Edge computing system for monitoring energy consumption of agricultural machinery

Abstract

The invention relates to the technical field of energy consumption monitoring, and particularly discloses an edge computing system for agricultural machinery energy consumption monitoring, which comprises a data acquisition module, a preprocessing module, an edge computing module, a cloud server, a data analysis module and an optimization module. According to the scheme, real-time processing and optimization of energy consumption data are achieved through the edge computing technology, meanwhile, the data processing flow is optimized, the adaptability and robustness of the system are enhanced, the operation state of agricultural equipment is monitored and adjusted in real time through a closed-loop feedback mechanism, an energy consumption analysis report is generated in time, the fault occurrence probability is reduced, and the energy consumption analysis efficiency is improved. The service life of equipment is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption monitoring, and in particular to an edge computing system for monitoring energy consumption of agricultural machinery. Background Art

[0002] With the development of agricultural mechanization, agricultural machinery and equipment are widely used in modern agricultural production, and energy consumption has gradually become a key factor affecting agricultural costs and the environment. The energy consumption of agricultural machinery and equipment is not only affected by factors such as the type of operation, working environment, and operation intensity, but is also closely related to the maintenance status, operation methods, and work efficiency of the equipment. Traditional agricultural machinery energy consumption monitoring methods are often based on simple data statistics and lack a dynamic adjustment mechanism. They cannot automatically optimize operating parameters during equipment operation, thus affecting agricultural production efficiency. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an edge computing system for monitoring the energy consumption of agricultural machinery. Traditional agricultural machinery energy consumption monitoring methods are often based on simple data statistics, lack a dynamic adjustment mechanism, and cannot automatically optimize operating parameters during equipment operation. This solution uses edge computing technology to realize real-time processing and optimization of energy consumption data, while optimizing the data processing process, enhancing the adaptability and robustness of the system, and monitoring and adjusting the operating status of agricultural machinery in real time through a closed-loop feedback mechanism, and generating energy consumption analysis reports in a timely manner, thereby reducing the probability of failures and extending the service life of equipment.

[0004] The present invention provides an edge computing system for monitoring energy consumption of agricultural machinery, comprising a data acquisition module, a preprocessing module, an edge computing module, a cloud server, a data analysis module, and an optimization module;

[0005] The data acquisition module is installed on the agricultural machinery and collects the operation data and energy consumption data of the agricultural machinery in real time, and sends the collected data to the preprocessing module;

[0006] The preprocessing module performs preliminary filtering and formatting on the collected data, removes noise and redundant data, obtains processed data, and sends the processed data to the edge computing module;

[0007] The edge computing module performs real-time calculation and analysis on the processed data, generates a preliminary energy consumption analysis report, and sends the energy consumption analysis report to the cloud server;

[0008] The cloud server stores the energy consumption analysis report, summarizes and deeply analyzes the energy consumption analysis report, generates energy consumption optimization suggestions, and sends the energy consumption optimization suggestions to the data analysis module;

[0009] The data analysis module analyzes the energy consumption optimization suggestions in detail, generates specific optimization strategies, and sends the optimization strategies to the optimization module;

[0010] The optimization module adjusts the operating parameters of the agricultural machinery equipment according to the received optimization strategy, continuously monitors the operating status of the agricultural machinery equipment, and dynamically adjusts the optimization strategy.

[0011] Furthermore, the preprocessing module performs preliminary filtering and formatting on the collected data, including the following steps:

[0012] Step P1: Data cleaning, dividing the collected data into data point sequences and removing invalid values ​​and outliers in the data point sequences;

[0013] Step P2: Data formatting, unifying the data collected by different sensors into a standard format;

[0014] Step P3: Data compression, removing redundant information from the data and performing data compression through a compression algorithm;

[0015] Step P4: Data labeling, adding a timestamp and equipment ID to each data point sequence. The timestamp is used to record the specific time of data collection, and the equipment ID is used to distinguish different agricultural machinery equipment.

[0016] Furthermore, the edge computing module performs real-time calculation and analysis on the processed data, including the following steps:

[0017] Step S1: Data aggregation, aggregating data with the same timestamp to generate time series data;

[0018] Step S2: Energy consumption pattern recognition, using clustering algorithm to analyze the operation mode of agricultural machinery and equipment, and identify the energy consumption characteristics under different working conditions. The specific steps are as follows:

[0019] Step S21: feature extraction, extracting key features from the time series data, including energy consumption peak, average energy consumption, energy consumption fluctuation range, and trend characteristics;

[0020] Step S22: Cluster analysis, using a Gaussian mixture clustering model to process the probability distribution in the data and identify different energy consumption characteristics, specifically including the following steps:

[0021] Step S221: setting the Gaussian distribution number to represent the number of clusters;

[0022] Step S222: Initialize the Gaussian mixture clustering model, initialize the mean, covariance matrix and mixing coefficient;

[0023] Step S223: iterative training, training the Gaussian mixture clustering model by expectation maximization, calculating the membership of each data point in each cluster based on the current model parameters, and updating the parameters of the Gaussian distribution, iterative training until the model converges;

[0024] Step S23: Pattern recognition, outputting the parameters of each cluster, and calculating the membership probability of each data point to different clusters, analyzing the energy consumption patterns represented by different clusters according to the mean and covariance characteristics of each cluster, and assigning a cluster label to each cluster;

[0025] Step S24: pattern matching, combining the actual operating parameters of the agricultural machinery and equipment, identifying the energy consumption pattern and specific operation tasks according to the cluster label;

[0026] Step S3: Anomaly detection, detecting anomalies in the data and generating anomaly reports, specifically including the following steps:

[0027] Step S31: abnormality definition, setting performance index thresholds of agricultural machinery;

[0028] Step S32: Analyze the time series data by moving average method. If a data point deviates from the predetermined range, the data point is considered abnormal, the time when the abnormality occurs is marked, and the related equipment where the abnormality occurs is identified according to the equipment identification;

[0029] Step S33: generating an abnormality report, generating an abnormality time series and an abnormality trend chart based on the time when the abnormality occurred, and summarizing the results of abnormality detection to generate an abnormality report;

[0030] Step S4: Energy consumption assessment: Based on key features and abnormal reports, an energy consumption model is established to assess the energy consumption level of agricultural machinery and equipment, and an energy consumption analysis report for each agricultural machinery and equipment is generated. The formula used is as follows: ;

[0031] In the formula, Indicates the current value, Indicates pressure, Indicates temperature, represents speed, a, b, c and d are weight parameters, Indicates the energy consumption level of agricultural machinery.

[0032] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0033] Traditional agricultural machinery energy consumption monitoring methods are often based on simple data statistics, lack a dynamic adjustment mechanism, and are unable to automatically optimize operating parameters during equipment operation. This solution uses edge computing technology to achieve real-time processing and optimization of energy consumption data, while optimizing the data processing process, enhancing the adaptability and robustness of the system, and using a closed-loop feedback mechanism to monitor and adjust the operating status of agricultural machinery in real time, and generate energy consumption analysis reports in a timely manner, reducing the probability of failures and extending the service life of equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of an edge computing system for monitoring energy consumption of agricultural machinery proposed by the present invention;

[0035] Figure 2 Schematic diagram of the process of edge computing module performing real-time calculation and analysis on processed data.

[0036] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0038] Example 1, see Figure 1 , an edge computing system for monitoring energy consumption of agricultural machinery provided by the present invention includes a data acquisition module, a preprocessing module, an edge computing module, a cloud server, a data analysis module, and an optimization module;

[0039] The data acquisition module is installed on the agricultural machinery and is equipped with a temperature sensor, a pressure sensor, a current sensor, and a speed sensor to collect the operation data and energy consumption data of the agricultural machinery in real time, and send the collected data to the preprocessing module via LoRa wireless communication;

[0040] The preprocessing module performs preliminary filtering and formatting on the collected data, removes noise and redundant data, obtains processed data, and sends the processed data to the edge computing module;

[0041] The edge computing module performs real-time calculation and analysis on the processed data, generates a preliminary energy consumption analysis report, and sends the energy consumption analysis report to the cloud server;

[0042] The cloud server stores the energy consumption analysis report, summarizes and deeply analyzes the energy consumption analysis report, generates energy consumption optimization suggestions, and sends the energy consumption optimization suggestions to the data analysis module;

[0043] The data analysis module analyzes the energy consumption optimization suggestions in detail, generates specific optimization strategies, and sends the optimization strategies to the optimization module;

[0044] The optimization module adjusts the operating parameters of the agricultural machinery equipment according to the received optimization strategy, continuously monitors the operating status of the agricultural machinery equipment, and dynamically adjusts the optimization strategy.

[0045] Example 2, see Figure 1 This embodiment is based on the first embodiment, and the preprocessing module performs preliminary filtering and formatting on the collected data, including the following steps:

[0046] Step P1: Data cleaning: divide the collected data into data point sequences, remove invalid values ​​and outliers in the data point sequences. Invalid values ​​include missing data points caused by sensor failures and data points whose readings exceed a reasonable range. Outliers are determined by calculating the standardized distance between the data point and the average value of the data point sequence using the Z-score method. If the standardized distance exceeds the preset threshold, the data point is considered to be an outlier. The formula used is as follows: ;

[0047] In the formula, represents a data point, represents the mean value of the data point sequence, represents the standard deviation of the data point sequence, represents the normalized distance;

[0048] Step P2: Data formatting, unifying the data collected by different sensors into a standard format;

[0049] Step P3: Data compression, removing redundant information from the data through dictionary encoding and Zstandard compression algorithm;

[0050] Step P4: Data labeling, adding a timestamp and equipment ID to each data point sequence. The timestamp is used to record the specific time of data collection, and the equipment ID is used to distinguish different agricultural machinery equipment.

[0051] Example 3, see Figure 1 This embodiment is based on the first embodiment, and the preprocessing module performs preliminary filtering and formatting on the collected data, including the following steps:

[0052] Step P1: Data cleaning: divide the collected data into data point sequences, remove invalid values ​​and outliers in the data point sequences. Invalid values ​​include missing data points caused by sensor failures and data points whose readings are beyond the reasonable range. Outliers use the IQR quartile method to calculate the quartile range of the data points to determine whether the data points are within the reasonable range. The formula used is as follows: ;

[0053] In the formula, represents the first quartile, represents the third quartile, represents the interquartile range;

[0054] If the data point is not [ Q1-1.5×IQR,Q3+1.5×IQR ] If the data point is within the range, it is considered to be an outlier.

[0055] Step P2: Data formatting, unifying the data collected by different sensors into a standard format;

[0056] Step P3: Data compression, using the LZ4 compression algorithm, removing redundant information from the data through a sliding window and a hash table, and performing data compression;

[0057] Step P4: Data labeling, adding a timestamp and equipment ID to each data point sequence. The timestamp is used to record the specific time of data collection, and the equipment ID is used to distinguish different agricultural machinery equipment.

[0058] Example 4, see Figure 1 and Figure 2 This embodiment is based on the third embodiment, and the edge computing module performs real-time calculation and analysis on the processed data, including the following steps:

[0059] Step S1: Data aggregation, aggregating data with the same timestamp to generate time series data;

[0060] Step S2: Energy consumption pattern recognition, using clustering algorithm to analyze the operation mode of agricultural machinery and equipment, and identify the energy consumption characteristics under different working conditions. The specific steps are as follows:

[0061] Step S21: Feature extraction, extracting key features from the time series data, including energy consumption peak value, average energy consumption, energy consumption fluctuation range, and trend characteristics. The formula used to extract energy consumption peak value and average energy consumption is as follows: ; ;

[0062] In the formula, Indicates the current value, represents the maximum value function, Indicates the voltage value, Indicates time, represents the summation function, Indicates the peak energy consumption. represents the average energy consumption;

[0063] Step S22: Cluster analysis, using a Gaussian mixture clustering model to process the probability distribution in the data and identify different energy consumption characteristics, specifically including the following steps:

[0064] Step S221: setting the Gaussian distribution number to represent the number of clusters;

[0065] Step S222: Initialize the Gaussian mixture clustering model, randomly initialize the mean, covariance matrix and mixing coefficient, the mean represents the center position of each cluster, the covariance matrix represents the distribution form of the data in each cluster, and the mixing coefficient represents the proportion of each cluster in the overall data;

[0066] Step S223: iterative training, training the Gaussian mixture clustering model by expectation maximization, calculating the membership of each data point in each cluster based on the current model parameters, and updating the parameters of the Gaussian distribution, iterative training until the model converges;

[0067] Step S23: Pattern recognition, outputting the parameters of each cluster, and calculating the membership probability of each data point to different clusters, analyzing the energy consumption patterns represented by different clusters according to the mean and covariance characteristics of each cluster, and assigning a cluster label to each cluster, which includes high-efficiency mode and low-efficiency mode;

[0068] Step S24: pattern matching, combining the actual operating parameters of the agricultural machinery and equipment, identifying the energy consumption pattern and specific operation tasks according to the cluster label;

[0069] Step S3: Anomaly detection, detecting anomalies in the data and generating anomaly reports, specifically including the following steps:

[0070] Step S31: abnormality definition, setting performance index thresholds of agricultural machinery;

[0071] Step S32: Analyze the time series data by moving average method. If a data point deviates from the predetermined range, the data point is considered abnormal, the time when the abnormality occurs is marked, and the related equipment where the abnormality occurs is identified according to the equipment identification;

[0072] Step S33: abnormal report generation, generating an abnormal time series and abnormal trend chart based on the time when the abnormality occurred, and summarizing the results of abnormality detection to generate an abnormal report, including abnormal operation tasks, abnormal number of times, abnormal equipment, abnormal duration, abnormal type and severity;

[0073] Step S4: Energy consumption assessment: Based on key features and abnormal reports, an energy consumption model is established to assess the energy consumption level of agricultural machinery and equipment, and an energy consumption analysis report for each agricultural machinery and equipment is generated. The formula used is as follows: ;

[0074] In the formula, Indicates pressure, Indicates temperature, represents speed, a, b, c and d are weight parameters, Indicates the energy consumption level of agricultural machinery.

[0075] By performing the above operations, the traditional agricultural machinery energy consumption monitoring method is often based on simple data statistics, lacks a dynamic adjustment mechanism, and cannot automatically optimize the operating parameters during the operation of the equipment. This solution uses edge computing technology to realize real-time processing and optimization of energy consumption data, while optimizing the data processing process, enhancing the adaptability and robustness of the system, and monitoring and adjusting the operating status of agricultural machinery in real time through a closed-loop feedback mechanism, and generating energy consumption analysis reports in a timely manner, thereby reducing the probability of failures and extending the service life of the equipment.

[0076] Example 5, see Figure 1 This embodiment is based on the above embodiment. The cloud server summarizes and deeply analyzes the transmitted energy consumption analysis report, specifically: summarizes the energy consumption analysis reports of all agricultural machinery equipment, generates comprehensive energy consumption data, extracts key information, and generates specific energy consumption optimization suggestions, including equipment maintenance and operation improvements.

[0077] Example 6, see Figure 1 This embodiment is based on the above embodiment, and the optimization module adjusts the operating parameters of the agricultural machinery equipment according to the received optimization strategy, including the following steps:

[0078] Step A1: Analyze the optimization strategy and convert the energy consumption optimization suggestions into specific adjustment instructions;

[0079] Step A2: Execute adjustment instructions to adjust the operating parameters, working speed, and working mode of the agricultural machinery;

[0080] Step A3: Effect evaluation: real-time monitoring of the operating status of the adjusted agricultural machinery and equipment, evaluation of the adjustment effect, and generation of an evaluation report;

[0081] Step A4: Feedback adjustment: dynamically adjust the optimization strategy according to the evaluation report to ensure continuous improvement of the optimization effect.

[0082] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0083] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0084] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. An edge computing system for monitoring energy consumption of agricultural machinery, characterized in that: It includes data acquisition module, preprocessing module, edge computing module, cloud server, data analysis module and optimization module; The data acquisition module is installed on the agricultural machinery and collects the operation data and energy consumption data of the agricultural machinery in real time, and sends the collected data to the preprocessing module; The preprocessing module performs preliminary filtering and formatting on the collected data, removes noise and redundant data, obtains processed data, and sends the processed data to the edge computing module; The edge computing module performs real-time calculation and analysis on the processed data, generates a preliminary energy consumption analysis report, and sends the energy consumption analysis report to the cloud server; The cloud server stores the energy consumption analysis report, summarizes and deeply analyzes the energy consumption analysis report, generates energy consumption optimization suggestions, and sends the energy consumption optimization suggestions to the data analysis module; The data analysis module analyzes the energy consumption optimization suggestions in detail, generates specific optimization strategies, and sends the optimization strategies to the optimization module; The optimization module adjusts the operating parameters of the agricultural machinery equipment according to the received optimization strategy, continuously monitors the operating status of the agricultural machinery equipment, and dynamically adjusts the optimization strategy.

2. The edge computing system for monitoring energy consumption of agricultural machinery according to claim 1, characterized in that: The preprocessing module performs preliminary filtering and formatting on the collected data, including the following steps: Step P1: Data cleaning, dividing the collected data into data point sequences and removing invalid values ​​and outliers in the data point sequences; Step P2: Data formatting, unifying the data collected by different sensors into a standard format; Step P3: Data compression, removing redundant information from the data and performing data compression through a compression algorithm; Step P4: Data labeling, adding timestamp and device identification to each data point sequence.

3. The edge computing system for monitoring energy consumption of agricultural machinery according to claim 2, characterized in that: The edge computing module performs real-time computing and analysis on the processed data, including the following steps: Step S1: Data aggregation, aggregating data with the same timestamp to generate time series data; Step S2: Energy consumption pattern recognition, using clustering algorithm to analyze the operation mode of agricultural machinery and equipment, and identify the energy consumption characteristics under different working conditions. The specific steps are as follows: Step S21: feature extraction, extracting key features from time series data; Step S22: Cluster analysis, using a Gaussian mixture clustering model to process the probability distribution in the data and identify different energy consumption characteristics, specifically including the following steps: Step S221: setting the Gaussian distribution number to represent the number of clusters; Step S222: Initialize the Gaussian mixture clustering model, initialize the mean, covariance matrix and mixing coefficient; Step S223: iterative training, training the Gaussian mixture clustering model by expectation maximization, calculating the membership of each data point in each cluster based on the current model parameters, and updating the parameters of the Gaussian distribution, iterative training until the model converges; Step S23: Pattern recognition, outputting the parameters of each cluster, and calculating the membership probability of each data point to different clusters, analyzing the energy consumption patterns represented by different clusters according to the mean and covariance characteristics of each cluster, and assigning a cluster label to each cluster; Step S24: pattern matching, combining the actual operating parameters of the agricultural machinery and equipment, identifying the energy consumption pattern and specific operation tasks according to the cluster label; Step S3: Anomaly detection, detecting anomalies in the data and generating anomaly reports, specifically including the following steps: Step S31: abnormality definition, setting performance index thresholds of agricultural machinery; Step S32: Analyze the time series data by moving average method. If a data point deviates from the predetermined range, the data point is considered abnormal. The time when the abnormality occurs is marked, and the related equipment where the abnormality occurs is identified according to the equipment identification. Step S33: generating an abnormality report, generating an abnormality time series and an abnormality trend chart based on the time when the abnormality occurred, and summarizing the results of abnormality detection to generate an abnormality report; Step S4: Energy consumption assessment: Based on key features and abnormal reports, an energy consumption model is established to assess the energy consumption level of agricultural machinery and equipment, and an energy consumption analysis report for each agricultural machinery and equipment is generated. The formula used is as follows: ； In the formula, Indicates the current value, Indicates pressure, Indicates temperature, represents speed, a, b, c and d are weight parameters, Indicates the energy consumption level of agricultural machinery.

Images