Implementation method of cold chain storage intelligent energy-saving platform based on pyside2 and MySQL

Abstract

The invention provides an implementation method of a cold chain storage intelligent energy-saving platform based on PySide2 and MySQL, and the method comprises the following steps: S1, data collection and storage: collecting data through a Modbus protocol, a unit main control board, a temperature and humidity sensor and an electric energy collection module, transmitting the data to an Ali cloud Internet of Things platform, and storing the data to an Ali cloud RDS MySQL database; s2, designing a platform interface, planning an interface layout by using a QT component, and realizing UI display by using PySide2; s3, a prediction model is constructed, based on LSTM and CNN neural network models, a database is remotely connected through SQL statements, data are read, future feature prediction is carried out, and intelligent execution is carried out in combination with a defrosting decision; and S4, a face recognition function: realizing user face recognition by embedding a YOLOv8n model, and storing new user data. The platform automatically manages cold chain storage data, improves the management efficiency, reduces the labor cost, predicts future data through the neural network, improves the decision accuracy, reduces the risk and cost, and achieves the energy-saving optimization effect.

Description

Technical Field

[0001] The present invention belongs to the field of computer front-end development. It mainly aims at establishing an intelligent energy-saving platform for the energy consumption problem of cold chain warehousing. In order to simplify the manual management of cold chain warehousing data and save cold chain warehousing energy consumption, pyside2 and MySQL are used to design an implementation method of the cold chain warehousing intelligent energy-saving platform. The neural network model is used to predict the characteristic data of a period of time in the future, and the defrost decision is set to achieve intelligent energy saving. Background Art

[0002] Energy issues have become one of the most concerned issues in the world, and electricity consumption is an important cause of energy problems, so saving electricity is of great significance. Cold chain warehousing is an application scenario with high electricity consumption, but in reality there are various serious electricity waste phenomena due to various reasons. Therefore, by building a cold chain warehousing intelligent energy-saving platform and implementing intelligent energy-saving measures, energy saving in cold chain warehousing scenarios has become more important. Summary of the invention

[0003] The technical problem to be solved by the present invention is to simplify the manual management of cold chain warehousing data, improve the efficiency of cold chain warehousing management, and save cold chain warehousing energy consumption.

[0004] In order to solve the above technical problems, the present invention provides a method for implementing a cold chain warehousing intelligent energy-saving platform based on pyside2 and MySQL, which is characterized by comprising the following steps:

[0005] Step 1: Create an Alibaba Cloud RDS MySQL database for storing cold storage data, read the cold storage environment parameter information through sensors, and save the collected data to the Alibaba Cloud RDS MySQL database.

[0006] Step 2: Design the platform interface:

[0007] Implement user login, registration, and data display interfaces, plan interface layouts through QT components, and create different components to display various elements and content.

[0008] Step 3: Use SQL commands on the PC to remotely connect to the Alibaba Cloud RDS MySQL database and read relevant data from it.

[0009] Step 4: Establish a neural network model to predict feature data for a period of time in the future. Make an intelligent defrost decision based on the predicted data and the pre-set defrost decision, and transmit the predicted feature data and defrost decision to the cloud MySQL database for storage.

[0010] Step 5: Establish a face recognition algorithm model to realize staff face recognition and save new staff face data.

[0011] Preferably, the MySQL database includes a user information database, an energy consumption database, a temperature database, a prediction feature database, and a defrost database.

[0012] Preferably, the data display interface includes the following interfaces: a temperature data display interface, an energy consumption data display interface, a defrost data display interface, and a face recognition display interface.

[0013] Preferably, in step 4, the neural network model for realizing the prediction of feature data for a period of time in the future is a dual model of LSTM and CNN.

[0014] Preferably, in step 4, the defrost decision includes an early defrost decision and a delayed defrost decision. According to the peak and valley periods of the local real-time electricity price, an average energy consumption price prediction calculation formula is designed, and the defrost decision is made intelligently through the calculation results to achieve energy saving.

[0015] Preferably, in step 5, the algorithm model for implementing face recognition is a YOLOv8n model.

[0016] The present invention develops an intelligent energy-saving platform for cold chain storage based on pyside2 and MySQL technology. The platform uses pyside2 to design the platform interface, uses Alibaba Cloud RDS MySQL database to store data, uses neural network models LSTM and CNN for dual prediction, sets defrost decisions, and makes intelligent defrost decisions.

[0017] The present invention establishes an exclusive data warehouse, stores the collected cold chain storage data in a separate manner, receives and stores defrost decisions in real time, realizes visual management of ambient temperature data, energy consumption data, and defrost data, and can present it to staff in various forms such as curve charts, tables, and comparison charts. The defrost decision is displayed on the interface through the status of the label. The staff can view the defrost status, defrost duration, remaining defrost time, expected energy saving, time to next defrost start, current frost thickness and other parameters, monitor the cold chain storage status in real time, and realize staff clocking in and new staff face entry through the face recognition interface. The cold chain storage platform displays real-time data and makes intelligent defrost decisions to improve the effect for the staff and achieve the purpose of saving energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is the process of collecting and using data for cold chain warehousing;

[0019] Figure 2 It is a decision flow chart of intelligent defrost model;

[0020] Figure 3 This is the operation flow chart of the cold chain warehousing intelligent energy-saving platform. DETAILED DESCRIPTION

[0021] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the appended claims of the application equally.

[0022] In the present invention, firstly, a data acquisition system is deployed in a cold chain storage environment to collect data in real time. The collected data include ambient temperature, temperature inside the warehouse, humidity inside the warehouse, exhaust temperature, return air temperature, liquid outlet temperature, evaporation temperature, condensation temperature, compressor current, low pressure, high pressure, electronic expansion valve step number 1, electronic expansion valve step number 2, door opening times, door opening time, current set temperature, current set temperature difference, and total system operation time. Figure 1 As shown in the figure, the collected data is transmitted to the Alibaba Cloud RDS MySQL database through the Alibaba Cloud IoT platform. In the cold chain warehousing intelligent energy-saving platform environment, SQL can be used to read cloud data for local use, data processing and interface display.

[0023] The following is a further detailed description of the implementation scheme of the present invention:

[0024] (1) Create an Alibaba Cloud RDS MySQL database for storing cold chain warehouse data

[0025] MYSQL is a fast and robust relational database management system. This database will allow you to efficiently store, search, sort and retrieve data. The MYSQL server will control access to the data, ensuring that multiple users can use it concurrently, while providing fast access and ensuring that only authenticated users can gain access to the data. It includes user information database, energy consumption database, temperature database, prediction feature database, and defrost database. Then create new data tables in these databases, including user information table, energy consumption data table, temperature data table, humidity data table, defrost data table, etc.

[0026] (2) Interface design of chain storage intelligent energy-saving platform:

[0027] First, implement the user login interface and the new user registration interface. All user information will be saved in the user information table in the Alibaba Cloud RDSMySQL database. Old user information records can be deleted through commands. The homepage of the campus energy-saving platform mainly includes the following interfaces: temperature data display interface, energy consumption data display interface, defrost data display interface, and face recognition display interface. Each interface displays the corresponding data in real time, including graphs and tables. The defrost status is visualized by highlighting the button to display the current defrost status of the cold chain warehouse. The historical cold chain warehouse data can be queried through the table. The face recognition display interface identifies the current user and displays the current user information.

[0028] (3) Defrosting decision-making plan

[0029] Basic strategy for normal defrost decision:

[0030] Determine the start of defrost: Use the Cop of the ideal defrost time obtained by experiment and the threshold set by the static pressure difference to determine that defrost begins when one of the thresholds is reached.

[0031] Defrost decision and prediction:

[0032] The time-sharing defrosting strategy is adopted to make full use of the peak-valley difference of electricity prices. When approaching the peak-valley period, the frosting time and defrosting time are predicted through the neural network model to determine whether the set required value is reached and the average energy consumption price difference is calculated, so as to decide whether to advance or delay defrosting. The purpose is to optimize energy consumption and save costs.

[0033] Mathematical model to calculate the amount of frost:

[0034] From the perspective of mathematical model calculation, the temperature, humidity and air volume data at the fan inlet and outlet are used to calculate the frosting rate through mathematical model analysis and existing formulas, and a frosting model is established. The amount of frost is obtained by accumulating over time (integral operation). After the frost rate is obtained, it is compared with the set threshold. If it is greater than or equal to the threshold, defrosting begins.

[0035] Delayed defrost strategy:

[0036] During the peak power period, if the time T between a certain frosting point and the valley power time is short (generally not more than one defrost cycle), the frosting time can be extended to the valley power time before defrosting. The defrost cycle is obtained by reading the COP time trend chart to ensure the best balance between defrosting economy and effect; during the peak power period, set the time T between a certain frosting point and the valley power time (generally T will not exceed one defrost cycle, and the frosting time can be extended to the valley power time before defrosting). Among them, the defrost cycle is obtained by reading the COP time trend chart.

[0037] Early defrost strategy:

[0038] The early defrost strategy aims to save energy and reduce costs, especially during peak and valley electricity periods. Early defrost can reduce the system's operating load during peak periods with high electricity prices, thereby minimizing energy costs. It helps optimize the energy efficiency performance of cold storage, reduce the burden on the power grid, and achieve significant cost savings at the economic level. At a certain starting point of frost formation, by reading the trend of COP changes over time, it is determined that the defrost cycle time is greater than or equal to the time from the peak electricity period, but less than the maximum defrost time, then early defrost needs to be considered.

[0039] Energy consumption prediction and visual monitoring:

[0040] The frosting and defrosting process is accurately predicted through the neural network model, and the advantages of the dual models (LSTM and CNN) are combined to finally display the frosting amount, defrosting time, real-time power, compressor status and other data on the cold chain storage platform, realizing visual monitoring and portable adjustment of data. This method can not only understand the system status in real time, but also perform necessary operation optimization and improve the intelligence and automation level of the system.

[0041] The specific implementation of this invention patent mainly requires a PC, as well as the deployment of a cold chain warehouse data collection system, the creation of an Alibaba Cloud RDS MySQL database, an interface design environment, and related software.

Claims

1. A method for implementing a cold chain storage intelligent energy-saving platform based on pyside2 and MySQL, characterized in that: The following steps are involved: Step 1. Use Alibaba Cloud RDS MySQL database to store cold chain storage data, use Kunlun Tongtai TPC1071Gt touch screen as the display, use MCGSPro to draw the engineering screen, and use the Modbus communication protocol to transmit data with the unit main control board, temperature and humidity sensor, and power acquisition module. Use Alibaba Cloud IoT platform as the server to receive the main control board data, and then transmit the relevant data to Alibaba Cloud RDS MySQL database. Step 2: Design the platform interface: Implement user login, registration, and data display interfaces, plan interface layouts through QT components, and create different components to display various elements and content. Step 3: Use SQL statements on the PC to remotely connect to the Alibaba Cloud RDS MySQL database and read relevant data. Step 4: Build a neural network model to predict feature data for a period of time in the future. Make an intelligent defrost decision based on the predicted feature data and the pre-set defrost decision, and transmit the predicted feature data and defrost decision to the Alibaba Cloud RDS MySQL database for storage. Step 5: Establish a face recognition algorithm model to realize user face recognition and save new user face data.

2. A method for implementing a cold chain warehousing intelligent energy-saving platform based on pyside2 and MySQL as described in claim 1, characterized in that the Alibaba Cloud RDS MySQL database includes a user information database, an energy consumption database, a temperature database, a prediction feature database, and a defrost database.

3. A method for implementing a cold chain warehousing intelligent energy-saving platform based on pyside2 and MySQL as described in claim 1, characterized in that, in step 2, the data display interface includes the following interfaces: temperature data display interface, energy consumption data display interface, defrost data display interface, and face recognition display interface.

4. A method for implementing a cold chain warehousing intelligent energy-saving platform based on pyside2 and MySQL as claimed in claim 1, characterized in that, in step 4, the neural network model for realizing feature data prediction for a period of time in the future is a LSTM and CNN dual model.

5. A method for implementing a cold chain warehousing intelligent energy-saving platform based on pyside2 and MySQL as claimed in claim 1, characterized in that, in step 4, the defrost decision includes an early defrost decision and a delayed defrost decision, and an average energy consumption price prediction calculation formula is designed according to the peak and valley periods of the local real-time electricity price, and the defrost decision is made intelligently through the calculation results to achieve the purpose of energy saving.

6. The method for implementing a cold chain warehousing intelligent energy-saving platform based on pyside2 and MySQL as claimed in claim 1, wherein in step 5, the algorithm model for implementing face recognition is a YOLOv8n model.

Images