Unlock instant, AI-driven research and patent intelligence for your innovation.

Memory, biochemical oxygen demand soft measurement method, system and device

A biochemical oxygen demand and soft-sensing technology, applied in neural learning methods, design optimization/simulation, biological neural network models, etc., can solve the problems of prone to deviation, unstable measurement result accuracy, and inability of prediction models to adapt to application scenarios, etc. problem, to achieve the effect of improving accuracy and stability

Pending Publication Date: 2021-11-19
CHINA PETROLEUM & CHEM CORP +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] After research, the inventor found that the measurement model for BOD soft measurement constructed according to the prior art, in actual application, its prediction model cannot adapt to the application scenario where the working conditions change, and the generated measurement results Accuracy is not stable enough, prone to deviation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Memory, biochemical oxygen demand soft measurement method, system and device
  • Memory, biochemical oxygen demand soft measurement method, system and device
  • Memory, biochemical oxygen demand soft measurement method, system and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] In order to make the measurement model of biochemical oxygen demand soft measurement in practical application, the measurement results generated by it are more accurate and stable, such as figure 1 As shown, a biochemical oxygen demand soft-sensing method is provided in the embodiment of the present invention. When establishing the biochemical oxygen demand BOD soft-sensing model based on the RBF neural network, the initial neural network of the hidden layer is determined during each PCA calculation. Number of elements, including steps:

[0076] S11. Obtain the input layer variables corresponding to the BOD soft sensor model during each PCA calculation;

[0077] The application scenario of the embodiment of the present invention is to realize the real-time prediction of the biochemical oxygen demand by establishing the biochemical oxygen demand BOD soft sensor model based on the RBF neural network.

[0078] The inventor found through research that the prediction model ...

Embodiment 2

[0122] On the basis of Embodiment 1, the specific manner of training and learning of the BOD soft sensor model in the embodiment of the present invention may include:

[0123] RBF neural network error e after the tth PCA calculation t (k) expression is:

[0124]

[0125] where, where, q is the number of neurons in the input layer, y td (k) is the expected output of the RBF neural network at time k after the t-th PCA calculation, y t (k) is the actual output of the RBF neural network at time k after the tth PCA calculation;

[0126] Using the gradient descent algorithm to train and learn the BOD soft sensor model, set e d is the ideal error, when e t (k)d , stop the adjustment.

[0127] Under the condition of working condition 1 and working condition 2, the test data of variable input BOD soft sensor model based on adaptive RBF neural network are shown in Table 2 and Table 3 respectively;

[0128] Table 2:

[0129]

[0130]

[0131] table 3:

[0132]

[0133...

Embodiment 3

[0136] On the other side of the embodiment of the present invention, a biochemical oxygen demand soft measuring device is also provided, Figure 4 It shows a schematic structural diagram of the biochemical oxygen demand soft measurement device provided by the embodiment of the present invention, and the biochemical oxygen demand soft measurement device is compatible with Figure 1 to Figure 3 The device corresponding to the biochemical oxygen demand soft-sensing method described in the corresponding embodiment, that is, realized by means of a virtual device Figure 1 to Figure 3 In the biochemical oxygen demand soft measurement method in any corresponding embodiment, each virtual module constituting the biochemical oxygen demand soft measurement device may be executed by electronic equipment, such as network equipment, terminal equipment, or server. Specifically, the biochemical oxygen demand soft measuring device in the embodiment of the present invention includes:

[0137] ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a memory and a biochemical oxygen demand soft measurement method, system and device, and the method comprises the steps of determining the number of initial neurons of a hidden layer during each PCA calculation when a biochemical oxygen demand BOD soft measurement model is established, and comprises the steps of obtaining an input layer variable corresponding to the BOD soft measurement model during each PCA calculation; determining the number of hidden layer neurons corresponding to the minimum error value after prediction calculation of the BOD soft measurement model during last PCA calculation as the number of reference hidden layer neurons; and determining the number of initial neurons of the hidden layer calculated by the PCA according to a comparison result of the number of variables of the input layer calculated by the PCA and the number of variables of the input layer calculated by the previous PCA by taking the number of neurons of the reference hidden layer as a reference. According to the invention, the measurement result generated by the prediction model of the biochemical oxygen demand is more accurate and stable in the application scene of actual working condition change.

Description

technical field [0001] The invention relates to the field of sewage treatment, in particular to a memory, a biochemical oxygen demand soft measurement method, system and device. Background technique [0002] Biochemical Oxygen Demand (BOD) is an important water quality indicator and an important monitoring indicator in the process of sewage treatment. [0003] The level of BOD can reflect the degree to which organic matter in water can be degraded by microbial biochemical action. Therefore, real-time monitoring of BOD is an important means for sewage treatment. [0004] In the prior art, the prediction model used for BOD soft measurement is generally aimed at the problem that the number of input variables is constant under stable working conditions, and then adjusts the prediction model in real time according to the computing power of each neuron, and then can The current value of biochemical oxygen demand is estimated by the measurement model. [0005] After research, the...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F30/27G06F17/16G06N3/04G06N3/08G06F111/10
CPCG06F30/27G06F17/16G06N3/08G06F2111/10G06N3/045
Inventor 卢薇隋立华郭亚逢唐晓丽宋项宁姚猛
Owner CHINA PETROLEUM & CHEM CORP