Power supply management system of industrial park

By using the radial-based neural network model to intelligently predict the power consumption of power equipment in the power supply management system of industrial parks, the problem of lack of intelligent analysis capabilities in the existing technology is solved, and reliable prediction and management of future power consumption is achieved. , improves the accuracy and stability of power supply management.

CN118940967AInactive Publication Date: 2024-11-12ZHENJIANG ZERO POINT REFRIGERATION EQUIP MFG CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411141932.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing technology lacks intelligent solutions to intelligently analyze the power consumption of various power equipment in the future time segments of industrial parks, making it difficult to provide reliable power management and linkage processing information.

Method used

A power supply management system for industrial parks was designed, and the radial-based neural network model was used to intelligently predict the power consumption in the next time period based on the current configuration parameters and the power consumption data of the power consumption equipment, and the power consumption of the power consumption in the next time period was analyzed through the target analysis device. The parameter input device, data extraction device and power consumption analysis mechanism perform data input and prediction, and the linkage processing mechanism sends signals of sufficient or insufficient power.

Benefits of technology

It realizes intelligent prediction of the power consumption of electricity in the next time period of the industrial park electricity equipment, provides reliable power management information, improves the power supply management level, and improves the prediction results through customization of radial-based neural network models with different structures. effectiveness and stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940967A_ABST
    Figure CN118940967A_ABST
Patent Text Reader

Abstract

The invention relates to a power supply management system for an industrial park, and the system comprises a power utilization analysis mechanism. The analysis module is used for intelligently analyzing each part of electric energy value consumed by each piece of electric equipment in the next time segment of the current moment based on multiple configuration parameters of the current industrial park and each part of electric energy value consumed by each piece of electric equipment in the previous time segment of the current moment by adopting a radial basis function neural network model; and the linkage processing mechanism is used for determining whether to wirelessly send an insufficient electric energy signal to a far-end power supply management server based on the intelligent analysis result. The power supply management system for the industrial park is intelligent in design and simple to operate. As the radial basis function neural network model designed in a targeted manner can be adopted to intelligently predict the electric energy value of each part consumed by each electric device in the current industrial park in the next time segment of the current moment, the power supply management level of the current industrial park is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of power supply management, and in particular to a power supply management system for an industrial park. Background Art

[0002] In the field of mathematical modeling, the radial basis function network (RBFnetwork) is an artificial neural network that uses radial basis functions as activation functions. The output of the radial basis function network is a linear combination of the input radial basis functions and neuron parameters. The generalized regression neural network is an improvement based on the radial basis function network. The generalized regression neural network can also be designed using radial basis neurons and linear neurons. The generalized regression neural network is a radial basis function network based on mathematical statistics, and its theoretical basis is nonlinear regression analysis. GRNN has strong nonlinear mapping capabilities and learning speed, and has stronger advantages than RBF. The network finally converges to the optimal regression with more sample size aggregation. When the sample data is small, the prediction effect is very good, and the network can also handle unstable data. Generally, a generalized regression neural network can be established using radial basis neurons and linear neurons.

[0003] As an important type of neural network, generalized regression neural network can be widely used in various application fields through data modeling. For example, in the intelligent analysis of the numerical values ​​of electric energy consumed by various electrical equipment in the current industrial park in future time segments, it is obvious that there is a lack of corresponding intelligent solutions in the existing technology, and it is necessary to carry out data modeling and field combination of generalized regression neural network to complete the above intelligent analysis. Summary of the invention

[0004] In order to solve the technical problems in the prior art, the present invention provides a power supply management system for an industrial park, which can use a specifically designed radial basis function neural network model to intelligently predict the values ​​of electric energy consumed by each electric equipment in the current industrial park in the next time segment at the current moment based on multiple configuration parameters of the current industrial park and the values ​​of electric energy consumed by each electric equipment in the current industrial park in the previous time segment at the current moment, thereby providing reliable information for the electric energy management and linkage processing of future time segments of the current industrial park.

[0005] According to the present invention, a power supply management system for an industrial park is provided, the system comprising: A target parsing device is used to parse a radial basis neural network model, in which the radial basis neural network is trained for each time to obtain a radial basis neural network after each training and used as the radial basis neural network model; The parameter input device is used to input the respective fixed power shares corresponding to the respective power-consuming equipment in the current industrial park, the number of power-consuming equipment in the current industrial park, and the distribution area of ​​the park, and output the respective fixed power shares corresponding to the respective power-consuming equipment in the current industrial park, the number of power-consuming equipment in the current industrial park, and the distribution area of ​​the park as multiple configuration parameters of the current industrial park; A data extraction device is used to extract the values ​​of the electric energy consumed by each electric device in the current industrial park in the previous time segment of the current moment, wherein the previous time segment of the current moment and the next time segment of the current moment are adjacent on the time axis and the duration of the two is a preset time length; The power consumption analysis mechanism is connected to the target analysis device, the parameter input device and the data extraction device respectively, and is used to input the preset time length, multiple configuration parameters of the current industrial park and the respective electric energy values ​​consumed by the various electric equipments in the current industrial park in the previous time segment at the current moment in parallel into the radial basis neural network model, and run the radial basis neural network model to obtain the respective electric energy values ​​consumed by the various electric equipments in the current industrial park in the next time segment at the current moment output by the radial basis neural network model; A linkage processing mechanism, connected to the power consumption analysis mechanism, is used to accumulate the respective electric energy values ​​consumed by the various electric equipment in the current industrial park in the next time segment at the current moment to obtain a reference total power consumption, and when the reference total power consumption is greater than the electric energy value pre-reserved for the next time segment at the current moment of the current industrial park, wirelessly send a power shortage signal to a remote power supply management server; The target parsing device is used to parse a radial basis neural network model, in which the radial basis neural network is trained for each time to obtain a radial basis neural network after each training and as the radial basis neural network model, including: the number of times the radial basis neural network is trained is proportional to the number of electrical equipment in the current industrial park; The linkage processing mechanism is also used to wirelessly send a sufficient power signal to a remote power supply management server when the reference total power consumption is less than or equal to the power value pre-reserved for the next time segment at the current moment of the current industrial park.

[0006] Therefore, the present invention has the following three outstanding technical effects: First: Based on multiple configuration parameters of the current industrial park and the power values ​​consumed by each power-consuming equipment in the current industrial park in the previous time segment at the current moment, the power values ​​consumed by each power-consuming equipment in the current industrial park in the next time segment at the current moment are intelligently predicted, thereby providing reliable information for power management and linkage processing of future time segments of the current industrial park; Second: To ensure the effectiveness and stability of the intelligent prediction results, the corresponding power of each power-consuming equipment in the current industrial park, the number of power-consuming equipment in the current industrial park, the distribution area of ​​the park, and the power values ​​consumed by each power-consuming equipment in the current industrial park in the previous time segment at the current moment are introduced as the basic data for intelligent prediction; Third: using the target parsing device to parse the radial basis neural network model, in which the radial basis neural network is trained multiple times to obtain the radial basis neural network after each training and used as the radial basis neural network model, the number of radial basis neural network training is proportional to the number of electrical equipment in the current industrial park, thereby customizing radial basis neural network models with different structures for intelligent prediction for different industrial parks, further ensuring the effectiveness and stability of the intelligent prediction results.

[0007] The power supply management system of the industrial park of the present invention is intelligently designed and easy to operate. Since a targeted radial basis function neural network model can be used to intelligently predict the power consumption values ​​of each power-consuming device in the current industrial park in the next time segment at the current moment, the power supply management level of the current industrial park is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0009] Figure 1 The figure is a structural block diagram of a power supply management system for an industrial park according to the first embodiment of the present invention.

[0010] Figure 2 The figure is a structural block diagram of a power supply management system for an industrial park according to the second embodiment of the present invention.

[0011] Figure 3 It is a structural block diagram of a power supply management system for an industrial park according to Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0012] The embodiment of the power supply management system for an industrial park of the present invention will be described in detail below with reference to the accompanying drawings.

[0013] Figure 1 The structure block diagram of the power supply management system of the industrial park according to the first embodiment of the present invention is shown, and the system includes: A target parsing device is used to parse a radial basis neural network model, in which the radial basis neural network is trained for each time to obtain a radial basis neural network after each training and used as the radial basis neural network model; Specifically, an ASIC device may be selected to implement the target parsing device for parsing a radial basis neural network model, in which the radial basis neural network is trained for each time to obtain a radial basis neural network after each training and used as the radial basis neural network model; The parameter input device is used to input the respective fixed power shares corresponding to the respective power-consuming equipment in the current industrial park, the number of power-consuming equipment in the current industrial park, and the distribution area of ​​the park, and output the respective fixed power shares corresponding to the respective power-consuming equipment in the current industrial park, the number of power-consuming equipment in the current industrial park, and the distribution area of ​​the park as multiple configuration parameters of the current industrial park; A data extraction device is used to extract the values ​​of the electric energy consumed by each electric device in the current industrial park in the previous time segment of the current moment, wherein the previous time segment of the current moment and the next time segment of the current moment are adjacent on the time axis and the duration of the two is a preset time length; The power consumption analysis mechanism is connected to the target analysis device, the parameter input device and the data extraction device respectively, and is used to input the preset time length, multiple configuration parameters of the current industrial park and the respective electric energy values ​​consumed by the various electric equipments in the current industrial park in the previous time segment at the current moment in parallel into the radial basis neural network model, and run the radial basis neural network model to obtain the respective electric energy values ​​consumed by the various electric equipments in the current industrial park in the next time segment at the current moment output by the radial basis neural network model; A linkage processing mechanism, connected to the power consumption analysis mechanism, is used to accumulate the respective electric energy values ​​consumed by the various electric equipment in the current industrial park in the next time segment at the current moment to obtain a reference total power consumption, and when the reference total power consumption is greater than the electric energy value pre-reserved for the next time segment at the current moment of the current industrial park, wirelessly send a power shortage signal to a remote power supply management server; The target parsing device is used to parse a radial basis neural network model, in which the radial basis neural network is trained for each time to obtain a radial basis neural network after each training and as the radial basis neural network model, including: the number of times the radial basis neural network is trained is proportional to the number of electrical equipment in the current industrial park; The linkage processing mechanism is further used to wirelessly send a sufficient power signal to a remote power supply management server when the reference total power consumption is less than or equal to the power value pre-reserved for the next time segment at the current time of the current industrial park; And wherein, the preset time length, multiple configuration parameters of the current industrial park, and the respective electric energy values ​​consumed by each electrical equipment in the current industrial park in the previous time segment at the current moment are input in parallel into the radial basis neural network model, and the radial basis neural network model is run to obtain the radial basis neural network model output of the respective electric energy values ​​consumed by each electrical equipment in the current industrial park in the next time segment at the current moment, including: performing hexadecimal value conversion on the preset time length, multiple configuration parameters of the current industrial park, and the respective electric energy values ​​consumed by each electrical equipment in the current industrial park in the previous time segment at the current moment, and then inputting them in parallel into the radial basis neural network model.

[0014] Figure 2 The figure is a structural block diagram of a power supply management system for an industrial park according to the second embodiment of the present invention.

[0015] Compared to Figure 1 , Figure 2 The power supply management system of the industrial park in the can also include: A current sensor device is connected to the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, respectively, and is used to measure the current real-time current values ​​of the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device respectively; Wherein, the current sensor device is respectively connected with the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, and is used to respectively measure the current real-time current values ​​of the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, including: the current sensor device includes a plurality of current measurement units, which are respectively connected with the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, so as to complete the measurement of the current real-time current values ​​of the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device; Wherein, the current sensor device includes a plurality of current measurement units, which are used to be respectively connected to the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device to complete the respective measurement of the current real-time current values ​​of the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, including: the plurality of current measurement units are a plurality of current sensing circuits, which are used to be respectively connected to the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device to complete the respective measurement of the current real-time current values ​​of the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device; Wherein, the multiple current measurement units are multiple current sensing circuits, which are used to be connected to the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device respectively, so as to complete the measurement of the current real-time current values ​​of the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device respectively, including: the structures of the multiple current sensing circuits are the same; And wherein, the multiple current measurement units are multiple current sensing circuits, which are used to be connected to the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device respectively, so as to complete the respective measurements of the current real-time current values ​​of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, and also include: the multiple current sensing circuits have the same current measurement upper limit value and current measurement lower limit value.

[0016] Figure 3 It is a structural block diagram of a power supply management system for an industrial park according to Embodiment 3 of the present invention.

[0017] Compared to Figure 1 , Figure 3 The power supply management system of the industrial park in the can also include: A real-time display component, connected to the multiple current sensing circuits of the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, respectively, for real-time display of the current real-time current values ​​of the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device; Wherein, the real-time display component is respectively connected to the multiple current sensing circuits of the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, and is used to display the current real-time current values ​​of the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device in real time, including: the real-time display component is an LED display array composed of multiple LED display units; And wherein, the real-time display component is respectively connected to multiple current sensing circuits of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, and is used to display the current real-time current values ​​of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device in real time, including: the real-time display component is an LCD display array composed of multiple LCD display units.

[0018] In addition, in the power supply management system of the industrial park, the preset time length, multiple configuration parameters of the current industrial park, and the respective electric energy values ​​consumed by each electrical equipment in the current industrial park in the previous time segment at the current moment are input into the radial basis function neural network model in parallel, and the radial basis function neural network model is run to obtain the respective electric energy values ​​consumed by each electrical equipment in the current industrial park in the next time segment at the current moment output by the radial basis function neural network model, which also includes: the respective electric energy values ​​consumed by each electrical equipment in the current industrial park in the next time segment at the current moment output by the radial basis function neural network model are in a hexadecimal numerical representation mode.

[0019] Finally, the above embodiments are described for ease of understanding of the present invention, and the present invention is not limited to the above embodiments. On the contrary, the present invention is intended to cover various modifications and equivalent structures included within the scope of the appended claims, and the scope of the claims is consistent with the broadest interpretation to include all such modifications and equivalent structures allowed by law.

Claims

1. A power supply management system for an industrial park, characterized in that: The system comprises: A target parsing device is used to parse a radial basis neural network model, in which the radial basis neural network is trained for each time to obtain a radial basis neural network after each training and used as the radial basis neural network model; The parameter input device is used to input the respective fixed power shares corresponding to the respective power-consuming equipment in the current industrial park, the number of power-consuming equipment in the current industrial park, and the distribution area of ​​the park, and output the respective fixed power shares corresponding to the respective power-consuming equipment in the current industrial park, the number of power-consuming equipment in the current industrial park, and the distribution area of ​​the park as multiple configuration parameters of the current industrial park; A data extraction device is used to extract the values ​​of the electric energy consumed by each electric device in the current industrial park in the previous time segment of the current moment, wherein the previous time segment of the current moment and the next time segment of the current moment are adjacent on the time axis and the duration of the two is a preset time length; The power consumption analysis mechanism is connected to the target analysis device, the parameter input device and the data extraction device respectively, and is used to input the preset time length, multiple configuration parameters of the current industrial park and the respective electric energy values ​​consumed by the various electric equipments in the current industrial park in the previous time segment at the current moment in parallel into the radial basis neural network model, and run the radial basis neural network model to obtain the respective electric energy values ​​consumed by the various electric equipments in the current industrial park in the next time segment at the current moment output by the radial basis neural network model; A linkage processing mechanism, connected to the power consumption analysis mechanism, is used to accumulate the respective electric energy values ​​consumed by the various electric equipment in the current industrial park in the next time segment at the current moment to obtain a reference total power consumption, and when the reference total power consumption is greater than the electric energy value pre-reserved for the next time segment at the current moment of the current industrial park, wirelessly send a power shortage signal to a remote power supply management server; The target parsing device is used to parse a radial basis neural network model, in which the radial basis neural network is trained for each time to obtain a radial basis neural network after each training and as the radial basis neural network model, including: the number of times the radial basis neural network is trained is proportional to the number of electrical equipment in the current industrial park; The linkage processing mechanism is also used to wirelessly send a sufficient power signal to a remote power supply management server when the reference total power consumption is less than or equal to the power value pre-reserved for the next time segment at the current moment of the current industrial park.

2. The power supply management system for an industrial park as claimed in claim 1, characterized in that: The preset time length, multiple configuration parameters of the current industrial park, and the respective electric energy values ​​consumed by each electrical equipment in the current industrial park in the previous time segment at the current moment are input in parallel into the radial basis neural network model, and the radial basis neural network model is run to obtain the radial basis neural network model output, which includes: performing hexadecimal value conversion on the preset time length, multiple configuration parameters of the current industrial park, and the respective electric energy values ​​consumed by each electrical equipment in the current industrial park in the previous time segment at the current moment, and then inputting them in parallel into the radial basis neural network model.

3. The power supply management system for an industrial park as claimed in claim 2, characterized in that: The system further comprises: A current sensor device is connected to the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, respectively, and is used to measure the current real-time current values ​​of the power analysis mechanism, the target analysis device, the parameter entry device and the data extraction device respectively; Among them, the current sensor device is respectively connected to the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, and is used to respectively measure the current real-time current values ​​of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device. The current sensor device includes multiple current measurement units, which are used to be respectively connected to the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device to complete the measurement of the current real-time current values ​​of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device.

4. The power supply management system for an industrial park as claimed in claim 3, characterized in that: The current sensor device includes a plurality of current measuring units, which are used to be respectively connected to the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device to complete the respective measurement of the current real-time current values ​​of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device. The plurality of current measuring units are a plurality of current sensing circuits, which are used to be respectively connected to the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device to complete the respective measurement of the current real-time current values ​​of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device.

5. The power supply management system for an industrial park as claimed in claim 4, characterized in that: The multiple current measurement units are multiple current sensing circuits, which are used to be connected to the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device respectively, so as to complete the respective measurements of the current real-time current values ​​of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, including: the structures of the multiple current sensing circuits are the same.

6. The power supply management system for an industrial park as claimed in claim 5, characterized in that: The multiple current measurement units are multiple current sensing circuits, which are used to be connected to the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device respectively, so as to complete the respective measurements of the current real-time current values ​​of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device. It also includes: the multiple current sensing circuits have the same current measurement upper limit value and current measurement lower limit value.

7. The power supply management system for an industrial park as claimed in claim 2, characterized in that: The system further comprises: A real-time display component is respectively connected to multiple current sensing circuits of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, and is used to display the current real-time current values ​​of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device in real time.

8. The power supply management system for an industrial park as claimed in claim 7, characterized in that: A real-time display component is respectively connected to multiple current sensing circuits of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, and is used to display the current real-time current values ​​of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device in real time. The real-time display component includes an LED display array composed of multiple LED display units.

9. The power supply management system for an industrial park as claimed in claim 7, characterized in that: A real-time display component is respectively connected to multiple current sensing circuits of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device, and is used to display the current real-time current values ​​of the power consumption analysis mechanism, the target analysis device, the parameter entry device and the data extraction device in real time. The real-time display component includes an LCD display array composed of multiple LCD display units.

Citation Information

Patent Citations

  • Monitoring system and method based on big data

    CN116799966A

  • Artificial intelligence multistage cooperation system and method for power industry

    CN117039888A

  • Power supply grid electric energy data dynamic allocation system

    CN117996743A

  • Power station energy storage dynamic distribution system applying artificial intelligence

    CN118100158A

  • Method and system for generating an energy consumption forecast for a vehicle

    DE102022119448A1