, road conditions, a kind of goods, and a weight of the goods.
Preferably, the preprocessing the trained steel logistics cost data to obtain a training set and a testing set includes:
performing matrixing processing on the historical data set to obtain a first data matrix and a second data matrix; the expression of the first data matrix is X ═ Xij]m×nThe expression of the second data matrix is Y ═ Yi]m×1(ii) a Wherein X is the first data matrix, XijThe jth influence factor in the ith historical data set is obtained; y isiThe logistics cost value in the ith historical data set is used as the logistics cost value; n is the number of the influencing factors; m is the total number of the steel logistics cost data;
respectively carrying out normalization processing on the first data matrix and the second data matrix to obtain first normalized data and second normalized data; the expression of the first normalized data is x*＝2×
The expression of the second normalized data is
Wherein x ismaxIs composed ofMaximum value of the above-mentioned influencing factor, xminIs the minimum value of the influencing factor; y ismaxIs the maximum value of said logistic cost value; y isminIs the minimum of said logistic cost values;
performing matrixing expression on the first normalized data and the second normalized data respectively to obtain a first processing matrix and a second processing matrix; the expression of the first processing matrix is
The expression of the second processing matrix is
Wherein, X*For the purpose of the first processing matrix,
normalized value of j influence factor in ith historical data set, Y*For the purpose of said second processing matrix,
normalized values for logistics cost values in the ith said historical data set;
determining the training set and the test set according to the first processing matrix and the second processing matrix.
Preferably, the initializing a preset hybrid neural network and training the initialized hybrid neural network according to the training set to obtain a trained hybrid neural network includes:
acquiring the preset hybrid neural network; the hybrid neural network comprises an input layer, a hidden layer and an output layer which are sequentially connected; the number of input nodes of the input layer is equal to the number of influencing factors;
determining the number of nodes of the hidden layer according to the number of the influence factors; the formula of the number of nodes of the hidden layer is as follows:
wherein n is*A is a preset empirical value, and is the number of nodes of the hidden layer;
determining the number of nodes of the output layer according to the second processing matrix;
initializing hybrid neural network parameters of the hybrid neural network; the parameters of the hybrid neural network comprise the learning rate, the minimum error of a training target, the maximum iteration times, the node weight, the node bias, an activation function and an output function of the hybrid neural network;
and training the hybrid neural network after initializing the parameters of the hybrid neural network according to the training set to obtain the trained hybrid neural network.
Preferably, the performing parameter iteration on the trained hybrid neural network by the global optimal optimization method to obtain the trained prediction model includes:
determining a loss value between a predicted value and an accurate value of the steel logistics cost; the loss value is calculated by the formula of (y ═ C)*-y)2(ii) a Wherein C is the loss value, y*Predicting the cost of the steel logistics;
during the training process, when the hybrid neural network reaches a new steel logistics cost loss CtThen, to CtCarrying out random disturbance to obtain new steel logistics cost loss Ct+1Selecting whether to update the disturbance according to the probability P, and multiplying a preset optimization constant by a coefficient for updating; the expression of the probability is
Wherein K is the optimization constant;
and when the updated optimization constant reaches the maximum iteration times, taking a plurality of continuous steel logistics cost losses and judging whether the steel logistics cost losses are all not accepted under the probability, and if so, obtaining the trained prediction model.
Preferably, the expression of the to-be-measured steel logistics cost data is T ═ { x ═ x1，x2，...，xn}; wherein T is the set of the steel logistics cost data to be detected; x is the number ofnIs the nth influencing factor.
A steel logistics cost prediction system based on a hybrid neural network comprises:
the to-be-detected data acquisition module is used for acquiring to-be-detected steel logistics cost data;
the prediction module is used for inputting the steel logistics cost data to be measured into a trained prediction model to obtain the predicted steel logistics cost;
the model determining module specifically comprises:
the training data acquisition unit is used for acquiring the trained steel logistics cost data;
the preprocessing unit is used for preprocessing the trained steel logistics cost data to obtain a training set and a testing set;
the initialization unit is used for initializing a preset hybrid neural network and training the initialized hybrid neural network according to the training set to obtain a trained hybrid neural network;
and the optimization unit is used for carrying out parameter iteration on the trained hybrid neural network based on a global optimal optimization method to obtain the trained prediction model.
Preferably, the method further comprises the following steps:
and the testing module is used for carrying out model testing on the trained prediction model according to the test set.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a method and a system for predicting steel logistics cost based on a hybrid neural network, which improve randomness existing in the traditional logistics cost prediction method, improve the accuracy degree of a prediction result by using the hybrid neural network, simultaneously optimize the problems of local optimization and excessive iteration times existing in the traditional hybrid neural network, and have high prediction accuracy and high implementability.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required 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 that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a prediction method in an embodiment provided by the present invention;
FIG. 2 is a schematic structural diagram of a hybrid neural network in an embodiment provided by the present invention;
FIG. 3 is a flow chart of model training and prediction in an embodiment provided by the present invention;
fig. 4 is a schematic diagram of an activation function of a hybrid neural network in an embodiment provided by the present 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.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, the inclusion of a list of steps, processes, methods, etc. is not limited to only those steps recited, but may alternatively include additional steps not recited, or may alternatively include additional steps inherent to such processes, methods, articles, or devices.
The invention aims to provide a method and a system for predicting the steel logistics cost based on a hybrid neural network, which can improve the prediction precision of the steel logistics cost.
In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, the present invention is described in detail with reference to the accompanying drawings and the detailed description thereof.
Fig. 1 is a flowchart of a prediction method in an embodiment provided by the present invention, and as shown in fig. 1, the present invention provides a method for predicting steel logistics cost based on a hybrid neural network, including:
the determination method of the prediction model comprises the following steps:
step 201: acquiring trained steel logistics cost data;
step 202: preprocessing the trained steel logistics cost data to obtain a training set and a testing set;
step 203: initializing a preset hybrid neural network, and training the initialized hybrid neural network according to the training set to obtain a trained hybrid neural network;
step 204: and performing parameter iteration on the trained hybrid neural network based on a global optimal optimization method to obtain the trained prediction model.
Preferably, the method further comprises the following steps:
step 300: and performing model test on the trained prediction model according to the test set.
Preferably, the expression of the trained steel logistics cost data is S ═ { x ═ x1，x2，...，xnY, wherein S is a historical data set of the trained steel logistics cost data, xnAnd y is the cost value of the steel logistics as the nth influencing factor.
Fig. 2 is a flow chart of model training in an embodiment provided by the present invention, and as shown in fig. 2, the hybrid neural network has three layers, nodes of the first input layer are all input nodes, each node represents an input data, and the steel logistics cost data set is represented by the following set S:
S＝{x1，x2，...，xn，y}
thus, the input layer input nodes need to input x separately1，x2，...，xn。
Where n represents the total influencing factor in the set, xiAnd (3) representing the ith influence factor, satisfying that i is more than or equal to 1 and less than or equal to n, and y represents the steel logistics cost value.
Preferably, the influencing factors include a departure starting point of the vehicle, a transportation destination of the vehicle, a type of the vehicle, a transportation day weather, a road condition, a kind of goods, and a weight of the goods.
Further, the above-mentioned influencing factors influencing the cost of steel logistics refer to the starting point of the vehicle, the transportation destination of the vehicle, the type of the vehicle, the weather of the transportation day (sunny, rainy, foggy, snowy, etc.), the road conditions, the type of goods, the weight of goods, and all factors related to the cost which are verified to be available by this method.
Fig. 3 is a flowchart of model training and prediction in the embodiment provided by the present invention, and as shown in fig. 3, the training and prediction method provided by the present embodiment includes:
s1, acquiring historical related steel logistics cost data;
s2, preprocessing the steel logistics cost data;
s3, initializing a hybrid neural network, training the neural network, and finally performing parameter iteration and model optimization by adopting a global optimal optimization mode;
and S4, predicting the steel logistics cost by using the optimized hybrid neural network.
Preferably, the step 202 comprises:
performing matrixing processing on the historical data set to obtain a first data matrix and a second data matrix; the expression of the first data matrix is X ═ Xij]m×nThe expression of the second data matrix is Y ═ Yi]m×1(ii) a Wherein X is the first data matrix, XijThe jth influence factor in the ith historical data set is obtained; y isiThe logistics cost value in the ith historical data set is used as the logistics cost value; n is the number of the influencing factors; m is the total number of the steel logistics cost data;
respectively carrying out normalization processing on the first data matrix and the second data matrix to obtain first normalized data and second normalized data; the expression of the first normalized data is
The expression of the second normalized data is
Wherein x ismaxIs the maximum value of said influencing factor, xminIs the minimum value of the influencing factor; y ismaxIs the maximum value of the logistic cost values; y isminIs the minimum of said logistic cost values;
performing matrixing expression on the first normalized data and the second normalized data respectively to obtain a first processing matrix and a second processing matrix; the expression of the first processing matrix is
The expression of the second processing matrix is
Wherein, X*For the purpose of the first processing matrix,
normalized value of j influence factor in ith historical data set, Y*For the purpose of said second processing matrix,
normalized values for logistics cost values in the ith said historical data set;
determining the training set and the test set according to the first processing matrix and the second processing matrix.
Specifically, the data input in this embodiment is input in a matrix form:
X＝[xij]m×n，Y＝[yi]m×1。
wherein the element xijThe jth influencing factor in the set S in the ith historical data, element yiRepresenting logistics cost values in the ith historical data. The division of the X and Y matrixes needs to be manually cut by an implementer, and the complexity of operation and implementation can be greatly reduced by using matrix operation through vector operation.
Further, in this embodiment, before data is input, the data matrix X, Y is normalized and a training set and test set data are divided.
Normalization, with all data values between [ -1, 1], using the following formula:
wherein max and min respectively represent xiThe maximum and minimum values of the corresponding steel logistics cost influence factors and the steel logistics cost y.
The processed data uses the following matrix X*，Y*Represents:
wherein the matrix elements
Respectively represent xij，yiNormalized value
Further, the matrix data X after normalization is subjected to*，Y*Performing matrix division, and taking the first 80% as training data set
The remaining 20% was used as test set
Preferably, said step 203 comprises:
acquiring the preset hybrid neural network; the hybrid neural network comprises an input layer, a hidden layer and an output layer which are sequentially connected; the number of input nodes of the input layer is equal to the number of influencing factors;
determining the number of nodes of the hidden layer according to the number of the influence factors; the formula of the number of nodes of the hidden layer is as follows:
wherein n is*A is the number of nodes of the hidden layer and is a preset empirical value;
determining the number of nodes of the output layer according to the second processing matrix;
initializing hybrid neural network parameters of the hybrid neural network; the parameters of the hybrid neural network comprise the learning rate, the minimum error of a training target, the maximum iteration times, the node weight, the node bias, an activation function and an output function of the hybrid neural network;
and training the hybrid neural network after initializing the parameters of the hybrid neural network according to the training set to obtain the trained hybrid neural network.
Specifically, in the present embodiment, the data set is based on X*Initially setting the number of input nodes of the hybrid neural network, and setting the number of input nodes as a set S ═ x1，x2，...，xnY, the number of x in y is the number of influencing factors influencing the steel logistics cost;
further, the number of nodes of the hidden layer of the hybrid neural network is set according to the number of influencing factors influencing the steel logistics cost, and an empirical formula is set according to the nodes of the hidden layer:
n is the number of influencing factors influencing the steel logistics cost, 1 is that only 1 output node is provided, and a can be any value within 1-10;
further, according to Y in the data set*The number of output nodes of the hybrid neural network is initially set, only 1 output node can be known from the steel logistics cost data set, and the number of the output nodes is also set to be 1.
And then, continuously configuring parameters of the neural network, perfecting the neural network:
firstly, setting a learning rate, training a target minimum error and a maximum iteration number:
the learning rate alpha is manually set to be 0.01, the value cannot be set to be too large or too small, the adjustment range is too large due to too large value, and an optimal prediction iron and steel logistics cost model is not easy to obtain; too small may result in too many iterations of the adjustment process and inefficiency. And setting the minimum error beta of the training target to be 0.001.
Then manually setting the weight w of each node of an input layer- > hidden layer and the hidden layer- > output layer and bias b;
setting an activation function f (x) of a hidden layer and an output layer:
f (x) is an activation function, a non-linear function, that maps the hidden layer output and the predicted stream cost output into [ -1, 1], as shown in FIG. 4.
The hidden layer can be obtained, the output of the output layer:
wherein h isjIs the input of the hidden layer to the output layer, wij，bijRespectively, the weight and the offset between the ith input node and the jth hidden layer node.
The weights and the offsets between the ith hidden node and the output nodes are respectively, and the predicted logistics cost y can be obtained.
Still further, after the hybrid neural network is initialized, the steel logistics cost data set is input
And training, wherein the weights and the offsets among the layers are continuously adjusted by using a global optimal optimization mode according to the loss of the predicted output value and the accurate output value of the steel logistics cost during training, a hybrid neural network is optimized, the purpose of predicting the steel logistics cost most accurately is achieved, the phenomena of overfitting and local optimization are prevented, and the iteration efficiency is improved.
The global optimal optimization adjustment mode is as follows:
first a larger constant K is defined 2000,
and defining the loss C between the predicted value and the accurate value of the steel logistics cost:
C＝(y*-y)2。
wherein y is*Represents a predicted value of the cost of the steel material flow, and y represents the corresponding steel material flowThe actual value of the cost. The aim is to make C as small as possible.
Further, when the mixed neural network obtains a new steel logistics cost loss CtThen, randomly disturbing the steel to obtain new steel logistics cost loss Ct+1And selecting whether to update the perturbation according to the probability P.
Wherein C ist，Ct+1For the above-mentioned cost loss of steel logistics, K is a constant for initialization,
and updating K to K multiplied by 0.99.
The above iteration process is repeated until the maximum number of iterations is reached. And then taking a plurality of continuous steel losses C, and if all the continuous steel losses C are not accepted under the condition P, finishing the global optimal optimization adjustment.
After the mixed neural network model is adjusted, the method for predicting the steel logistics cost based on the mixed neural network is also completed. Only the data set of the influence factors of the steel logistics cost for testing needs to be input later
Performing model test, and finally performing inverse normalization on the steel logistics prediction cost matrix output by the output layer to obtain a matrix
As model predictive outcome output and
and comparing and verifying the accuracy of the model.
Preferably, the step 204 comprises:
determining a loss value between a predicted value and an accurate value of the steel logistics cost; the loss value is calculated by the formula of (y ═ C)*-y)2(ii) a Wherein C is the loss value, y*Cost prediction for the steel logisticsA value;
during the training process, when the mixed neural network reaches a new steel logistics cost loss CtThen, to CtCarrying out random disturbance to obtain new steel logistics cost loss Ct+1Selecting whether to update the current disturbance according to the probability P, and multiplying a preset optimization constant by a coefficient for updating; the expression of the probability is
Wherein K is the optimization constant;
and when the updated optimization constant reaches the maximum iteration times, taking a plurality of continuous steel logistics cost losses and judging whether the steel logistics cost losses are all not accepted under the probability, and if so, obtaining the trained prediction model.
Preferably, the expression of the to-be-measured steel logistics cost data is T ═ { x ═ x1，x2，...，xn}; wherein T is a set of the steel logistics cost data to be detected; x is the number ofnIs the nth influencing factor.
In the embodiment, if a user needs to predict the steel logistics cost in the future, the influence factors are input according to the input sequence, and the predicted steel logistics cost y output according to the requirement can be obtained. The input data is represented by the following set T:
T＝{x1，x2，...，xn}; wherein the element xiThe ith factor influencing the steel logistics cost is shown, and n influencing factors are provided in total;
the embodiment also correspondingly provides a system for predicting the logistics cost of steel based on the hybrid neural network, which comprises:
the to-be-detected data acquisition module is used for acquiring to-be-detected steel logistics cost data;
the prediction module is used for inputting the steel logistics cost data to be detected into a trained prediction model to obtain the predicted steel logistics cost;
the model determining module specifically comprises:
the training data acquisition unit is used for acquiring training steel logistics cost data;
the preprocessing unit is used for preprocessing the trained steel logistics cost data to obtain a training set and a testing set;
the initialization unit is used for initializing a preset hybrid neural network and training the initialized hybrid neural network according to the training set to obtain a trained hybrid neural network;
and the optimization unit is used for carrying out parameter iteration on the trained hybrid neural network based on a global optimal optimization method to obtain the trained prediction model.
The invention has the following beneficial effects:
the method improves the randomness existing in the traditional logistics cost prediction method, simultaneously optimizes the problems of local optimization and excessive iteration times existing in the traditional neural network, and has high prediction accuracy and high implementability.
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 method part for description.
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 above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. A method for predicting the logistics cost of steel based on a hybrid neural network is characterized by comprising the following steps:
acquiring steel logistics cost data to be detected;
inputting the steel logistics cost data to be measured into a trained prediction model to obtain the predicted steel logistics cost;
the determination method of the prediction model comprises the following steps:
acquiring trained steel logistics cost data;
preprocessing the trained steel logistics cost data to obtain a training set and a testing set;
initializing a preset hybrid neural network, and training the initialized hybrid neural network according to the training set to obtain a trained hybrid neural network;
and performing parameter iteration on the trained hybrid neural network based on a global optimal optimization method to obtain the trained prediction model.
2. The method for predicting the logistics cost of steel based on the hybrid neural network as claimed in claim 1, further comprising:
and performing model test on the trained prediction model according to the test set.
3. The hybrid neural network-based steel logistics cost prediction method of claim 1, wherein the expression of the trained steel logistics cost data is S ═ { x ═ x1，x2，…，xnY, wherein S is a historical data set of the trained steel logistics cost data, xnAnd y is the cost value of the steel logistics as the nth influencing factor.
4. The hybrid neural network-based steel logistics cost prediction method of claim 1, wherein the influence factors include a vehicle departure starting location, a vehicle transportation destination, a vehicle type, a transportation day weather, road conditions, a cargo type and a cargo weight.
5. The hybrid neural network-based steel logistics cost prediction method of claim 3, wherein the preprocessing the trained steel logistics cost data to obtain a training set and a test set comprises:
performing matrixing processing on the historical data set to obtain a first data matrix and a second data matrix; the expression of the first data matrix is X ═ Xij]m×nThe expression of the second data matrix is Y ═ Yi]m×1(ii) a Wherein X is the first data matrix, XijThe jth influence factor in the ith historical data set is obtained; y isiThe logistics cost value in the ith historical data set is used as the logistics cost value; n is the number of the influencing factors; m is the total number of the steel logistics cost data;
respectively carrying out normalization processing on the first data matrix and the second data matrix to obtain first normalized data and second normalized data; the expression of the first normalized data is
The expression of the second normalized data is
Wherein x ismaxIs the maximum value of said influencing factor, xminIs the minimum value of the influencing factor; y ismaxIs the maximum value of said logistic cost value; y isminIs the minimum of said logistic cost values;
performing matrixing expression on the first normalized data and the second normalized data respectively to obtain a first processing matrix and a second processing matrix; the expression of the first processing matrix is
The expression of the second processing matrix is
Wherein, X*For the purpose of the first processing matrix,
normalized value of j influence factor in ith historical data set, Y*For the purpose of said second processing matrix,
normalized values for logistics cost values in the ith said historical data set;
determining the training set and the test set according to the first processing matrix and the second processing matrix.
6. The method for predicting the logistics cost of steel and iron based on the hybrid neural network according to claim 5, wherein the initializing a preset hybrid neural network and training the initialized hybrid neural network according to the training set to obtain the trained hybrid neural network comprises:
acquiring the preset hybrid neural network; the hybrid neural network comprises an input layer, a hidden layer and an output layer which are sequentially connected; the number of input nodes of the input layer is equal to the number of influencing factors;
determining the number of nodes of the hidden layer according to the number of the influence factors; the formula of the number of nodes of the hidden layer is as follows:
wherein n is*A is a preset empirical value, and is the number of nodes of the hidden layer;
determining the number of nodes of the output layer according to the second processing matrix;
initializing hybrid neural network parameters of the hybrid neural network; the parameters of the hybrid neural network comprise the learning rate, the minimum error of a training target, the maximum iteration times, the node weight, the node bias, an activation function and an output function of the hybrid neural network;
and training the hybrid neural network after initializing the parameters of the hybrid neural network according to the training set to obtain the trained hybrid neural network.
7. The method for predicting the steel logistics cost based on the hybrid neural network as claimed in claim 6, wherein the method for optimizing based on the global optimum performs parameter iteration on the trained hybrid neural network to obtain the trained prediction model, and comprises the following steps:
determining a loss value between a predicted value and an accurate value of the steel logistics cost; the loss value is calculated by the formula of (y ═ C)*-y)2(ii) a Wherein C is the loss value, y*Predicting the cost of the steel logistics;
during the training process, when the mixed neural network reaches a new steel logistics cost loss CtThen, to CtCarrying out random disturbance to obtain new steel logistics cost loss Ct+1Selecting whether to update the current disturbance according to the probability P, and multiplying a preset optimization constant by a coefficient for updating; the expression of the probability is
Wherein K is the optimization constant;
and when the updated optimization constant reaches the maximum iteration number, taking a plurality of continuous steel logistics cost losses and judging whether the steel logistics cost losses are all not accepted under the probability, and if so, obtaining the trained prediction model.
8. The method according to claim 1, wherein the expression of the to-be-measured steel logistics cost data is T ═ x1，x2，…，xn}; wherein T is the set of the steel logistics cost data to be detected; x is the number ofnIs the nth influencing factor.
9. A steel logistics cost prediction system based on a hybrid neural network is characterized by comprising the following components:
the to-be-detected data acquisition module is used for acquiring to-be-detected steel logistics cost data;
the prediction module is used for inputting the steel logistics cost data to be measured into a trained prediction model to obtain the predicted steel logistics cost;
the model determining module specifically comprises:
the training data acquisition unit is used for acquiring the trained steel logistics cost data;
the preprocessing unit is used for preprocessing the trained steel logistics cost data to obtain a training set and a testing set;
the initialization unit is used for initializing a preset hybrid neural network and training the initialized hybrid neural network according to the training set to obtain a trained hybrid neural network;
and the optimization unit is used for carrying out parameter iteration on the trained hybrid neural network based on a global optimal optimization method to obtain the trained prediction model.
10. The hybrid neural network-based steel logistics cost prediction system of claim 9, further comprising:
and the testing module is used for carrying out model testing on the trained prediction model according to the testing set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210349735.XA CN114626635A (en) | 2022-04-02 | 2022-04-02 | Steel logistics cost prediction method and system based on hybrid neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210349735.XA CN114626635A (en) | 2022-04-02 | 2022-04-02 | Steel logistics cost prediction method and system based on hybrid neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114626635A true CN114626635A (en) | 2022-06-14 |
Family
ID=81905109
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210349735.XA Pending CN114626635A (en) | 2022-04-02 | 2022-04-02 | Steel logistics cost prediction method and system based on hybrid neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114626635A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6269351B1 (en) * | 1999-03-31 | 2001-07-31 | Dryken Technologies, Inc. | Method and system for training an artificial neural network |
| US20040111169A1 (en) * | 2002-12-04 | 2004-06-10 | Hong Se June | Method for ensemble predictive modeling by multiplicative adjustment of class probability: APM (adjusted probability model) |
| CN108449295A (en) * | 2018-02-05 | 2018-08-24 | 西安电子科技大学昆山创新研究院 | Combined modulation recognition methods based on RBM networks and BP neural network |
| CN109671272A (en) * | 2018-12-29 | 2019-04-23 | 广东工业大学 | A kind of freeway traffic flow prediction technique |
| CN109859469A (en) * | 2019-02-15 | 2019-06-07 | 重庆邮电大学 | A kind of vehicle flowrate prediction technique based on integrated LSTM neural network |
| CN109858127A (en) * | 2018-04-13 | 2019-06-07 | 北京工商大学 | Cyanobacterial bloom prediction technique based on recurrence sequential depth confidence network |
| CN110097185A (en) * | 2019-03-29 | 2019-08-06 | 北京大学 | A kind of Optimized model method and application based on generation confrontation network |
| CN110601777A (en) * | 2019-08-29 | 2019-12-20 | 浙江大学 | Method for estimating satellite-ground downlink co-channel interference under low-orbit mobile satellite constellation |
| WO2020177863A1 (en) * | 2019-03-06 | 2020-09-10 | Nokia Technologies Oy | Training of algorithms |
-
2022
- 2022-04-02 CN CN202210349735.XA patent/CN114626635A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6269351B1 (en) * | 1999-03-31 | 2001-07-31 | Dryken Technologies, Inc. | Method and system for training an artificial neural network |
| US20040111169A1 (en) * | 2002-12-04 | 2004-06-10 | Hong Se June | Method for ensemble predictive modeling by multiplicative adjustment of class probability: APM (adjusted probability model) |
| CN108449295A (en) * | 2018-02-05 | 2018-08-24 | 西安电子科技大学昆山创新研究院 | Combined modulation recognition methods based on RBM networks and BP neural network |
| CN109858127A (en) * | 2018-04-13 | 2019-06-07 | 北京工商大学 | Cyanobacterial bloom prediction technique based on recurrence sequential depth confidence network |
| CN109671272A (en) * | 2018-12-29 | 2019-04-23 | 广东工业大学 | A kind of freeway traffic flow prediction technique |
| CN109859469A (en) * | 2019-02-15 | 2019-06-07 | 重庆邮电大学 | A kind of vehicle flowrate prediction technique based on integrated LSTM neural network |
| WO2020177863A1 (en) * | 2019-03-06 | 2020-09-10 | Nokia Technologies Oy | Training of algorithms |
| CN110097185A (en) * | 2019-03-29 | 2019-08-06 | 北京大学 | A kind of Optimized model method and application based on generation confrontation network |
| CN110601777A (en) * | 2019-08-29 | 2019-12-20 | 浙江大学 | Method for estimating satellite-ground downlink co-channel interference under low-orbit mobile satellite constellation |
Non-Patent Citations (3)
| Title |
|---|
| YYYA77: "模拟退火算法（SA）原理与python实例", HTTPS://BLOG.CSDN.NET/A999999123/ARTICLE/DETAILS/109500746, 5 November 2020 (2020-11-05), pages 1 - 2 * |
| 大写的FENG: "数据预处理：归一化和标准化", HTTPS://ZHUANLAN.ZHIHU.COM/P/296252799, 16 November 2020 (2020-11-16), pages 1 - 2 * |
| 马威, 张国平, 王正欧: "一种基于参数扰动退火策略的神经网络全局优化新算法", 系统工程理论方法应用, no. 04, 25 December 2002 (2002-12-25), pages 314 - 318 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106874581B (en) | Building air conditioner energy consumption prediction method based on BP neural network model | |
| US10331810B2 (en) | Method for determining a model of an output quantity of a technical system | |
| CN108920863B (en) | Method for establishing energy consumption estimation model of robot servo system | |
| CN104217258B (en) | A kind of electric load sigma-t Forecasting Methodology | |
| CN113408715B (en) | Method and device for fixing neural network | |
| CN109242265B (en) | Urban water demand combined prediction method based on least square sum of errors | |
| CN109143408B (en) | Dynamic region combined short-time rainfall forecasting method based on MLP | |
| CN110263429B (en) | Method for adjusting shape and surface precision of cable net reflecting surface antenna based on machine learning | |
| CN112990587B (en) | Method, system, equipment and medium for accurately predicting power consumption of transformer area | |
| CN110543978A (en) | Traffic flow data prediction method and device based on wavelet neural network | |
| CN110766190A (en) | Power distribution network load prediction method | |
| CN111898867A (en) | Airplane final assembly production line productivity prediction method based on deep neural network | |
| CN111401642A (en) | Method, device and equipment for automatically adjusting predicted value and storage medium | |
| CN115906399A (en) | Improved method for predicting key process quality of product under small sample data | |
| CN114564787A (en) | Bayesian optimization method, device and storage medium for target-related airfoil design | |
| CN113570007A (en) | Method, device and equipment for optimizing construction of part defect identification model and storage medium | |
| CN114037139A (en) | Freight vehicle warehouse stay time length prediction method based on attention mechanism | |
| CN111461329B (en) | Model training method, device, equipment and readable storage medium | |
| CN106067075B (en) | Building energy load prediction model building and load prediction method and device | |
| CN114626635A (en) | Steel logistics cost prediction method and system based on hybrid neural network | |
| CN115794805B (en) | Method for supplementing measurement data of medium-low voltage distribution network | |
| CN114861739B (en) | Characteristic channel selectable multi-component system degradation prediction method and system | |
| CN111507499A (en) | Construction method, test method, device and system of model for prediction | |
| CN112529328B (en) | Product performance prediction method and system | |
| JP3056324B2 (en) | Learning / recalling method and device |
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 |