Factory monitoring method and system based on Internet of Things, and storage medium

Abstract

The invention discloses a factory monitoring method and system based on the Internet of Things, and a storage medium. The method comprises the steps of obtaining energy consumption data, an equipment list and energy consumption characteristic parameters; preprocessing the energy consumption data to obtain a standardized data set, and obtaining an energy consumption association network through analysis operation; predicting the energy consumption of the equipment according to the energy consumption data to obtain an energy consumption change trend; judging according to the energy consumption change trend and a preset energy consumption threshold value; if the equipment energy consumption in the energy consumption change trend is greater than a preset energy consumption threshold value, judging that the equipment energy consumption is an abnormal energy consumption behavior; according to the energy consumption association network and the abnormal energy consumption behavior optimization, obtaining a process scheme; optimizing according to the equipment list and the energy consumption characteristic parameters to obtain a layout scheme; and setting the system according to the flow scheme and the layout scheme, so that the system works according to the flow scheme and the layout scheme. According to the method, continuous optimization of factory equipment energy consumption can be realized, and energy consumption is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of industrial Internet of Things and energy management technology, and in particular to a factory monitoring method, system and storage medium based on the Internet of Things. Background Art

[0002] In the factory production process, in order to achieve efficient use and conservation of energy, it is necessary to collect and analyze the energy consumption data of the equipment in real time. However, the production environment inside the factory is complex, the equipment is diverse, and the energy consumption characteristics and laws of different equipment are different, which brings challenges to the accurate collection and analysis of energy consumption data. At the same time, the production process inside the factory is often dynamically changing, and the operating status and load of the equipment are also constantly changing. How to achieve real-time collection and analysis of energy consumption data in such a dynamically changing environment is a technical problem that needs to be solved urgently.

[0003] In addition, when identifying high-energy-consuming equipment or abnormal energy consumption behavior, it is not enough to rely solely on the energy consumption data of a single device. It is also necessary to comprehensively consider the correlation between equipment and the overall energy consumption of the production process. How to establish a comprehensive energy consumption data analysis model, integrate multi-source heterogeneous energy consumption data, and mine the correlation rules between equipment and the energy consumption characteristics of the production process, so as to achieve accurate identification of high-energy-consuming equipment and abnormal energy consumption behavior, is a complex technical challenge. In terms of optimizing production processes and equipment layout, how to minimize energy consumption while ensuring production efficiency and product quality is an optimization problem that requires balancing multiple objectives. This requires comprehensive consideration of multiple factors such as the energy consumption characteristics of the equipment, the requirements of the production process, and the quality standards of the product, and the use of mathematical modeling and optimization algorithms to find the optimal production process and equipment layout plan. This is a complex technical problem involving multiple disciplines that requires in-depth research and exploration.

[0004] In one existing technology, a single-device energy consumption monitoring system is used to collect energy consumption data of each device in real time by installing energy consumption sensors, and analyze it using simple statistical methods to identify peak hours and abnormal consumption. During implementation, the system will regularly collect and store energy consumption data, and use visualization tools for monitoring and reporting.

[0005] However, the existing technology cannot fully consider the interrelationships between devices and the energy consumption characteristics of the overall production process, resulting in high energy consumption when identifying high-energy consumption equipment or abnormal energy consumption behavior. Summary of the invention

[0006] The present invention provides a factory monitoring method, system and storage medium based on the Internet of Things to solve the problem that the prior art cannot fully consider the interrelationships between devices and the energy consumption characteristics of the overall production process, resulting in high energy consumption when identifying high-energy consumption equipment or abnormal energy consumption behavior.

[0007] In a first aspect, in order to solve the above technical problems, the present invention provides a factory monitoring method based on the Internet of Things, comprising:

[0008] Obtain real-time energy consumption data, production equipment list and equipment energy consumption characteristic parameters;

[0009] Preprocessing is performed according to the real-time energy consumption data to obtain a standardized energy consumption data set;

[0010] Perform feature analysis based on the standardized energy consumption data set to obtain a device energy consumption feature library;

[0011] Performing correlation analysis based on the equipment energy consumption feature library to obtain an equipment energy consumption correlation network;

[0012] Predicting the energy consumption of the equipment according to the real-time energy consumption data to obtain the energy consumption change trend of the equipment;

[0013] A judgment is made based on the energy consumption change trend of the device and the preset energy consumption threshold; if the energy consumption of the device in the energy consumption change trend of the device is greater than the preset energy consumption threshold, the energy consumption of the device is determined to be abnormal energy consumption behavior; if the energy consumption of the device in the energy consumption change trend of the device is less than the preset energy consumption threshold, the energy consumption of the device is determined to be normal energy consumption behavior;

[0014] Optimize energy consumption according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process solution;

[0015] Perform layout optimization according to the production equipment list and the equipment energy consumption characteristic parameters to obtain an optimal equipment layout plan;

[0016] The production system is set up according to the optimal production process plan and the optimal equipment layout plan so that the production system works according to the optimal production process plan and the optimal equipment layout plan.

[0017] In an implementation manner of the first aspect, performing feature analysis according to the standardized energy consumption data set to obtain a device energy consumption feature library includes:

[0018] Performing cluster analysis using a K-means clustering algorithm based on the standardized energy consumption data set to obtain a clustering result;

[0019] Dividing the devices according to the clustering results to obtain device categories;

[0020] Performing feature analysis according to the device category to obtain a device energy consumption feature vector;

[0021] A decision tree algorithm is used to construct a model based on the equipment energy consumption feature vector to obtain an equipment energy consumption feature classification model;

[0022] The energy consumption of the equipment is divided according to the equipment energy consumption characteristic classification model to obtain the equipment energy consumption mode;

[0023] The energy consumption patterns of the equipment in the energy consumption mode are collected to obtain an equipment energy consumption feature library.

[0024] In an implementable manner of the first aspect, performing association analysis according to the device energy consumption feature library to obtain a device energy consumption association network includes:

[0025] The historical data in the equipment energy consumption feature library is trained using a decision tree algorithm to obtain an equipment energy consumption decision tree model;

[0026] Perform energy consumption correlation analysis between different devices according to the equipment energy consumption decision tree model to obtain an energy consumption correlation coefficient matrix;

[0027] A network is constructed according to the energy consumption correlation coefficient matrix to obtain a device energy consumption correlation network.

[0028] In an implementable manner of the first aspect, predicting the energy consumption of the device according to the real-time energy consumption data to obtain a trend of energy consumption changes of the device includes:

[0029] Collect the real-time energy consumption data of equipment in different production environments to obtain a time series data set;

[0030] Preprocessing is performed according to the time series data to obtain smoothed data;

[0031] The smoothed data is predicted using a time series analysis algorithm to obtain a trend of equipment energy consumption changes.

[0032] In an implementable manner of the first aspect, the step of optimizing energy consumption according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process solution includes:

[0033] Perform energy consumption anomaly analysis based on the equipment energy consumption association network and the abnormal energy consumption behavior to obtain key abnormal links;

[0034] Optimize the key abnormal links to obtain multiple optimization solutions;

[0035] Input each of the plurality of optimization schemes into a pre-stored equipment energy consumption model for prediction to obtain an overall energy consumption level;

[0036] By comparing the overall energy consumption levels of various solutions, the solution with the lowest overall energy consumption level is selected as the optimal production process solution.

[0037] In an implementation manner of the first aspect, the plurality of optimization schemes refer to schemes generated by optimizing the production process, adjusting the equipment operation sequence and load distribution by using a genetic algorithm and a simulated annealing algorithm.

[0038] In an implementable manner of the first aspect, performing layout optimization according to the production equipment list and the equipment energy consumption characteristic parameters to obtain an optimal equipment layout solution includes:

[0039] Integrate the equipment energy consumption characteristic parameters of the equipment in the production equipment list to obtain an equipment energy consumption characteristic database;

[0040] Using a clustering algorithm to classify the equipment energy consumption characteristic database, a classification result of equipment energy consumption is obtained;

[0041] The equipment energy consumption classification results are input into a pre-stored directed graph model of production equipment layout, and iterative optimization is performed with minimizing total energy consumption as the optimization goal to obtain an optimal equipment layout solution.

[0042] In a second aspect, the present invention provides a factory monitoring system based on the Internet of Things, comprising:

[0043] Data acquisition module, used to obtain real-time energy consumption data, production equipment list and equipment energy consumption characteristic parameters;

[0044] A data standardization module, used for preprocessing the real-time energy consumption data to obtain a standardized energy consumption data set;

[0045] A feature analysis module, used to perform feature analysis based on the standardized energy consumption data set to obtain a device energy consumption feature library;

[0046] A feature association module, used to perform association analysis based on the device energy consumption feature library to obtain a device energy consumption association network;

[0047] An energy consumption prediction module is used to predict the future energy consumption of the equipment based on the real-time energy consumption data to obtain the energy consumption change trend of the equipment;

[0048] An abnormality judgment module is used to judge according to the energy consumption change trend of the device and the preset energy consumption threshold; if the energy consumption of the device in the energy consumption change trend of the device is greater than the preset energy consumption threshold, the energy consumption of the device is judged to be abnormal energy consumption behavior;

[0049] A production process optimization module, used to optimize energy consumption according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process solution;

[0050] An equipment layout optimization module is used to optimize the layout according to the production equipment list and the equipment energy consumption characteristic parameters to obtain an optimal equipment layout plan;

[0051] The system setting module is used to set up the production system according to the optimal production process plan and the optimal equipment layout plan, so that the production system works according to the optimal production process plan and the optimal equipment layout plan.

[0052] In an implementation manner of the second aspect, performing feature analysis according to the standardized energy consumption data set to obtain a device energy consumption feature library includes:

[0053] Performing cluster analysis using a K-means clustering algorithm based on the standardized energy consumption data set to obtain a clustering result;

[0054] Dividing the devices according to the clustering results to obtain device categories;

[0055] Performing feature analysis according to the device category to obtain a device energy consumption feature vector;

[0056] A decision tree algorithm is used to construct a model based on the equipment energy consumption feature vector to obtain an equipment energy consumption feature classification model;

[0057] The energy consumption of the equipment is divided according to the equipment energy consumption characteristic classification model to obtain the equipment energy consumption mode;

[0058] The energy consumption patterns of the equipment in the energy consumption mode are collected to obtain an equipment energy consumption feature library.

[0059] In an implementation manner of the second aspect, performing association analysis according to the device energy consumption feature library to obtain a device energy consumption association network includes:

[0060] The historical data in the equipment energy consumption feature library is trained using a decision tree algorithm to obtain an equipment energy consumption decision tree model;

[0061] Perform energy consumption correlation analysis between different devices according to the equipment energy consumption decision tree model to obtain an energy consumption correlation coefficient matrix;

[0062] A network is constructed according to the energy consumption correlation coefficient matrix to obtain a device energy consumption correlation network.

[0063] In an implementation manner of the second aspect, predicting the energy consumption of the device according to the real-time energy consumption data to obtain a trend of energy consumption changes of the device includes:

[0064] Collect the real-time energy consumption data of equipment in different production environments to obtain a time series data set;

[0065] Preprocessing is performed according to the time series data to obtain smoothed data;

[0066] The smoothed data is predicted using a time series analysis algorithm to obtain a trend of equipment energy consumption changes.

[0067] In an implementable manner of the second aspect, the step of optimizing energy consumption according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process solution includes:

[0068] Perform energy consumption anomaly analysis based on the equipment energy consumption association network and the abnormal energy consumption behavior to obtain key abnormal links;

[0069] Optimize the key abnormal links to obtain multiple optimization solutions;

[0070] Input each of the plurality of optimization schemes into a pre-stored equipment energy consumption model for prediction to obtain an overall energy consumption level;

[0071] By comparing the overall energy consumption levels of various solutions, the solution with the lowest overall energy consumption level is selected as the optimal production process solution.

[0072] In an implementation manner of the second aspect, the plurality of optimization schemes refer to schemes generated by optimizing the production process, adjusting the equipment operation sequence and load distribution by using a genetic algorithm and a simulated annealing algorithm.

[0073] In an implementable manner of the second aspect, performing layout optimization according to the production equipment list and the equipment energy consumption characteristic parameters to obtain an optimal equipment layout solution includes:

[0074] Integrate the equipment energy consumption characteristic parameters of the equipment in the production equipment list to obtain an equipment energy consumption characteristic database;

[0075] Using a clustering algorithm to classify the equipment energy consumption characteristic database, a classification result of equipment energy consumption is obtained;

[0076] The equipment energy consumption classification results are input into a pre-stored directed graph model of production equipment layout, and iterative optimization is performed with minimizing total energy consumption as the optimization goal to obtain an optimal equipment layout solution.

[0077] In a third aspect, the present invention further provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the factory monitoring method based on the Internet of Things as described above is implemented.

[0078] In a fourth aspect, the present invention further provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned IoT-based factory monitoring methods.

[0079] Compared with the prior art, the present invention has the following beneficial effects:

[0080] The present invention discloses a factory monitoring method based on the Internet of Things, comprising acquiring real-time energy consumption data, a production equipment list and equipment energy consumption characteristic parameters; preprocessing according to the real-time energy consumption data to obtain a standardized energy consumption data set; performing feature analysis according to the standardized energy consumption data set to obtain an equipment energy consumption characteristic library; performing association analysis according to the equipment energy consumption characteristic library to obtain an equipment energy consumption association network; predicting equipment energy consumption according to the real-time energy consumption data to obtain an equipment energy consumption change trend; making a judgment according to the equipment energy consumption change trend and a preset energy consumption threshold; if the equipment energy consumption in the equipment energy consumption change trend is greater than the preset energy consumption threshold, then determining that the equipment energy consumption is an abnormal energy consumption behavior; performing energy consumption optimization according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process plan; performing layout optimization according to the production equipment list and the equipment energy consumption characteristic parameters to obtain an optimal equipment layout plan; and setting a production system according to the optimal production process plan and the optimal equipment layout plan so that the production system works according to the optimal production process plan and the optimal equipment layout plan. The present invention collects equipment energy consumption data in real time through sensor networks and edge computing technology, preprocesses and standardizes the data, and constructs an energy consumption analysis model. Clustering and decision tree algorithms are used to identify equipment energy consumption characteristics and correlations, and generate energy consumption correlation networks. Combined with time series analysis, energy consumption trends are monitored in real time and abnormal behaviors are judged. Based on these analysis results, the present invention uses a heuristic algorithm to generate a production process plan that minimizes energy consumption, and uses a layout optimization algorithm to design the optimal equipment layout. By deploying the optimization plan into the production system and dynamically adjusting it, the present invention achieves continuous optimization of factory equipment energy consumption and effectively reduces energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 It is a schematic flow chart of a factory monitoring method based on the Internet of Things provided by the first embodiment of the present invention;

[0082] Figure 2 It is a schematic diagram of the structure of a factory monitoring system based on the Internet of Things provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0083] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0084] Reference Figure 1 The first embodiment of the present invention provides a factory monitoring method based on the Internet of Things, comprising the following steps:

[0085] S1, obtain real-time energy consumption data, production equipment list and equipment energy consumption characteristic parameters;

[0086] S2, preprocessing the real-time energy consumption data to obtain a standardized energy consumption data set;

[0087] S3, performing feature analysis based on the standardized energy consumption data set to obtain a device energy consumption feature library;

[0088] S4, performing association analysis according to the device energy consumption feature library to obtain a device energy consumption association network;

[0089] S5, predicting the energy consumption of the equipment according to the real-time energy consumption data to obtain a change trend of the energy consumption of the equipment;

[0090] S6, judging according to the energy consumption change trend of the device and the preset energy consumption threshold; if the energy consumption of the device in the energy consumption change trend of the device is greater than the preset energy consumption threshold, judging that the energy consumption of the device is abnormal energy consumption behavior;

[0091] S7, optimizing energy consumption according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process solution;

[0092] S8, performing layout optimization according to the production equipment list and the equipment energy consumption characteristic parameters to obtain an optimal equipment layout plan;

[0093] S9, setting the production system according to the optimal production process plan and the optimal equipment layout plan, so that the production system works according to the optimal production process plan and the optimal equipment layout plan.

[0094] In step S1, real-time energy consumption data, a production equipment list and equipment energy consumption characteristic parameters are obtained.

[0095] In a specific embodiment, according to the production process and process requirements, the production equipment list and the energy consumption characteristic parameters of each equipment are obtained, including the rated power of the equipment, energy efficiency level, load characteristics, etc. For real-time energy consumption data, sensor networks and edge computing technologies are used to dynamically adjust the data collection frequency and accuracy according to the energy consumption characteristics of different equipment to ensure data integrity and real-time performance. For factory equipment, a sensor network is deployed to collect energy consumption data of the equipment in real time. The sensor type is determined according to the energy consumption characteristics of the equipment, and the collection frequency is dynamically adjusted according to the energy consumption changes. After obtaining the real-time energy consumption data collected by the sensor, it is preprocessed through the edge computing node. According to the energy consumption characteristics of the equipment, the data compression algorithm and parameters are dynamically adjusted to improve the transmission efficiency while ensuring data integrity. If the energy consumption data of a certain device changes dramatically, the collection accuracy and frequency of the sensor of the device are improved; if the energy consumption data is stable, the collection accuracy and frequency are appropriately reduced to save resources. At the edge node, an incremental learning algorithm is used to dynamically optimize the feature extraction and anomaly detection model of the energy consumption data according to the historical energy consumption data of the equipment to improve the real-time performance and accuracy of data processing.

[0096] In step S2, preprocessing is performed based on the real-time energy consumption data to obtain a standardized energy consumption data set.

[0097] In a specific embodiment, the collected multi-source heterogeneous real-time energy consumption data is preprocessed, and noise and outliers are eliminated through data cleaning and normalization methods, and the data format and unit are unified to generate a standardized energy consumption data set. The collected multi-source heterogeneous real-time energy consumption data is obtained, and the key fields of the data are extracted by using corresponding parsing methods for data from different sources and formats. The extracted energy consumption data is subjected to exploratory analysis, and the distribution characteristics of the data, including mean, variance, median, etc., are calculated by statistical methods to determine whether there are outliers. If outliers are found, outlier detection is performed using methods such as box plots, and data that exceeds the normal range is marked as outliers and removed from the data set. The energy consumption data after removing outliers is subjected to noise processing, and methods such as Kalman filtering are used to remove high-frequency noise in the data to obtain a smooth data sequence. According to the physical meaning of the energy consumption data, data of different units are converted into standard units, such as kilowatt-hours, joules, etc. The minimum-maximum normalization method is used to map energy consumption data of different numerical ranges to the [0, 1] interval, eliminate numerical size differences, and obtain a standardized energy consumption data set.

[0098] In step S3, feature analysis is performed based on the standardized energy consumption data set to obtain a device energy consumption feature library.

[0099] In the above step S3, the feature analysis is performed according to the standardized energy consumption data set to obtain a device energy consumption feature library, which specifically includes the following steps:

[0100] S31, performing cluster analysis using a K-means clustering algorithm according to the standardized energy consumption data set to obtain a clustering result;

[0101] S32, classifying the devices according to the clustering result to obtain device categories;

[0102] S33, performing feature analysis according to the device category to obtain a device energy consumption feature vector;

[0103] S34, constructing a model using a decision tree algorithm according to the device energy consumption feature vector to obtain a device energy consumption feature classification model;

[0104] S35, classifying the energy consumption of the equipment according to the equipment energy consumption characteristic classification model to obtain an equipment energy consumption mode;

[0105] S36, collecting the energy consumption rules under the energy consumption mode of the equipment to obtain the equipment energy consumption feature library. In a specific embodiment, in the above steps S31 to S36, the implementation process includes: using the K-means clustering algorithm to perform cluster analysis on the standardized energy consumption data set, and dividing the equipment into different categories according to the clustering results, each category represents an energy consumption mode; the K-means clustering algorithm is a commonly used unsupervised learning method, which is used to divide the data set into K different clusters, each cluster consists of a group of similar objects, and the clusters are quite different. For each equipment category, the time series characteristics of its energy consumption data are analyzed, and the statistical characteristics of the energy consumption data, such as mean, variance, peak value, etc., are extracted to construct the equipment energy consumption feature vector. The decision tree algorithm is used to classify the equipment energy consumption feature vector, and an equipment energy consumption feature classification model is generated to determine which energy consumption mode the new equipment belongs to. According to the judgment result of the equipment energy consumption feature classification model, the equipment energy consumption rules under the corresponding energy consumption mode are obtained, such as energy consumption peak period, energy consumption periodicity, etc., to form a knowledge base of equipment energy consumption rules. The device energy consumption feature vector and the corresponding energy consumption law are combined to generate a device energy consumption feature-law mapping table to obtain a device energy consumption feature library.

[0106] For example, taking a steel plant as an example, the original energy consumption data of equipment such as blast furnaces and converters will have outliers and missing values. The box plot method can be used to identify outliers, such as data points where the blast furnace consumes more than 7,000 kWh per hour. For missing values, time series interpolation can be used to fill them. After cleaning and standardization, a reliable energy consumption data set is obtained, laying the foundation for subsequent analysis. The K-means clustering algorithm can effectively divide the energy consumption pattern of equipment. Assuming that the energy consumption data of 10 blast furnaces are clustered, three categories can be obtained: low energy consumption (average 3,000 kWh / hour), medium energy consumption (5,000 kWh / hour) and high energy consumption (7,000 kWh / hour). This classification helps to identify energy efficiency differences and provide a basis for targeted optimization. Time series feature extraction is an important means to understand the energy consumption pattern of equipment. Taking a medium-energy-consuming blast furnace as an example, the statistical features of its 24-hour energy consumption curve, such as the mean (5000 kWh), standard deviation (500 kWh), and peak value (6000 kWh, usually occurring during peak production), can be calculated. These features constitute the energy consumption feature vector of the equipment, which comprehensively describes its energy consumption behavior. The decision tree algorithm performs well in classifying equipment energy consumption patterns. By training the decision tree model with the above feature vector, the energy consumption category of new equipment can be quickly determined. For example, if the average daily energy consumption of a new blast furnace is 5200 kWh and the peak is 6100 kWh, the model will classify it as a medium-energy-consuming category. This automatic classification method improves the efficiency of energy consumption management. The establishment of an energy consumption law knowledge base is crucial to optimizing production. By analyzing the energy consumption data of a medium-energy-consuming blast furnace, the following rules can be found: the peak energy consumption occurs between 14:00 and 16:00 every day, and the periodicity is reflected in the higher energy consumption on weekdays than on weekends. These rules provide a basis for formulating strategies such as staggered production and load balancing. The equipment energy consumption feature-law mapping table is the core of the equipment energy consumption feature library. Taking a medium-energy-consuming blast furnace as an example, its feature vector (average daily energy consumption of 5,000 kWh, peak of 6,000 kWh, etc.) is mapped with the energy consumption law (peak at 14:00-16:00, higher on weekdays than on weekends). This mapping relationship enables energy managers to quickly understand the equipment energy consumption characteristics, predict energy consumption trends, and thus formulate accurate energy-saving strategies. Through this series of steps, steel mills can establish a comprehensive equipment energy consumption feature library.

[0107] In step S4, correlation analysis is performed according to the device energy consumption feature library to obtain a device energy consumption correlation network, which specifically includes the following steps:

[0108] S41, training the historical data in the equipment energy consumption feature library using a decision tree algorithm to obtain an equipment energy consumption decision tree model;

[0109] S42, performing energy consumption correlation analysis between different devices according to the device energy consumption decision tree model to obtain an energy consumption correlation coefficient matrix;

[0110] S43, constructing a network according to the energy consumption correlation coefficient matrix to obtain a device energy consumption correlation network.

[0111] It should be noted that in the above steps S41 to S43, the specific implementation process includes: using the decision tree algorithm to train the equipment energy consumption feature vector according to the historical data in the equipment energy consumption feature library to generate an equipment energy consumption decision tree model. Through the equipment energy consumption decision tree model, the energy consumption correlation between different devices is analyzed, and the energy consumption correlation coefficient matrix between devices is calculated. According to the energy consumption correlation coefficient matrix between devices, a device energy consumption association network is constructed, in which the nodes in the network represent the devices, and the edges represent the energy consumption correlation between devices. In the equipment energy consumption association network, key nodes with higher energy consumption values ​​are identified and determined as high-energy consumption devices. For the identified high-energy consumption devices, their topological structure in the association network is analyzed, and the upstream and downstream devices directly connected to them are determined to be their main influencing factors.

[0112] For example, taking a blast furnace in a steel plant as an example, its feature vector may include average daily energy consumption, peak energy consumption, standard deviation of energy consumption, etc. By analyzing historical data, a feature vector of a blast furnace can be obtained:

[0113] [5000,6000,500], respectively, represent the average daily energy consumption of 5000 kWh, the peak energy consumption of 6000 kWh, and the standard deviation of energy consumption of 500 kWh. This feature extraction method can comprehensively characterize the energy consumption behavior of the equipment. The decision tree algorithm performs well in the classification of energy consumption patterns. The energy consumption category of new equipment can be quickly determined by training the decision tree model with the extracted feature vectors. For example, if the feature vector of a new blast furnace is [5200,6100,550], the decision tree model will classify it as a medium energy consumption category. This automatic classification method improves the efficiency of energy consumption management and helps to identify abnormal energy consumption patterns in a timely manner. The energy consumption correlation coefficient matrix reflects the energy consumption correlation between different equipment. Assume that the three types of equipment, blast furnace, converter and rolling mill, are analyzed, and the correlation coefficient matrix is ​​as follows: blast furnace 1.0 0.8 0.5 converter 0.8 1.0 0.7 rolling mill 0.5 0.7 1.0 This matrix shows that the energy consumption correlation between blast furnace and converter is the strongest (correlation coefficient 0.8), while the correlation between blast furnace and rolling mill is relatively weak (correlation coefficient 0.5). Based on the correlation coefficient matrix, an equipment energy consumption correlation network can be constructed. In this network, blast furnace, converter and rolling mill are respectively used as nodes, and the edge weights between nodes are the correlation coefficients.

[0114] In step S5, the energy consumption of the equipment is predicted based on the real-time energy consumption data to obtain the energy consumption change trend of the equipment.

[0115] In the above step S5, predicting the energy consumption of the equipment according to the real-time energy consumption data to obtain the energy consumption change trend of the equipment specifically includes the following steps:

[0116] S51, collecting the real-time energy consumption data of equipment in different production environments to obtain a time series data set;

[0117] S52, performing preprocessing according to the time series data to obtain smoothed data;

[0118] S53, using a time series analysis algorithm to predict the smoothed data to obtain a trend of equipment energy consumption changes.

[0119] In one possible implementation, the above steps S51 to S53 include: obtaining real-time energy consumption data of equipment in the production environment to form a time series data set. Preprocessing the time series data to remove missing values ​​and outliers and smooth data fluctuations. Using a time series analysis algorithm such as an ARIMA model, trend forecasting is performed on the equipment energy consumption data to obtain a predicted energy consumption change trend.

[0120] For example, in a steel plant, smart meters can be installed on key equipment such as blast furnaces and converters to record electricity consumption every minute. These data form a time series, such as [5200, 5180, 5220, ...] kWh for a blast furnace within 24 hours. This high-frequency collection can capture subtle changes in equipment energy consumption and provide rich information for subsequent analysis. Data preprocessing is crucial to ensure the quality of analysis. First, missing values ​​are processed, such as data gaps caused by sensor failures, which can be filled using linear interpolation. For example, if the data at 10:00 and 12:00 are 5000 kWh and 5200 kWh respectively, and the data at 11:00 is missing, it can be estimated as 5100 kWh. Second, outliers are eliminated, such as a sudden drop in energy consumption due to sudden equipment failure. The 3σ principle can be used to treat data that exceeds three standard deviations from the mean as abnormal. Finally, the moving average method is used to smooth the data to reduce the impact of random fluctuations. These steps can significantly improve data quality and lay the foundation for subsequent analysis. The ARIMA model is a powerful time series forecasting tool. It combines three components: autoregression (AR), differencing (I), and moving average (MA). Before applying the ARIMA model, you need to determine the order of the model (p, d, q). You can make a preliminary judgment by observing the autocorrelation function (ACF) and partial autocorrelation function (PACF) graphs. For example, if the ACF decays exponentially and the PACF is truncated after lag 1, the ARIMA (1, 0, 0) model is suitable. Using the determined model, the energy consumption for the next 24 hours can be predicted, and a forecast sequence such as [5150, 5180, 5200, ...] kWh can be obtained.

[0121] In step S6, a judgment is made based on the device energy consumption change trend and a preset energy consumption threshold; if the device energy consumption in the device energy consumption change trend is greater than the preset energy consumption threshold, the device energy consumption is determined to be abnormal energy consumption behavior.

[0122] For example, the normal energy consumption range of a blast furnace is set to 4800-5500 kWh / h. If the forecast shows that the energy consumption will continue to exceed 5500 kWh / h in the next 4 hours, the system will trigger an early warning. This early warning mechanism can detect and determine in advance that the energy consumption of the equipment is abnormal, giving managers enough time to take preventive measures.

[0123] In step S7, energy consumption is optimized according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process solution.

[0124] In the above step S7, energy consumption optimization is performed according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process solution, which specifically includes the following steps:

[0125] S71, performing energy consumption anomaly analysis according to the device energy consumption association network and the abnormal energy consumption behavior to obtain key abnormal links;

[0126] S72, optimizing according to the key abnormal links to obtain multiple optimization solutions;

[0127] S73, inputting each of the multiple optimization solutions into a pre-stored equipment energy consumption model for prediction to obtain an overall energy consumption level;

[0128] S74, comparing the overall energy consumption levels of the various solutions, and selecting the solution with the lowest overall energy consumption level as the optimal production process solution.

[0129] It should be noted that in the above steps S71 to S74, the specific implementation process includes: using an association rule mining algorithm to analyze abnormal energy consumption events on the equipment energy consumption association network, obtain the correlation of each link in the production process, and obtain the key production links and equipment combinations that cause abnormal energy consumption. For key abnormal links, optimize the production process, adjust the equipment operation sequence and load distribution, and generate multiple optimization schemes through optimization search algorithms such as genetic algorithms, simulated annealing algorithms, etc. According to the equipment energy consumption model, predict the overall energy consumption level of each optimization scheme, and select the scheme with minimized energy consumption as the optimal production process. Convert the optimal production process into equipment control instructions, send them to the production execution system, and optimize the equipment operation sequence and load through automated control. Continuously monitor the optimized production energy consumption data. If the optimization effect is not ideal, return to step 72 and re-trigger the production process optimization until the energy consumption is minimized.

[0130] For example, in a steel plant, smart meters can be installed on key equipment such as blast furnaces and converters to record electricity consumption every minute. These high-frequency data can capture subtle changes in equipment energy consumption and provide rich information for subsequent analysis. Building an energy consumption model for each device is a key step. Taking the blast furnace as an example, a multivariate regression model that considers factors such as temperature, pressure, and raw material ratio can be established by analyzing historical data. This model can help understand the energy consumption performance under normal operating conditions and identify the characteristics of abnormal energy consumption behavior. For example, the model will show that under normal circumstances, the energy consumption of a blast furnace should fluctuate between 4800 and 5500 kWh per hour. Real-time monitoring is the key to timely detecting anomalies. Suppose one day the energy consumption of the blast furnace suddenly soars to 6000 kWh / hour, far exceeding the normal range. The system will immediately trigger an abnormal warning and record the event. This rapid response mechanism can help managers promptly discover and deal with potential problems, such as abnormal raw material quality or equipment failure. Association rule mining algorithms can help deeply understand the root causes of abnormal energy consumption. For example, through analysis, it is found that abnormal blast furnace energy consumption is highly correlated with factors such as insufficient upstream raw material preheating and reduced downstream iron tapping frequency. This analysis can not only point out the direct cause, but also reveal potential problem points in the entire production process. Optimizing the production process is an effective means to reduce energy consumption. Taking genetic algorithms as an example, various parameters in the production process (such as raw material ratio, blast temperature, etc.) can be encoded as "genes" and these parameter combinations can be continuously optimized by simulating the evolutionary process. For example, the algorithm will find that increasing the blast temperature by 50 degrees and adjusting the raw material ratio can reduce the blast furnace energy consumption by 5%. Predicting the effect of the optimization plan is the key to selecting the best plan. Using the energy consumption model established earlier, each optimization plan can be simulated to predict its overall energy consumption level. Assuming there are three plans, the predicted energy consumption is 4900, 4850 and 4800 kWh / h respectively, and the third plan will be selected as the optimal solution. Assume that after implementing the optimization plan, it is found that the actual energy consumption reduction is not as expected, only 2%. At this time, the system will automatically trigger a new round of optimization process, considering more factors or using different optimization algorithms until the expected energy saving effect is achieved.

[0131] In step S8, layout optimization is performed based on the production equipment list and the equipment energy consumption characteristic parameters to obtain an optimal equipment layout plan.

[0132] In the above step S8, the layout optimization is performed according to the production equipment list and the equipment energy consumption characteristic parameters to obtain the optimal equipment layout plan, which specifically includes the following steps:

[0133] S81, integrating the equipment energy consumption characteristic parameters of the equipment in the production equipment list to obtain an equipment energy consumption characteristic database;

[0134] S82, performing classification using a clustering algorithm according to the device energy consumption characteristic database to obtain a device energy consumption classification result;

[0135] S83, inputting the equipment energy consumption classification result into a pre-stored directed graph model of production equipment layout to perform iterative optimization with minimizing total energy consumption as the optimization goal, and obtaining an optimal equipment layout solution.

[0136] In a specific embodiment, the implementation process of the above steps S81 to S83 includes: according to the production process and process requirements, obtaining the production equipment list and the energy consumption characteristic parameters of each equipment, including the equipment rated power, energy efficiency level, load characteristics, etc., to form an equipment energy consumption characteristic database. The equipment energy consumption characteristic data is analyzed by a clustering algorithm, and the equipment is divided into several categories according to parameters such as equipment energy consumption level and load characteristics to obtain the equipment energy consumption classification results. According to the production process, the material flow between each process and the connection relationship between the equipment are determined, and a directed graph model of the production equipment layout is constructed, and the equipment energy consumption classification results are used as the attributes of the nodes in the graph. The equipment layout is optimized and solved by a genetic algorithm, with minimizing the total energy consumption as the optimization goal, comprehensively considering factors such as the distance between equipment and the length of pipelines, and iteratively searching for the optimal layout plan through operations such as selection, crossover, and mutation. In the optimization process, an energy transmission loss model is introduced, and the transmission distance and loss of energy such as electricity and heat between each equipment are calculated according to the equipment layout plan, and it is used as one of the constraints for layout optimization. Through multiple iterative optimizations, the solution with the lowest total energy consumption and transmission loss is selected from the candidate layout solutions as the final device layout optimization result.

[0137] S9, setting the production system according to the optimal production process plan and the optimal equipment layout plan, so that the production system works according to the optimal production process plan and the optimal equipment layout plan.

[0138] In summary, the present invention discloses a factory monitoring method based on the Internet of Things, including obtaining real-time energy consumption data, a production equipment list and equipment energy consumption characteristic parameters; preprocessing according to the real-time energy consumption data to obtain a standardized energy consumption data set; performing feature analysis according to the standardized energy consumption data set to obtain an equipment energy consumption feature library; performing association analysis according to the equipment energy consumption feature library to obtain an equipment energy consumption association network; predicting equipment energy consumption according to the real-time energy consumption data to obtain an equipment energy consumption change trend; making a judgment according to the equipment energy consumption change trend and a preset energy consumption threshold; if the equipment energy consumption in the equipment energy consumption change trend is greater than the preset energy consumption threshold, then determining that the equipment energy consumption is an abnormal energy consumption behavior; performing energy consumption optimization according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process plan; performing layout optimization according to the production equipment list and the equipment energy consumption characteristic parameters to obtain an optimal equipment layout plan; setting a production system according to the optimal production process plan and the optimal equipment layout plan so that the production system works according to the optimal production process plan and the optimal equipment layout plan. The present invention collects equipment energy consumption data in real time through sensor networks and edge computing technology, preprocesses and standardizes the data, and constructs an energy consumption analysis model. Clustering and decision tree algorithms are used to identify equipment energy consumption characteristics and correlations, and generate energy consumption correlation networks. Combined with time series analysis, energy consumption trends are monitored in real time and abnormal behaviors are judged. Based on these analysis results, the present invention uses a heuristic algorithm to generate a production process plan that minimizes energy consumption, and uses a layout optimization algorithm to design the optimal equipment layout. By deploying the optimization plan into the production system and dynamically adjusting it, the present invention achieves continuous optimization of factory equipment energy consumption and effectively reduces energy consumption.

[0139] Reference Figure 2 The second embodiment of the present invention provides a factory monitoring system based on the Internet of Things, including:

[0140] Data acquisition module 101, used to acquire real-time energy consumption data, production equipment list and equipment energy consumption characteristic parameters;

[0141] A data standardization module 102, configured to perform preprocessing on the real-time energy consumption data to obtain a standardized energy consumption data set;

[0142] A feature analysis module 103 is used to perform feature analysis based on the standardized energy consumption data set to obtain a device energy consumption feature library;

[0143] A feature association module 104 is used to perform association analysis based on the device energy consumption feature library to obtain a device energy consumption association network;

[0144] The energy consumption prediction module 105 is used to predict the future energy consumption of the equipment according to the real-time energy consumption data to obtain the energy consumption change trend of the equipment;

[0145] The abnormality judgment module 106 is used to judge according to the energy consumption change trend of the device and the preset energy consumption threshold; if the energy consumption of the device in the energy consumption change trend of the device is greater than the preset energy consumption threshold, the energy consumption of the device is judged to be abnormal energy consumption behavior;

[0146] The production process optimization module 107 is used to optimize energy consumption according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process solution;

[0147] The equipment layout optimization module 108 is used to optimize the layout according to the production equipment list and the equipment energy consumption characteristic parameters to obtain the optimal equipment layout plan;

[0148] The system setting module 109 is used to set the production system according to the optimal production process plan and the optimal equipment layout plan, so that the production system works according to the optimal production process plan and the optimal equipment layout plan.

[0149] It should be noted that the IoT-based factory monitoring system provided in an embodiment of the present invention is used to execute all process steps of the IoT-based factory monitoring method in the above embodiment. The working principles and beneficial effects of the two correspond one to one, and thus will not be described in detail.

[0150] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a factory monitoring program based on the Internet of Things. When the processor executes the computer program, the steps in the above-mentioned factory monitoring method embodiments based on the Internet of Things are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the data acquisition module.

[0151] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the electronic device.

[0152] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. The electronic device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0153] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, and uses various interfaces and lines to connect various parts of the entire electronic device.

[0154] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0155] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0156] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0157] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A factory monitoring method based on the Internet of Things, characterized in that: Executed by a computer, including: Obtain real-time energy consumption data, production equipment list and equipment energy consumption characteristic parameters; Preprocessing is performed according to the real-time energy consumption data to obtain a standardized energy consumption data set; Perform feature analysis based on the standardized energy consumption data set to obtain a device energy consumption feature library; Performing correlation analysis based on the equipment energy consumption feature library to obtain an equipment energy consumption correlation network; Predicting the energy consumption of the equipment according to the real-time energy consumption data to obtain the energy consumption change trend of the equipment; A judgment is made based on the energy consumption change trend of the device and a preset energy consumption threshold; if the energy consumption of the device in the energy consumption change trend of the device is greater than the preset energy consumption threshold, the energy consumption of the device is determined to be abnormal energy consumption behavior; Optimize energy consumption according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process solution; Perform layout optimization according to the production equipment list and the equipment energy consumption characteristic parameters to obtain an optimal equipment layout plan; The production system is set up according to the optimal production process plan and the optimal equipment layout plan so that the production system works according to the optimal production process plan and the optimal equipment layout plan.

2. The factory monitoring method based on the Internet of Things according to claim 1, characterized in that: The step of performing feature analysis according to the standardized energy consumption data set to obtain a device energy consumption feature library includes: Performing cluster analysis using a K-means clustering algorithm based on the standardized energy consumption data set to obtain a clustering result; Dividing the devices according to the clustering results to obtain device categories; Performing feature analysis according to the device category to obtain a device energy consumption feature vector; A decision tree algorithm is used to construct a model based on the equipment energy consumption feature vector to obtain an equipment energy consumption feature classification model; The energy consumption of the equipment is divided according to the equipment energy consumption characteristic classification model to obtain the equipment energy consumption mode; The energy consumption patterns of the equipment in the energy consumption mode are collected to obtain an equipment energy consumption feature library.

3. The factory monitoring method based on the Internet of Things according to claim 1 is characterized in that: The performing association analysis according to the device energy consumption feature library to obtain a device energy consumption association network includes: The historical data in the equipment energy consumption feature library is trained using a decision tree algorithm to obtain an equipment energy consumption decision tree model; Perform energy consumption correlation analysis between different devices according to the equipment energy consumption decision tree model to obtain an energy consumption correlation coefficient matrix; A network is constructed according to the energy consumption correlation coefficient matrix to obtain a device energy consumption correlation network.

4. The factory monitoring method based on the Internet of Things according to claim 1 is characterized in that: The predicting of the equipment energy consumption according to the real-time energy consumption data to obtain the equipment energy consumption change trend includes: Collect the real-time energy consumption data of equipment in different production environments to obtain a time series data set; Preprocessing is performed according to the time series data to obtain smoothed data; The smoothed data is predicted using a time series analysis algorithm to obtain a trend of equipment energy consumption changes.

5. The factory monitoring method based on the Internet of Things according to claim 1 is characterized in that: The step of optimizing energy consumption according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process solution includes: Perform energy consumption anomaly analysis based on the equipment energy consumption association network and the abnormal energy consumption behavior to obtain key abnormal links; Optimize the key abnormal links to obtain multiple optimization solutions; Input each of the plurality of optimization schemes into a pre-stored equipment energy consumption model for prediction to obtain an overall energy consumption level; By comparing the overall energy consumption levels of various solutions, the solution with the lowest overall energy consumption level is selected as the optimal production process solution.

6. The factory monitoring method based on the Internet of Things according to claim 5 is characterized in that: The multiple optimization schemes refer to schemes generated by optimizing the production process, adjusting the equipment operation sequence and load distribution by using a genetic algorithm and a simulated annealing algorithm.

7. The factory monitoring method based on the Internet of Things according to claim 1 is characterized in that: The optimizing the layout according to the production equipment list and the equipment energy consumption characteristic parameters to obtain the optimal equipment layout plan includes: Integrate the equipment energy consumption characteristic parameters of the equipment in the production equipment list to obtain an equipment energy consumption characteristic database; Using a clustering algorithm to classify the equipment energy consumption characteristic database, a classification result of equipment energy consumption is obtained; The equipment energy consumption classification results are input into a pre-stored directed graph model of production equipment layout, and iterative optimization is performed with minimizing total energy consumption as the optimization goal to obtain an optimal equipment layout solution.

8. A factory monitoring system based on the Internet of Things, characterized in that: include: Data acquisition module, used to obtain real-time energy consumption data, production equipment list and equipment energy consumption characteristic parameters; A data standardization module, used for preprocessing the real-time energy consumption data to obtain a standardized energy consumption data set; A feature analysis module, used to perform feature analysis based on the standardized energy consumption data set to obtain a device energy consumption feature library; A feature association module, used to perform association analysis based on the device energy consumption feature library to obtain a device energy consumption association network; An energy consumption prediction module is used to predict the future energy consumption of the equipment based on the real-time energy consumption data to obtain the energy consumption change trend of the equipment; An abnormality judgment module is used to judge according to the energy consumption change trend of the device and the preset energy consumption threshold; if the energy consumption of the device in the energy consumption change trend of the device is greater than the preset energy consumption threshold, the energy consumption of the device is judged to be abnormal energy consumption behavior; A production process optimization module, used to optimize energy consumption according to the equipment energy consumption association network and the abnormal energy consumption behavior to obtain an optimal production process solution; An equipment layout optimization module, used to optimize the layout according to the production equipment list and the equipment energy consumption characteristic parameters to obtain an optimal equipment layout plan; The system setting module is used to set up the production system according to the optimal production process plan and the optimal equipment layout plan, so that the production system works according to the optimal production process plan and the optimal equipment layout plan.

9. An electronic device, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the factory monitoring method based on the Internet of Things as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the factory monitoring method based on the Internet of Things as described in any one of claims 1 to 7.

Images