Workshop digital air conditioner temperature and humidity remote metering system and method

Abstract

The invention discloses a workshop digital air conditioner temperature and humidity remote metering system and method, and belongs to the technical field of instrument metering. The system comprises a WIFI / 5G communication board and a temperature and humidity sensor. The temperature and humidity sensor is connected with the WIFI / 5G communication board through a line. According to the method, the problems of low quality of traditional metering data and low metering efficiency are effectively solved, and an error prediction model is realized in combination with machine learning; the waiting time of personnel is shortened, asynchronous metering can be achieved, instrument errors can be found in time, manpower is saved, digital workshop construction is promoted, and the lean management level of metering instruments is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of instrument measurement, and in particular relates to a remote temperature and humidity measurement system and method for digital air conditioning in a workshop. Background Art

[0002] Production workshops have strict requirements on the temperature and humidity of the environment. Traditional temperature and humidity control methods mainly rely on manual adjustment or simple automatic control, which is difficult to respond to environmental changes in a timely manner, resulting in unstable product quality. In addition, existing systems usually lack remote monitoring and intelligent analysis functions, and cannot achieve real-time collection and optimization control of multi-point data. Traditional temperature and humidity measurement methods have many shortcomings in practical applications, which are mainly reflected in the following aspects:

[0003] Equipment disassembly is complex and maintenance is difficult: Traditional temperature and humidity monitoring equipment usually uses analog sensors, which need to be directly connected to the air conditioning control system. Due to the complex structure of the equipment, the installation and maintenance of the sensor requires partial disassembly of the air conditioning system. Each time the sensor is calibrated or repaired, the relevant equipment needs to be shut down and disassembled, which is a cumbersome process and prone to other failures.

[0004] Laboratory measurement is complex and delayed: In order to ensure the accuracy of temperature and humidity sensors, they must be calibrated regularly. The traditional method requires the sensor to be disassembled and sent to a professional laboratory for measurement, which not only increases manpower and time costs, but may also cause the sensor to be damaged during transportation and reinstallation. In addition, the laboratory measurement cycle is long and cannot meet the real-time and continuity requirements of the production site.

[0005] Frequent manual intervention and low work efficiency: Due to the low degree of automation, operators are required to manually adjust air conditioning parameters in many cases. This not only increases the workload of personnel, but may also cause inaccurate adjustments or delays due to human factors. At the same time, operators need to have certain professional knowledge, and the training cost is high.

[0006] Low level of informatization and inability to integrate: Traditional temperature and humidity control systems usually operate independently and cannot be integrated with other information systems in the workshop (such as production management systems and quality control systems), resulting in information islands and limiting the improvement of the overall intelligence level of the workshop.

[0007] At present, remote measurement and analysis is a relatively advanced measurement technology. It can collect temperature and humidity data online in real time by installing a standard meter that meets the requirements and send it to a remote server for data analysis and remote calibration, making the collected pressure data persistent and convenient for remote measurement and analysis. The system can also be remotely connected to the measurement laboratory to facilitate the control and coordination of various parts of the work and free up manpower. Summary of the invention

[0008] The purpose of the present invention is to provide a remote temperature and humidity metering system and method for a digital air conditioner in a workshop. By introducing a machine learning algorithm, real-time monitoring, intelligent analysis and remote correction of the temperature and humidity instruments in the workshop can be achieved, thereby improving product quality and production efficiency.

[0009] In order to achieve the above object, the present invention adopts the following technical solution:

[0010] A workshop digital air conditioning temperature and humidity remote metering system includes a WIFI / 5G communication board and a temperature and humidity sensor; the temperature and humidity sensor is connected to the WIFI / 5G communication board through a line; wherein,

[0011] A WIFI / 5G communication board is configured to communicate with the temperature and humidity sensor;

[0012] The temperature and humidity sensor is configured to collect temperature and humidity data.

[0013] In addition, the present invention also mentions a remote measurement method for temperature and humidity of a workshop digital air conditioner, which adopts the remote measurement system for temperature and humidity of a workshop digital air conditioner as described above, and specifically comprises the following steps:

[0014] Step 1: Collect temperature and humidity data through the temperature and humidity sensor, and store the collected temperature and humidity data in the local database;

[0015] Step 2: Preprocess and align the collected temperature and humidity data;

[0016] Step 3: Through multiple linear regression analysis and time series prediction algorithm, the error prediction of the preprocessed and aligned temperature and humidity data is carried out, and the error prediction model is constructed using the normalization method;

[0017] Step 4: Apply the error prediction model to perform statistical analysis and generate a measurement result report.

[0018] Preferably, step 2 specifically includes the following steps:

[0019] Step 2.1: Preprocess the collected temperature and humidity data, including data resampling, window segmentation, and standardization;

[0020] Step 2.2: Perform data alignment on the preprocessed data and store the data in a database as a data source for error prediction model training.

[0021] Preferably, step 2.2 specifically includes the following steps:

[0022] Step 2.2.1: Data smoothing;

[0023] Step 2.2.2: Peak extraction;

[0024] Step 2.2.3: Filtering and outlier processing;

[0025] Step 2.2.4: Time series mean alignment.

[0026] Beneficial technical effects brought by the present invention:

[0027] The present invention proposes a remote temperature and humidity metering system and method for digital air conditioning in a workshop, which effectively solves the problems of low quality of traditional metering data and low metering efficiency, and realizes an error prediction model in combination with machine learning. The above technical method reduces the waiting time of personnel, can realize asynchronous metering, timely discover instrument errors, save manpower, promote the construction of digital workshops, and improve the lean management level of metering instruments. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is the structural diagram of the temperature and humidity measuring system of the present invention.

[0029] Figure 2 This is a flow chart of the error prediction function of the present invention.

[0030] Figure 3 It is a flow chart of the metering process of the present invention. DETAILED DESCRIPTION

[0031] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments:

[0032] The present invention includes hardware design, software design and algorithm design.

[0033] Overall hardware solution

[0034] The hardware system includes WIFI / 5G communication board, high-precision temperature and humidity sensor, and easy-to-detach installation structure. The high-precision temperature and humidity sensor (standard meter) is installed near the workshop digital temperature and humidity meter (tested meter) through structural parts to ensure the time and space synchronization and continuity of data collection;

[0035] The sensor supports remote data collection, covering temperature and humidity data, signal strength, battery power and other information, to ensure the comprehensiveness and accuracy of metering data; the sensor supports the adjustment of collection strategies. When the equipment is operating normally, a general collection strategy is adopted to reduce energy consumption, making the collected values ​​characteristic values; the sensor adopts a wireless design to effectively reduce the difficulty of system wiring; the sensor data supports LAN uplink and public network uplink, and is compatible with cloud deployment.

[0036] Software overall solution

[0037] The software system includes data collection services, data analysis, error prediction, remote correction and service applications. The service application adopts the microservice architecture of SpringCloud, with front-end and back-end separated development and functions implemented based on B / S. The data collection service is developed as a system module, and the data analysis software uses the Python programming language. The data analysis service is developed based on Django, with MySQL as the database and Redis as the high-speed data cache.

[0038] This system adopts B / S architecture, can support mobile terminal, PDA multi-terminal measurement, PC terminal data display, can effectively reduce the waiting time of metering personnel, use asynchronous measurement, and improve measurement efficiency;

[0039] Service applications use SSE to push data and exception information to improve system response timeliness; all service software supports cross-platform deployment.

[0040] Algorithm Design

[0041] The algorithm design includes data signal preprocessing, data alignment, multivariate linear regression and time series prediction algorithm, normalization technology, and statistical analysis. The data analysis service is developed based on Django and uses MySQL as the database.

[0042] The data signal preprocessing steps include filtering, denoising and feature extraction to ensure the quality and accuracy of the input data; data alignment technology is used to deal with the problem of inconsistent acquisition time points of different sensors to ensure the consistency and synchronization of data. Normalization technology is used to process data of different dimensions so that the data is comparable when performing statistical analysis. Multiple linear regression and time series prediction algorithms are used to analyze and predict the trend of temperature and humidity changes, providing a scientific basis for remote measurement. The statistical analysis part provides decision support for the system by calculating the statistics of the data. The entire algorithm design aims to improve the accuracy and response speed of the system and ensure the efficiency and reliability of remote measurement.

[0043] System technology solutions

[0044] This embodiment collects data from temperature and humidity instruments in a production enterprise workshop. The structure of the temperature and humidity metering system is as follows: Figure 1 As shown in the figure, it mainly includes the temperature and humidity meter to be measured, the temperature and humidity standard meter, the communication module, and the analysis server; the measurement process is as follows Figure 3 As shown:

[0045] Step S1: Develop data acquisition interfaces for temperature and humidity sensors at key locations in the workshop. For devices that lack IoT interfaces, implement communication module modifications to implement communication interfaces based on WIFI / 5G technology as the measured instrument.

[0046] Step S2: Customize high-precision temperature and humidity sensors and perform WIFI / 5G technology transformation on the communication module. At the same time, design and optimize the installation structure to facilitate installation and disassembly as a standard table.

[0047] Step S3: Install the standard table to ensure the uniformity of time and space conditions to ensure the consistency and comparability of the measurement results.

[0048] Step S4: Develop a data collection interface to realize the automatic collection of data from the measured table and the standard table, and build a unified data collection platform. The collected data will be stored in the MySQL database system for subsequent analysis and processing.

[0049] Step S5: Develop a metering system to realize asynchronous metering function. The system will send instructions to the meter under test and the standard meter to collect relevant test data to ensure the synchronization and accuracy of data collection.

[0050] Step S6: Data signal preprocessing, using algorithms to perform data alignment, data normalization, associating the standard table with the table under test, analyzing and predicting the temperature and humidity change trends based on multiple linear regression and time series prediction algorithms, and building an error prediction model;

[0051] Step S6.1: preprocessing the collected temperature and humidity data, including data resampling, window segmentation, and standardization, and transforming the input data format for the error prediction model;

[0052] Step S6.2: aligning the data of the high-precision standard table and the table under test, and storing the data in a database as a data source for error prediction model training;

[0053] Step S6.3: Perform error prediction based on multiple linear regression and time series prediction algorithm.

[0054] Step S6.4: using normalization technology to fine-tune the model, and after repeated iterations, an error prediction model adapted to the target data is obtained;

[0055] Step S6.5: Statistically analyze relevant metrological capability indicators, analyze and judge the data based on the standard table, and form metrological results.

[0056] Step S7: Implement the alarm and push functions of the metering system, summarize and analyze the metering data, push the metering and prediction results to the user, and form a metering report. The user can also log in to the mobile terminal or PC terminal to view it.

[0057] In step S6, the data signal is preprocessed, the algorithm is used to align the data, the data is cleaned, and the standard table and the table under test are associated. The process is as follows:

[0058] Step S6.2: Data alignment: data smoothing -> peak extraction -> filtering and outlier processing -> time series mean alignment.

[0059] Step S6.3: Error prediction: time series resampling, time series analysis-multivariate linear regression.

[0060] Figure 2 This is a flow chart of the error prediction function of the present invention.

[0061] In this embodiment, we use the technical method proposed in the present invention to measure and predict errors for instruments that do not have remote metering conditions, have a small amount of data, and are not aligned in time and space. To improve the metering efficiency of the system, this embodiment designs easily detachable structural parts and installs communication modules to achieve asynchronous metering, thereby effectively improving the utilization rate of metering time. To achieve a closed-loop metering, the metering results of this system can be adjusted in the form of the original metering instrument or data acquisition system to complete metering correction. To improve metering response, this system supports multi-terminal applications such as mobile terminals and PC terminals, and pushes results based on protocols such as SSE.

[0062] The method of the present invention collects data from the workshop temperature and humidity digital meter standard table and the measured table, builds an error anomaly detection and early warning model, and uses machine learning and time series alignment and other algorithmic technologies to realize data comparison and analysis of the workshop temperature and humidity digital meter, thereby realizing remote measurement analysis of the temperature and humidity digital meter, and combining the system push function to realize the overall solution of temperature and humidity digital meter measurement. Therefore, the present invention has the value of being applied to the remote measurement of workshop temperature and humidity digital meters.

[0063] Of course, the above description is not a limitation of the present invention, and the present invention is not limited to the above examples. Changes, modifications, additions or substitutions made by technicians in this technical field within the essential scope of the present invention should also fall within the protection scope of the present invention.

Claims

1. A workshop digital air conditioning temperature and humidity remote metering system, characterized by: It includes a WIFI / 5G communication board and a temperature and humidity sensor; the temperature and humidity sensor is connected to the WIFI / 5G communication board through a line; wherein, A WIFI / 5G communication board is configured to communicate with the temperature and humidity sensor; The temperature and humidity sensor is configured to collect temperature and humidity data.

2. A remote measurement method for temperature and humidity of a workshop digital air conditioner, characterized in that: The digital air conditioning temperature and humidity remote metering system for a workshop as claimed in claim 1 specifically comprises the following steps: Step 1: Collect temperature and humidity data through the temperature and humidity sensor, and store the collected temperature and humidity data in the local database; Step 2: Preprocess and align the collected temperature and humidity data; Step 3: Through multiple linear regression analysis and time series prediction algorithm, the error prediction of the preprocessed and aligned temperature and humidity data is carried out, and the error prediction model is constructed using the normalization method; Step 4: Apply the error prediction model to perform statistical analysis and generate a measurement result report.

3. The remote measurement method for temperature and humidity of a workshop digital air conditioner according to claim 2 is characterized in that: Step 2 specifically includes the following steps: Step 2.1: Preprocess the collected temperature and humidity data, including data resampling, window segmentation, and standardization; Step 2.2: Perform data alignment on the preprocessed data and store the data in a database as a data source for error prediction model training.

4. The remote measurement method for temperature and humidity of a workshop digital air conditioner according to claim 3 is characterized in that: Step 2.2 specifically includes the following steps: Step 2.2.1: Data smoothing; Step 2.2.2: Peak extraction; Step 2.2.3: Filtering and outlier processing; Step 2.2.4: Time series mean alignment.

Images