Energy and carbon management method and system based on production process data, medium, terminal and program product

Abstract

The invention provides an energy and carbon management method and system based on production process data, a medium, a terminal and a program product, and the method comprises the steps: collecting the production process data generated in the operation process of the process industry; preprocessing the production process data to convert the production process data into a data format suitable for a deep neural network model; inputting the format-converted production process data into a deep neural network model for training to obtain an energy carbon emission prediction model; and deploying the energy carbon emission prediction model so as to predict an energy carbon value emitted in real time. According to the method, the energy carbon value can be accurately and efficiently predicted, the energy carbon value can be optimized, and the optimal energy conservation and emission reduction effects are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of energy-carbon management, and in particular to energy-carbon management methods, systems, media, terminals and program products based on production process data. Background Art

[0002] In the industrial production process, accurate prediction and control of carbon emissions is the key to achieving energy conservation and emission reduction and achieving green production goals. Traditional carbon emission monitoring methods often rely on regular manual measurements and empirical estimates, which are not only time-consuming and labor-intensive, but also have limited accuracy. They often cannot effectively predict energy consumption or carbon emissions, and it is even more difficult to efficiently control the process flow to achieve the purpose of efficient prediction-optimization. With the development of big data and artificial intelligence technology, especially the mature application of machine learning algorithms, new solutions have been provided for real-time monitoring and prediction of carbon emissions.

[0003] Machine learning is a technology that allows computers to "learn" and "experience" through data and make predictions or decisions without explicit programming. It can use statistical principles and algorithmic models to automatically extract patterns and laws from large amounts of historical data to predict future data.

[0004] However, with the continuous advancement of science and industrial technology, existing technologies are unable to meet the predicted needs of energy consumption and carbon emissions in industrial production, and are unable to form a complete energy-carbon management model for process industries, resulting in the inability to optimize energy consumption or carbon emissions in process industries.

[0005] Therefore, it is necessary to provide an energy-carbon management method, system, medium, terminal and program product based on production process data to solve the above-mentioned problems existing in the prior art. Summary of the invention

[0006] In view of the shortcomings of the prior art mentioned above, the purpose of this application is to provide an energy-carbon management method, system, medium, terminal and program product based on production process data, so as to solve the technical problem that the prior art cannot form a complete energy-carbon management model for the process industry.

[0007] To achieve the above objectives and other related objectives, the first aspect of the present application provides an energy-carbon management method based on production process data, comprising:

[0008] Collect production process data generated by process industries during operations;

[0009] Preprocessing the production process data to convert it into a data format suitable for a deep neural network model; inputting the format-converted production process data into the deep neural network model for training to obtain an energy carbon emission prediction model;

[0010] The energy carbon emission prediction model is deployed to predict the energy carbon value of real-time emissions.

[0011] In some embodiments of the first aspect of the present application, the production process data generated by the process industry during the operation process is collected, which includes: collecting corresponding production process data from a variety of process industry equipment based on different communication protocols through a pre-deployed edge gateway device; the edge gateway device is integrated with drivers of various types of Internet of Things protocols.

[0012] In some embodiments of the first aspect of the present application, the production process data collected by the edge gateway device is sent to an edge computing platform; wherein: a data processing framework for processing real-time data streams is implemented on the edge computing platform, and the data processing framework includes an Apache Flink framework or a Spark Streaming framework; based on a data caching mechanism and a local storage mechanism, the received production process data is cached.

[0013] In some embodiments of the first aspect of the present application, the method of preprocessing the production process data includes:

[0014] Downsample the production process data to make each category of production process data have the same sampling frequency and align the time points;

[0015] Perform data cleaning operations on the downsampled and aligned production process data;

[0016] The cleaned production process data is standardized to make it suitable for training deep neural network models.

[0017] In some embodiments of the first aspect of the present application, the production process data includes a variety of energy consumption data and process parameter data generated by the process industry during the operation process; according to the nature and source of the energy, the various energy consumption data are converted into corresponding carbon emission data; the energy consumption data, process parameter data and carbon emission data are downsampled, aligned, cleaned and standardized to make them suitable for the training of a deep neural network model.

[0018] In some embodiments of the first aspect of the present application, the method further includes performing any one or more of the following interpretability configurations on the deep neural network:

[0019] A model component with certain explanatory power is configured in the neural network; the model component includes a decision tree or a linear model;

[0020] Use SHAP values ​​or LIME to evaluate and explain the importance of each feature in the model;

[0021] Use visualization techniques to demonstrate the model's decision-making process and feature impact.

[0022] In some embodiments of the first aspect of the present application, the method also includes: dividing the production process data into a training set, a validation set and a test set in a certain ratio, the training set is used to train the deep neural network model so that the model learns rules and patterns from the training set; the validation set is used for tuning and hyperparameter selection of the deep neural network model to optimize model performance; the test set is used to evaluate the generalization ability of the deep neural network model.

[0023] In some embodiments of the first aspect of the present application, the method further includes: optimizing the energy-to-carbon value predicted by the energy-to-carbon emission prediction model using a genetic algorithm to obtain a local optimal solution.

[0024] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides an energy-carbon management system based on production process data, including:

[0025] Data collection module, used to collect production process data generated by process industries during operations;

[0026] A model building module is used to pre-process the production process data to convert it into a data format suitable for a deep neural network model; input the format-converted production process data into the deep neural network model for training to obtain an energy carbon emission prediction model;

[0027] The model deployment module is used to deploy the energy carbon emission prediction model to predict the energy carbon value of real-time emissions.

[0028] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the above-mentioned method when executed by a processor.

[0029] To achieve the above-mentioned purpose and other related purposes, the fourth aspect of the present application provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer implements the above-mentioned method.

[0030] To achieve the above-mentioned purpose and other related purposes, the fifth aspect of the present application provides an electronic terminal, including a memory, a processor and a computer program stored in the memory; the processor executes the computer program to implement the above-mentioned method.

[0031] As described above, the energy-carbon management method, system, medium, terminal and program product based on production process data of the present application have the following beneficial effects:

[0032] By constructing an energy-carbon emission prediction model and deploying the trained energy-carbon emission prediction model, we can achieve efficient prediction of the real-time emission energy-carbon value, provide the setting range of key parameters, and combine real-time production process data to timely adjust process parameters or operating strategies to optimize energy consumption and carbon emission values, thereby achieving the best energy-saving and emission reduction effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 Shown is a flow chart of an energy-carbon management method based on production process data in one embodiment of the present application.

[0034] Figure 2 Shown is a schematic diagram of the transmission of production process data collected in a process industry in one embodiment of the present application.

[0035] Figure 3 Shown is a schematic diagram of an edge gateway device in one embodiment of the present application.

[0036] Figure 4 Shown is a schematic diagram of production process data analysis in one embodiment of the present application.

[0037] Figure 5 Shown is a schematic diagram of the structure of an energy-carbon management system based on production process data in one embodiment of the present application.

[0038] Figure 6 Shown is a schematic diagram of the structure of an electronic terminal in one embodiment of the present application. DETAILED DESCRIPTION

[0039] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0040] In the embodiments of the present application, words such as "first" and "second" are used to distinguish the same or similar items with substantially the same functions and effects. For example, the first XX and the second XX are only used to distinguish different XXs, and do not limit their order. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0041] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" represent examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0042] In the embodiments of the present application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0043] Before further describing the present invention in detail, the nouns and terms involved in the embodiments of the present invention are explained. The nouns and terms involved in the embodiments of the present invention are applicable to the following interpretations:

[0044] <1> Industrial communication protocol: refers to a series of standardized rules and specifications for data exchange and communication between devices in industrial automation and control systems. These protocols define the format of data, transmission method, error detection and correction mechanism, and how devices identify and communicate with each other on the network.

[0045] <2> Internet of Things (IoT) protocols: refers to a series of standardized rules and specifications for data exchange and communication between devices or between devices and servers in the IoT environment. These protocols ensure interoperability and compatibility between different manufacturers, different types of devices, and different networks.

[0046] It is worth emphasizing that the energy and carbon management methods, systems, media, terminals and program products based on production process data provided by this application are applied in the process industry, which covers a wide range of fields, including but not limited to oil and gas, chemicals, pharmaceuticals, food, etc. Compared with ordinary conventional industries, the characteristic of the process industry is that its production process is continuous rather than intermittent. Therefore, the production line of the process industry often requires a high degree of automation and precise control to ensure the stability of the production process and the consistency of product quality.

[0047] Process industries are vital to the global economy. They are the main consumers of raw materials and energy, and are also promoters of innovative technologies and processes. With the increasing awareness of environmental protection, process industries are gradually transforming in the direction of greening and low-carbonization to reduce the impact on the environment. However, at present, the existing technology cannot meet the energy-carbon management needs in the process industry, that is, it is impossible to accurately and efficiently predict the energy-carbon value, nor can it optimize the energy-carbon value, so as to achieve good energy-saving and emission reduction effects. Therefore, the present application provides an energy-carbon management method, system, medium, terminal and program product based on production process data, which can accurately and efficiently predict the energy-carbon value, and at the same time optimize the energy-carbon value, so as to achieve the best energy-saving and emission reduction effect.

[0048] To facilitate understanding of the embodiments of the present application, first Figure 1 Detailed description. Figure 1 The flowchart of an energy-carbon management method based on production process data in an embodiment of the present invention is shown. The energy-carbon management method based on production process data in this embodiment mainly includes the following steps:

[0049] Step S11: Collecting production process data generated by the process industry during operation.

[0050] In one embodiment, collecting production process data generated by process industries during operation includes: collecting corresponding production process data from a variety of process industry equipment based on different communication protocols through a pre-deployed edge gateway device; the edge gateway device is integrated with drivers for various types of Internet of Things protocols.

[0051] In one embodiment, the production process data collected by the edge gateway device is sent to the edge computing platform; wherein, a data processing framework for processing real-time data streams is implemented on the edge computing platform, and the data processing framework includes an Apache Flink framework or a Spark Streaming framework; based on a data caching mechanism and a local storage mechanism, the received production process data is cached.

[0052] It should be understood that an edge gateway device is an Industrial Internet of Things (IIoT) hardware device that is located at the edge of an industrial site or network, close to the data source. After various sensors and industrial equipment collect raw data, the edge gateway device collects production process data from various sensors and industrial equipment. At the same time, the edge gateway device supports a variety of industrial communication protocols and can convert the collected data into a unified format for further processing and analysis.

[0053] It should also be understood that an edge computing platform is a computing architecture that places computing, storage, and network services close to the data source, typically at the edge of the network, rather than in a remote central data center. This architecture is designed to reduce latency, improve response speed, save bandwidth, and enhance data processing capabilities.

[0054] like Figure 2 As shown, illustratively, production process data, such as energy consumption data, safety monitoring data, and smart meter data, are collected by a collection instrument 21, sent to an edge gateway device 22, and then sent to an edge computing platform 23 through a network. It should be emphasized that Figure 2 The schematic diagram shown is for reference only and can be configured according to actual usage.

[0055] like Figure 3 As shown, the edge gateway device 22 is integrated with drivers for various types of IoT protocols, so that the edge gateway device can integrate data collected from devices using different IoT protocols into a unified data stream for easy analysis and processing. Exemplarily, the edge gateway device 22 is integrated with a driver 221 based on a serial communication protocol, a driver 222 based on a cross-platform industrial communication protocol, and a driver 223 based on an Ethernet industrial communication protocol. It should be understood that the serial communication protocol (Modbus) allows devices to exchange data through serial ports; the cross-platform industrial communication protocol (Open Platform Communications Unified Architecture, OPC UA) provides real-time data exchange capabilities and is suitable for industrial control systems that require fast response; the Ethernet industrial communication protocol (EtherNet / IP) aims to provide a standardized method to achieve communication and data exchange between devices, using a standard Ethernet network, allowing industrial communications to be deployed on existing network infrastructure.

[0056] Compared with conventional industries, process industries have very high requirements for real-time performance, data integrity, and system stability. If data cannot be transmitted in real time or the transmitted data is incomplete, it will be difficult for the system to make judgments and adjustments to the real-time data in industrial production, resulting in the inability to optimize production process parameters and reduced production efficiency. Therefore, by pre-deploying edge gateway devices, real-time data transmission can be achieved, the response speed can be improved, and the requirements of process industries for high-performance communication and real-time data transmission can be met.

[0057] In view of the continuity of process industries, a data processing framework is implemented on the edge computing platform to process real-time data and monitor industrial process data in real time. The specific data processing framework adopts the Apache Flink framework or the Spark Streaming framework. Furthermore, the Apache Flink framework is an open source stream processing framework for real-time data processing and complex event processing. The Spark Streaming framework provides an effective method for real-time data processing in the Spark ecosystem by splitting the data stream into small batches for processing. It combines the reliability of batch processing and the real-time nature of stream processing, making real-time big data processing more feasible.

[0058] In the process industry, the continuity and real-time nature of the production process require that the data processing framework be able to quickly and reliably process a large amount of data. By implementing data caching and local storage mechanisms, the received production process data is cached, which can improve the response speed, reduce the delay in data processing, and enhance the level of intelligence. For example, in a reactor in a chemical plant, a temperature sensor is used to monitor the temperature of the reactor. If the data caching and local storage mechanisms are not used, then each time the sensor reads the data, it must wait for the data to be transmitted to the control system through the network before it can be processed and responded to. This may cause delays in data processing, affecting the real-time control of the reactor temperature, and any network fluctuations will cause the response speed of the production process to slow down, increasing the risk of production. However, in this embodiment, the data caching mechanism and local storage mechanism are implemented on the edge gateway, and the data collected by the sensor will be cached locally. The edge gateway can respond quickly, such as adjusting the heating or cooling system, and reduce the delay in data processing, and also ensure the integrity of the data.

[0059] It should be noted that the acquired real-time production process data can be processed and integrated using statistical analysis, statistical inference and other methods to obtain a further understanding of the original data, and the results can be visualized and displayed on the system interface in the form of reports, charts, etc., which is convenient for intuitive viewing, so as to realize the function of analyzing real-time data. In the process industry, the collection and analysis of real-time data plays an irreplaceable role in improving production efficiency, ensuring safe operation, reducing energy consumption and reducing emissions. Furthermore, real-time data can help engineers and operators monitor key parameters in the production process, such as temperature, pressure, flow, etc., to ensure that process conditions are always in the best state, and through data analysis, provide decision support for energy and carbon management, help enterprises better plan production plans, improve production efficiency and benefits, and at the same time, timely discover potential problems to avoid production interruptions or product quality degradation.

[0060] Specifically, a data analysis method is used to analyze and process the obtained production process data, such as various energy consumption data. Various energy consumption data include, for example, the amount of electricity, gas, heat, and steam consumed during the production process. The analysis and processing steps are: processing missing values, including deleting records with missing values ​​or replacing missing values ​​with the mean of the data, and calculating the mean and standard deviation within a time window to obtain the specific distribution of the data, and then removing outliers outside the range of the mean ± 3 times the standard deviation. For example, Figure 4 As shown, the temperature of a certain device collected by a temperature sensor, the pressure of a certain device collected by a pressure sensor, and the power load collected by an electric meter are transmitted to a data analysis platform. After data analysis, they are displayed in the form of visual charts, etc., which is convenient for production personnel to monitor process parameters.

[0061] Step S12: pre-process the production process data to convert it into a data format suitable for the deep neural network model; input the format-converted production process data into the deep neural network model for training to obtain an energy carbon emission prediction model.

[0062] In one embodiment, the method of preprocessing production process data includes: downsampling the production process data so that each category of production process data is at the same sampling frequency, and aligning the time points; performing data cleaning operations on the downsampled and aligned production process data; and standardizing the cleaned production process data to make it suitable for the training of a deep neural network model.

[0063] Since data with low sampling frequency is often easier to align, and a sampling frequency that is too low will reduce the quality of the data and affect the results of subsequent calculations, the time point alignment operation in this embodiment needs to be considered simultaneously with the sampling frequency so that the production process data of each category is at the same sampling frequency while the time points are aligned.

[0064] Optionally, the data cleaning operation in this embodiment includes but is not limited to: abnormal value or outlier processing, specifically filling by mean replacement or interpolation; data deletion, specifically, under the premise of serious data missing or poor data quality, consider deleting these uncertain data (pressure, temperature, medium information) records to avoid affecting subsequent calculations, thereby improving the overall quality of the data set.

[0065] It is worth emphasizing that since the magnitude of production process data such as pressure is usually greater than ten to the fifth power, and production process data such as temperature is hundreds of Kelvin, it is not a good choice to directly analyze or compare the two. Therefore, these data need to be normalized or standardized to put them in one dimension for easy analysis and calculation. Specific standardization processing includes but is not limited to: zero mean standardization processing, decimal calibration standardization processing, logarithmic transformation standardization processing, power law transformation standardization processing, normalization standardization processing, etc., which are not limited to this.

[0066] In a specific embodiment, the production process data includes a variety of energy consumption data and process parameter data generated by the process industry during the operation process; the various energy consumption data are converted into corresponding carbon emission data according to the nature and source of the energy; the energy consumption data, process parameter data and carbon emission data are downsampled, aligned, cleaned and standardized to make them suitable for the training of the deep neural network model.

[0067] It should be noted that since the carbon emissions converted from electricity, heat and other energy sources from different sources will be different, it is necessary to consider the nature and source of information such as electricity and heat energy transmitted from the outside world, and convert them into carbon emissions and energy consumption respectively. At the same time, the energy source and nature from within the factory should be considered. For example, the factory has its own wind power equipment, photovoltaic equipment, etc., and can obtain part of the electricity source by itself. The energy-to-carbon conversion ratio of this part is also different, and different conversion coefficients need to be converted according to a reasonable ratio. After the relevant calculations are completed, the data before and after the conversion need to be persisted and saved in the database to provide data support for subsequent steps. Specifically, for example, the following formula is used to convert energy consumption data into carbon emission data:

[0068] Total CO2 emissions (kg) = energy consumption (kWh or m3) × carbon emission factor (kg CO2 / kWh or kg CO2 / m3); Formula (1)

[0069] Among them, the carbon emission factor refers to the CO2 emissions generated by unit energy consumption, which varies according to the region, energy type and energy production method. It can be calculated specifically in accordance with relevant specifications and will not be repeated here.

[0070] Optionally, real-time process parameter data is obtained, such as the inlet and outlet pressures obtained by the pressure sensor, the inlet and outlet flow obtained by the flow meter, the equipment process temperature obtained by the temperature sensor, etc. during the production process, and then stored in the corresponding database for use in subsequent steps.

[0071] In one embodiment, the method also includes: dividing the production process data into a training set, a validation set and a test set in a certain ratio, the training set is used to train the deep neural network model so that the model learns rules and patterns from the training set; the validation set is used for tuning the deep neural network model and selecting hyperparameters to optimize model performance; the test set is used to evaluate the generalization ability of the deep neural network model.

[0072] It should be noted that the division ratio of the production process data can be, for example, 80% training set, 10% validation set, and 10% test set, and the specific ratio is not limited.

[0073] Specifically, before segmenting the data set, the data set can be further processed by feature engineering, data conversion, etc.

[0074] In this embodiment, the deep neural network model (DNN) is a machine learning model composed of multiple layers of neural networks, which processes complex data patterns by simulating the neural network structure of the human brain. Specifically, the deep neural network model includes an input layer, multiple hidden layers and an output layer, each layer is composed of multiple neurons, and the neurons are connected by weights.

[0075] In a specific embodiment, during the training of the deep neural network model, a regression algorithm is used to fit the model, and the root mean square error (RMSE) loss function is selected to measure the accuracy of the model prediction. The model is learned with the goal of minimizing the root mean square error to obtain a model with a smaller error as a prediction model. The root mean square error is defined as the square root of the mean of the square of the difference between the predicted value and the true value, and its specific calculation formula is as follows:

[0076]

[0077] Where n is the number of samples, y i is the true value of the i-th sample, is the predicted value of the ith sample.

[0078] Step S13: deploying the energy carbon emission prediction model to predict the energy carbon value of real-time emissions.

[0079] Specifically, the trained energy carbon emission prediction model is deployed in the production environment of the process industry to perform actual prediction tasks in the production process.

[0080] In one embodiment, the energy and carbon management method based on production process data also includes performing any one or more of the following interpretability configurations on the deep neural network: configuring a model component with certain interpretability in the neural network; the model component includes a decision tree or a linear model; using SHAP values ​​or LIME to evaluate and explain the importance of each feature in the model; and displaying the decision-making process and feature impact of the model based on visualization technology.

[0081] It should be understood that SHAP (Shapley Additive Explanations) is an explanation method based on cost function, which can explain any decision of any model. Its core idea is to explain the decision process of the model by calculating the contribution of each feature in the model decision. LIME (Local Interpretable Model-agnostic Explanations) is a locally interpretable model-agnostic explanation method, which can explain any decision of any model. Its core idea is to explain the decision process of the original model by building a simplified model.

[0082] In the process technology, interpretable configuration is performed in the deep neural network to facilitate operators and engineers to understand the decision-making process of the model. Specifically, by using easy-to-understand components such as decision trees or linear models, it is convenient for operators and engineers to collaborate across disciplines. At the same time, tools such as SHAP values ​​or LIME can be used to identify and explain the importance of each feature in the model, thereby helping engineers optimize the process flow. By displaying the decision-making process and feature influence of the model through visualization technology, engineers can better understand which parameters have the greatest impact on product quality and output, thereby ensuring that the deep neural network model can not only provide accurate predicted energy-to-carbon values, but also that its decision-making process is clear to operators, which helps to improve the efficiency and effectiveness of the entire production process. Since the safety risks involved in ordinary industries are relatively low and the requirements for real-time and safety are not high, ordinary conventional industries do not need to perform interpretable configuration. However, due to the process industry in the application scenario of the embodiment of the present application, its demand for model interpretability is much higher than that of ordinary industries. The reasons are: (1) The process industry usually involves high-risk environments, such as the chemical, oil and gas industries. Any operational errors may lead to serious safety accidents. Therefore, interpretability is crucial to understanding model behavior, preventing errors and ensuring safety; (2) In the process industry, decisions usually need to be based on accurate data and analysis. Interpretability configuration enables decision makers to understand the predictions and recommendations of the model and make correct decisions; (3) The maintenance of process industry equipment and systems requires rapid diagnosis and response to potential problems. The interpretability of the model helps to quickly identify and solve problems. Therefore, it is crucial to perform interpretability configuration in the process industry in the application scenario of the embodiment of the present application.

[0083] In one embodiment, the energy-carbon management method based on production process data further includes: using a genetic algorithm to optimize the energy-carbon value predicted by the energy-carbon emission prediction model to obtain a local optimal solution. It should be emphasized that the optimization algorithm in this embodiment can also use a simulated annealing algorithm or a particle swarm algorithm to optimize the target energy-carbon value to obtain the optimal effect.

[0084] In this embodiment, after training the energy carbon emission prediction model, it is necessary to further optimize the predicted energy carbon value, so as to reduce the carbon emission value and reduce energy consumption. The energy carbon emission prediction model is used as a reasonable approximation of the true value of future energy carbon emission to predict future emissions, and then the intelligent optimization algorithm is used to find the local optimal solution that minimizes future energy carbon emission, so as to optimize the existing energy carbon emission value. Here, various values ​​in the current generation process can be cleaned and preprocessed to ensure data quality, and the preprocessed data is input into the model to obtain the predicted output value. In addition, the optimal value that can minimize emissions is searched within the process production range. According to the optimal value, the specific parameter values ​​required by each instrument or equipment are adjusted to achieve the predicted optimal energy carbon emission value, and its state is adjusted so that the corresponding equipment parameters reach the optimal level of energy carbon emission, so as to obtain a better energy carbon emission value and optimize the production process. In addition, the prediction results and actual emissions of the model can be continuously monitored and adjusted as needed. By feeding the optimization results back to the model training process, the prediction ability and optimization effect of the model can be further improved. Throughout the optimization process, the deep neural network model acts as a prediction and evaluation tool, while the intelligent optimization algorithm is used to find the optimal solution within the feasible process range. This method, which combines data-driven prediction and algorithm optimization, helps achieve the energy conservation and emission reduction goals of the production process.

[0085] In the actual process of optimizing carbon emissions, it is necessary to consider the current range of values ​​of various parameters and the design values ​​of these parameters. If the current or designed values ​​are not considered, unrealistic values ​​will be obtained, causing the optimization to fail. For example, the magnitude of pressure usually has a certain range of values, and negative values ​​are impossible. The pressure at the last moment is likely to be near the range at this moment, and it is unlikely to have a sudden change, etc. Since the optimization model is based on the result of fitting historical data, obviously unreasonable values ​​may appear within a certain range. Therefore, a range must be limited to make it a constrained optimization problem.

[0086] After the deep neural network model training is completed, the model needs to be retrained regularly or irregularly. Here, the main consideration is whether the model can truly reflect the original rules in the new time period. If the model error increases or is no longer applicable to the current working conditions, the model must be retrained and optimized.

[0087] Figure 5 is a schematic block diagram of an energy-carbon management system based on production process data provided by an embodiment of the present application. Figure 5 As shown, the energy carbon management system 500 based on production process data includes:

[0088] The data collection module 501 is used to collect production process data generated by the process industry during operation;

[0089] The model building module 502 is used to pre-process the production process data to convert it into a data format suitable for a deep neural network model; input the format-converted production process data into the deep neural network model for training to obtain an energy carbon emission prediction model;

[0090] The model deployment module 503 is used to deploy the energy carbon emission prediction model to predict the energy carbon value of real-time emissions.

[0091] It should be understood that the specific process of each module executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0092] It should also be understood that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0093] The energy-carbon management system 500 based on production process data can process complex production process data, identify key factors affecting carbon emissions, and establish an accurate prediction model to predict the energy-carbon value of real-time emissions. Once the model is trained and deployed, it can predict carbon emissions in the real-time production environment of the process industry. Combined with real-time production data, the system can instantly adjust process parameters or operating strategies to achieve the best energy-saving and emission-reduction effects.

[0094] Figure 6 is a schematic block diagram of an electronic terminal provided in an embodiment of the present application. Figure 6 As shown, the electronic terminal includes: at least one processor 601, a memory 602, at least one network interface 603 and a user interface 605. The various components in the device are coupled together through a bus system 604. It can be understood that the bus system 604 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 604 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 6In the specification, various buses are labeled as bus systems.

[0095] The user interface 605 may include a display, a keyboard, a mouse, a trackball, a click gun, keys, buttons, a touch pad or a touch screen.

[0096] It is understood that the memory 602 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM). The memory described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable categories of memory.

[0097] The memory 602 in the embodiment of the present invention is used to store various categories of data to support the operation of the electronic terminal 600. Examples of these data include: any executable program for operating on the electronic terminal 600, such as an operating system 6021 and an application 6022; the operating system 6021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 6022 may include various applications, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The energy-carbon management method based on production process data provided in the embodiment of the present invention may be included in the application 6022.

[0098] The method disclosed in the above embodiment of the present invention can be applied to the processor 601, or implemented by the processor 601. The processor 601 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 601 or the instruction in the form of software. The above processor 601 may be a general processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 601 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiment of the present invention. The general processor 601 may be a microprocessor or any conventional processor, etc. In combination with the steps of the accessory optimization method provided in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0099] In an exemplary embodiment, the electronic terminal 600 may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD) to execute the aforementioned method.

[0100] According to the method provided in the embodiment of the present application, the present application also provides a computer program product, which includes: a computer program code, when the computer program code is run on a computer, the computer executes Figure 1 A method according to any one of the embodiments shown.

[0101] According to the method provided in the embodiment of the present application, the present application also provides a computer-readable storage medium, which stores a program code, and when the program code is run on a computer, the computer executes Figure 1 A method according to any one of the embodiments shown.

[0102] Exemplarily, the use process of this application is as follows: the system administrator first logs in to the system and imports the energy carbon management data into the system database through the system; then the system automatically cleans and preprocesses these data, and stores these processed data in the database; then the system administrator can click on the interface to train a model and adjust the hyperparameters synchronously, and obtain an energy carbon prediction model after training; the user logs in to the system through the login interface, and after verifying the login information, the system gives the user the authority to use the energy carbon management optimization model. The user can click to import real-time data and optimize the data at this moment to obtain the state value of each optimized instrument and equipment; after obtaining the state value, the relevant process parameters can be adjusted manually or automatically, the valves can be adjusted, the pressure can be controlled, the power and heat energy consumption can be reduced, etc., so that the energy carbon emission is optimized. Different user role information needs to be considered here, such as the authority of engineers with the ability to train models and the authority of personnel who need to view energy carbon management data and obtain model prediction or optimization results. At the same time, it is necessary to have the configuration authority to configure the range of various parameters of the instrument and equipment. This part of the data is used to warn when the data obtained from the actual test exceeds the range or to set the variable value interval of the optimization model when optimizing the energy carbon index.

[0103] The terms "component", "module", "system", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program and / or a computer. By way of illustration, both applications running on a computing device and a computing device can be components. One or more components may reside in a process and / or an execution thread, and a component may be located on a computer and / or distributed between two or more computers. In addition, these components may be executed from various computer-readable media having various data structures stored thereon. Components may, for example, communicate through local and / or remote processes according to signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system and / or a network, such as the Internet interacting with other systems through signals).

[0104] Those of ordinary skill in the art will appreciate that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0105] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0106] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0107] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0108] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0109] In the above embodiments, the functions of each functional unit can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When loading and executing computer program instructions (programs) on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media integrations. Available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., high-density digital video discs (DVDs), or semiconductor media (e.g., solid state disks (SSDs), etc.).

[0110] If the function 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 this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0111] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0112] In summary, the energy-carbon management method, system, medium, terminal and program product based on production process data provided by this application provide a complete set of real-time production process data for energy-carbon management in process industries for analysis, prediction and optimization. Specifically, the production process data generated in real time in the process industry is analyzed, processed, integrated, analyzed, and statistically analyzed, and presented in the form of a set of reports and charts. At the same time, by constructing and deploying an energy-carbon emission value prediction model, energy consumption and carbon emission values ​​are predicted, and the setting range of key parameters can be given to optimize energy consumption and carbon emission values, thereby optimizing energy use and reducing carbon footprint, which is crucial to responding to global carbon reduction initiatives and reducing operating costs. Therefore, this application effectively overcomes the various shortcomings of the prior art and has a high industrial utilization value.

[0113] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. An energy-carbon management method based on production process data, characterized in that: include: Collect production process data generated by process industries during operations; Preprocessing the production process data to convert it into a data format suitable for a deep neural network model; inputting the format-converted production process data into the deep neural network model for training to obtain an energy carbon emission prediction model; The energy carbon emission prediction model is deployed to predict the energy carbon value of real-time emissions.

2. The energy-carbon management method based on production process data according to claim 1 is characterized in that: The production process data generated by the process industry during operation is collected, including: Corresponding production process data are collected from various process industrial equipment based on different communication protocols through pre-deployed edge gateway devices; the edge gateway devices are integrated with drivers of various types of Internet of Things protocols.

3. The energy-carbon management method based on production process data according to claim 2 is characterized in that: The production process data collected by the edge gateway device is sent to the edge computing platform; wherein: A data processing framework for processing real-time data streams is implemented on the edge computing platform, and the data processing framework includes an Apache Flink framework or a Spark Streaming framework; based on a data caching mechanism and a local storage mechanism, the received production process data is cached.

4. The energy-carbon management method based on production process data according to claim 1 is characterized in that: The method of preprocessing the production process data includes: Downsample the production process data to make each category of production process data have the same sampling frequency and align the time points; Perform data cleaning operations on the downsampled and aligned production process data; The cleaned production process data is standardized to make it suitable for training deep neural network models.

5. The energy-carbon management method based on production process data according to claim 4 is characterized in that: The production process data includes various energy consumption data and process parameter data generated by the process industry during the operation process; according to the nature and source of energy, the various energy consumption data are converted into corresponding carbon emission data; The energy consumption data, process parameter data and carbon emission data are downsampled, aligned, cleaned and standardized to make them suitable for the training of the deep neural network model.

6. The energy-carbon management method based on production process data according to claim 1 is characterized in that: The method further includes performing any one or more of the following interpretability configurations on the deep neural network: A model component with certain explanatory power is configured in the neural network; the model component includes a decision tree or a linear model; Use SHAP values ​​or LIME to evaluate and explain the importance of each feature in the model; Use visualization techniques to demonstrate the model's decision-making process and feature impact.

7. The energy-carbon management method based on production process data according to claim 1 is characterized in that: The method also includes: dividing the production process data into a training set, a validation set and a test set in a certain ratio, wherein the training set is used to train the deep neural network model so that the model learns rules and patterns from the training set; the validation set is used for tuning the deep neural network model and selecting hyperparameters to optimize model performance; and the test set is used to evaluate the generalization ability of the deep neural network model.

8. The energy-carbon management method based on production process data according to claim 1 is characterized in that: The method further comprises: optimizing the energy-to-carbon value predicted by the energy-to-carbon emission prediction model using a genetic algorithm to obtain a local optimal solution.

9. An energy-carbon management system based on production process data, characterized in that: include: Data collection module, used to collect production process data generated by process industries during operations; A model building module is used to pre-process the production process data to convert it into a data format suitable for a deep neural network model; input the format-converted production process data into the deep neural network model for training to obtain an energy carbon emission prediction model; The model deployment module is used to deploy the energy carbon emission prediction model to predict the energy carbon value of real-time emissions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

11. A computer program product, characterized in that The computer program product includes a computer program code, and when the computer program code is executed on a computer, the computer is enabled to implement the method as described in any one of claims 1 to 8.

12. An electronic terminal comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method according to any one of claims 1 to 8.

Images