Digital energy management and control platform and energy consumption management method

Abstract

The invention relates to the technical field of data prediction, in particular to a digital energy management and control platform and an energy consumption management method. The method comprises the following steps: acquiring predicted steam consumption of a current production process according to steam consumption in a historical production process; in a production process, the fuel consumption of the boiler is obtained according to the amount of steam actually generated by the boiler, the fuel consumption energy for generating unit steam and the heat efficiency of the boiler; according to the fuel consumption, the start-stop operation cost, the fuel unit price, the fuel pollution discharge coefficient, the pollutant treatment efficiency and the pollutant unit treatment cost, an objective function is constructed; and obtaining a fuel scheduling strategy of the boiler in the current production process according to the predicted steam consumption of the current production process and the target function. By predicting the fuel scheduling strategy of the boiler in the current production process, fuel is reasonably distributed, resource waste is avoided, and meanwhile the production cost of an enterprise is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of data prediction, and in particular to a digital energy management and control platform and an energy consumption management method. Background Art

[0002] Energy is the core driving force of social development. It is a limited resource, so it needs to be reasonably allocated. For industrial enterprises, energy cost is an important part of business operations and is related to the profitability of the enterprise. Therefore, it is necessary to reasonably allocate and utilize energy under the premise of the lowest possible energy cost.

[0003] At present, in the manufacturing and production process of industrial enterprises, due to the backward method of collecting energy consumption data, the collection and analysis of energy consumption data is difficult to synchronize with the production process, which makes it difficult to adjust the production equipment and production plans in advance, resulting in unreasonable energy allocation and waste of resources; and the existing energy management and control platform cannot achieve the balance of enterprise production energy in real time, and cannot automatically achieve energy consumption benchmarking, which also leads to unreasonable energy allocation and waste of resources. Summary of the invention

[0004] In order to solve the technical problem of unreasonable energy distribution and waste of resources, the purpose of the present invention is to provide a digital energy management and control platform and an energy consumption management method. The technical solutions adopted are as follows: In a first aspect, an embodiment of the present invention provides a digital energy consumption management method, the method comprising the following steps: According to the steam consumption during the process production start and stop period and the steam consumption during the process production stable operation period in the historical production process, the first steam consumption during the process production start and stop period and the second steam consumption during the process production stable operation period of the current production process are predicted to determine the predicted steam consumption of the current production process; In a production process, the fuel consumption of each boiler is obtained based on the actual amount of steam generated by each boiler, the fuel consumption energy per unit of steam generated, and the thermal efficiency of the boiler; the energy consumption cost is obtained based on the fuel consumption of each boiler, the start-up and shutdown operation cost, and the unit price of fuel; The environmental protection cost is obtained based on the fuel consumption, fuel emission coefficient, pollutant treatment efficiency and unit pollutant treatment cost of each boiler in a production process; among them, the fuel consumption, fuel emission coefficient and unit pollutant treatment cost are all positively correlated with the environmental protection cost, and the pollutant treatment efficiency is negatively correlated with the environmental protection cost; The function formed by adding energy consumption cost and environmental protection cost is used as the objective function; According to the predicted steam consumption and objective function of the current production process, the fuel scheduling strategy of the boiler in the current production process is obtained.

[0005] Furthermore, the method for obtaining the first steam consumption is: The process production start and stop periods of the first preset number of historical production processes adjacent to the current production process are all used as the historical process production start and stop periods; The steam consumption during the start and stop periods of historical process production is arranged according to the production order from front to back of the corresponding historical production process to obtain the historical steam consumption sequence during the start and stop periods of process production; According to the historical steam consumption sequence, the steam consumption prediction model for the process production start and stop period is constructed through the ARIMA model to predict the first steam consumption of the process production start and stop period of the current production process.

[0006] Furthermore, the method for obtaining the second steam consumption is: Obtaining a trend reference value according to steam consumption during a period of stable process production operation of a second preset number of historical production processes adjacent to the current production process; Taking the quarter in which the current production process is located as the target quarter, obtaining a seasonal reference value based on the steam consumption during the stable operation period of process production in the third preset number of historical target quarters adjacent to the current production process; The result of normalizing the sum of the trend reference value and the season reference value is used as the time factor characteristic value of the stable operation period of the process production; The time factor characteristic value, external environment factor characteristic value and process factor characteristic value during the stable operation period of process production are used as the input of the long short-term memory network to predict the second steam consumption during the stable operation period of process production in the current production process.

[0007] Furthermore, the method for obtaining the trend reference value is: The steam consumption of a second preset number of historical production processes adjacent to the current production process during the process production stable operation period is constructed into a row matrix as a trend matrix; Obtain the mean value of all steam consumption in the trend matrix as the first reference value; The result of negatively correlating and normalizing the difference between each steam consumption in the trend matrix and the first reference value is used as the first weight of the corresponding steam consumption; Arrange the first weights vertically from left to right in the trend matrix according to the corresponding steam consumption to construct a column matrix as a trend weight matrix; The product of the trend weight matrix and the trend matrix is ​​used as the trend reference value; The method for obtaining the seasonal reference value is: For any historical target quarter, the sum of steam consumption during stable production periods of all processes in the historical target quarter is obtained as the target steam consumption for the historical target quarter; constructing the target steam consumption of the third preset number of historical target quarters adjacent to the current production process into a row matrix as a seasonal matrix; Obtain the mean of all target steam consumptions in the seasonal matrix as a second reference value; The result of negatively correlating and normalizing the difference between each target steam consumption in the seasonal matrix and the second reference value is used as the second weight of the corresponding target steam consumption; Arrange the second weights vertically from left to right in the seasonal matrix according to the corresponding target steam consumption to construct a column matrix as a seasonal weight matrix; The product of the seasonal weight matrix and the seasonal matrix is ​​used as the seasonal reference value.

[0008] Furthermore, the method for obtaining the fuel consumption is: The difference between the thermal enthalpy of steam and the thermal enthalpy of feed water is obtained as the enthalpy difference; The ratio of the enthalpy difference to the unit calorific value of the fuel is taken as the fuel consumption energy for producing unit steam; For any boiler, the ratio of the fuel consumption energy to produce unit steam to the thermal efficiency of the boiler is taken as the actual fuel consumption energy to produce unit steam by the boiler; The product of the actual amount of steam generated by the boiler and the actual fuel consumption energy for generating unit steam is taken as the fuel consumption of the boiler.

[0009] Furthermore, the method for obtaining the energy consumption cost is: For any boiler, the product of the fuel consumption of the boiler and the fuel unit price corresponding to the fuel of the boiler is used as the first fuel cost of the boiler; The sum of the first fuel cost and the start-stop operation cost of the boiler is used as the energy consumption reference cost of the boiler; The relevant results of the energy consumption reference costs of all boilers in a production process are taken as energy consumption costs.

[0010] Furthermore, the method for obtaining the environmental protection cost is: The sum of the fuel consumption of each boiler in a production process is taken as the overall fuel consumption; The negative correlation result of the pollutant treatment efficiency is taken as the first result, and the product of the overall fuel consumption, the fuel emission coefficient and the first result is taken as the pollutant emission; The product of pollutant emissions and the unit treatment cost of pollutants is taken as the environmental protection cost.

[0011] Furthermore, the method for obtaining the fuel scheduling strategy of the boiler in the current production process according to the predicted steam consumption and the objective function of the current production process is: The constraint conditions of the objective function are set as follows: the sum of the actual steam generated by all boilers in the current production process is greater than or equal to the predicted steam consumption of the current production process; The environmental protection cost is less than or equal to the preset maximum environmental protection cost; When the objective function is minimized while satisfying the constraints, the fuel corresponding to each boiler at this time is used as the fuel scheduling strategy for each boiler in the current production process.

[0012] Furthermore, the method for obtaining the predicted steam consumption is: The sum of the first steam consumption and the second steam consumption is used as the predicted steam consumption of the current production process.

[0013] In a second aspect, another embodiment of the present invention provides a digital energy management and control platform, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of any one of the above methods are implemented.

[0014] The present invention has the following beneficial effects: The present invention obtains the predicted steam consumption of the current production process according to the steam consumption in the historical production process, sets a reference amount for the steam consumption of the current production process, which is conducive to the subsequent reasonable allocation of energy in the current production process; in order to reasonably analyze the fuel scheduling strategy of the boiler in the production process, avoid waste of resources and reduce the production cost of the enterprise, and then in a production process, according to the actual amount of steam generated by each boiler and the fuel consumption energy of generating unit steam, and the thermal efficiency of the boiler, the fuel consumption of each boiler is obtained, and the energy consumption of each boiler is accurately reflected; further, according to the fuel consumption, start-stop operation cost, fuel unit price, fuel emission coefficient, pollutant treatment efficiency and unit pollutant treatment fee of each boiler, an objective function is constructed to determine the method for obtaining the cost in the production process, which is conducive to the subsequent reasonable allocation of the fuel scheduling strategy of the boiler in the production process; in order to avoid predicting that the fuel scheduling strategy has insufficient steam production, according to the predicted steam consumption of the current production process and the objective function, the fuel scheduling strategy of the boiler in the current production process is accurately obtained, and the fuel in the manufacturing and production operation process of the enterprise is targetedly predicted and controlled to avoid waste of resources and effectively reduce the production cost of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A schematic flow chart of a digital energy consumption management method provided by an embodiment of the present invention; Figure 2 A flow chart of a method for obtaining predicted steam consumption provided by one embodiment of the present invention; Figure 3 A flow chart of a method for obtaining a second steam consumption provided by an embodiment of the present invention; Figure 4 A structural diagram of a digital energy consumption management system provided by an embodiment of the present invention; Figure 5 A schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, characteristics and effects of a digital energy management and control platform and energy consumption management method proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The following is a detailed description of a digital energy management and control platform and a specific energy consumption management method provided by the present invention in conjunction with the accompanying drawings.

[0020] Embodiment 1: The present invention proposes a digital energy consumption management method, please refer to Figure 1 , which shows a schematic flow chart of a digital energy consumption management method provided by an embodiment of the present invention, the method comprising the following steps: Step S1: Based on the steam consumption during the process production start and stop periods and the steam consumption during the process production stable operation period in the historical production process, predict the first steam consumption during the process production start and stop periods and the second steam consumption during the process production stable operation period of the current production process, and then determine the predicted steam consumption of the current production process.

[0021] The digital energy and carbon management center for industrial enterprises and parks is an information system that is built based on intelligent algorithms, industrial Internet, Internet of Things and other technologies to meet the energy consumption and carbon emission management needs of industrial enterprises and parks, and has the functions of energy consumption and carbon emission data collection, analysis, prediction, early warning and management. Its core goal is to save energy and reduce carbon emissions and reduce costs and increase efficiency for industrial enterprises and parks. According to the requirements of relevant industry standards, the system architecture of the energy and carbon management center for industrial enterprises and parks is designed, which includes six modules: infrastructure layer, data collection layer, data architecture layer, model component layer, business application layer, and interactive display layer.

[0022] The infrastructure layer includes: industrial enterprises and parks can provide a stable and secure operating environment for the carbon pipeline center through their own servers or cloud servers. The entire operating environment includes servers, storage, networks, operating systems, and databases to ensure that the carbon management center responds quickly and has maintainability and scalability.

[0023] The data collection layer includes: the energy carbon management center can complete the collection and upload of energy consumption, production and operation and other related data through docking with the previous database, manual entry, sensor measurement and other collection methods. And clean the data to remove the interference of redundant data, so that the subsequent analysis and processing of the data will be more concise and efficient.

[0024] The data architecture layer includes: storing various types of data through the original data architecture of the enterprise and industrial park industrial Internet platform, or building basic databases, collection databases, business databases, statistical databases, etc. Data from different sources have different data types. For example, business data and equipment operating parameters belong to relational data; historical energy usage data belongs to time series data; and real-time energy usage trend data belongs to streaming data.

[0025] The model component layer includes: enterprise carbon emission accounting model, industrial energy efficiency benchmarking model and energy consumption forecasting and early warning model. Among them, the enterprise carbon emission accounting model realizes the accounting and analysis of the enterprise's carbon emissions according to the enterprise application scenario and various requirements; the industrial energy efficiency benchmarking model realizes the energy efficiency benchmarking of the enterprise's main products and equipment according to the energy consumption limit standards stipulated in the relevant requirements; the energy consumption forecasting and early warning model accurately predicts the different energy consumption at different stages of the enterprise's production process based on historical data, combines the forecast results with the production schedule, and issues an alarm when the actual energy consumption exceeds the planned energy consumption.

[0026] The business application layer includes: the business functions of industrial enterprises include energy carbon query, energy consumption structure analysis, energy consumption benchmarking, energy forecasting and early warning, energy efficiency optimization and balance, etc. The Industrial Park Energy Carbon Management Center provides digital support and public service capabilities such as energy consumption and carbon emission management for settled enterprises. At the same time, combined with the actual situation of the park, it conducts diversified analysis from different latitudes such as the park, region, building, and enterprises in the zone.

[0027] Interactive display layer: Based on the actual needs of industrial enterprises and parks, it provides access portals for industrial enterprises and parks through large screens, PCs or mobile phones, and builds visualization capabilities for related data and businesses.

[0028] Therefore, the energy carbon management platform can automatically collect and analyze the energy consumption data of enterprises in the production process, and generate production plans and specific working conditions of various energy-consuming equipment and production equipment that meet the expected interests of the enterprise based on the energy consumption early warning module and energy efficiency balance module, thus completing the complete process of collecting, diagnosing and solving the energy consumption data of the enterprise. When using the energy carbon management platform, relevant personnel of the enterprise can intuitively see the energy consumption early warning situation in the enterprise's production, the energy consumption diagnosis report of the current production process and the corresponding solutions, that is, the control plan for production equipment and production plans.

[0029] This embodiment takes a large manufacturing enterprise as an example for analysis and describes the core modules in the energy and carbon management platform. The manufacturing enterprise includes three workshops, namely the manufacturing workshop, the wrapping workshop and the logistics warehouse area. Among them, the manufacturing workshop is divided into a production area and a storage cabinet area, which is mainly used for material production; the wrapping workshop is mainly used for product production and packaging; the logistics warehouse area is mainly used for semi-finished product storage, finished product storage, auxiliary material storage, finished product warehousing, raw material turnover, etc. The energy consumption of the three major workshops is mainly natural gas, fuel oil, electricity and other energy sources. Among them, natural gas and fuel oil support the operation of boiler equipment, and the steam generated by the boiler is used for central air-conditioning operation and process production; the operation of central air-conditioning equipment relies on electricity and steam, and its function is to regulate the material storage environment and process production environment; process production requires steam, electricity, compressed air and soft water to manufacture products.

[0030] In order to accurately analyze the energy consumption in the production process, this embodiment sets sensors on different equipment and units to collect data in various production processes of each workshop and assembly line in real time, such as steam consumption, steam generation, electricity usage, temperature data, etc. It should be noted that in this embodiment, each production process is a complete and non-stop production process.

[0031] For manufacturing companies, the direct purpose of optimizing energy consumption management is to reduce costs. In the production process, steam is the main production power, and steam is produced by burning fuel in the boiler. Therefore, this embodiment analyzes the steam consumption of the production process and the actual amount of steam generated by the boiler, and then reasonably allocates the fuel burned by the boiler that produces steam to reduce the production cost of the manufacturing company. In order to better analyze, this embodiment constructs a steam intelligent prediction model and a steam production balance optimization model. Among them, the steam intelligent prediction model predicts the steam consumption at different stages of the production process to support the calculation of the subsequent energy scheduling model; the goal of the steam production balance optimization model is to schedule fuel for equipment such as boilers that produce steam, while meeting the energy consumption benchmark and production consumption, so that the fuel cost and environmental protection cost of the company's steam production are minimized.

[0032] The consumption of process steam in the production process is highly periodic, and the periods of steam consumption are the process production start and stop periods and the process production stable operation periods. In order to reasonably set the scheduling of boiler fuel in the production process, this embodiment first constructs a steam intelligent prediction model. Therefore, according to the steam consumption in the process production start and stop periods and the steam consumption in the process production stable operation period in the historical production process, the first steam consumption in the process production start and stop periods of the current production process and the second steam consumption in the process production stable operation period are predicted, and then the predicted steam consumption of the current production process is determined, which is conducive to the subsequent reasonable scheduling of boiler fuel.

[0033] Preferably, in one possible implementation of this embodiment, the method for obtaining the predicted steam consumption is as follows: Figure 2 , which shows a flow chart of a method for obtaining predicted steam consumption provided in this embodiment, the method comprising the following steps: Step S201: predicting the first steam consumption during the process production start and stop periods of the current production process.

[0034] The start and stop periods of process production are affected by many factors such as the real-time status of the equipment and human operation. The steam consumption during the start and stop periods of process production cannot be quantified using a mechanism model. Usually, the market demand for the products produced by manufacturing companies has a certain regularity. Therefore, this embodiment predicts the first steam consumption during the start and stop periods of process production in the current production process based on the historical steam consumption during the start and stop periods of process production.

[0035] Preferably, in a method that can be implemented in this embodiment, the method for obtaining the first steam consumption is: the process production start and stop periods of the first preset number of historical production processes adjacent to the current production process are all used as historical process production start and stop periods; in this embodiment, the first preset number is set to 50, and the implementer can set the size of the first preset number according to the actual situation, which is not limited here. If there are less than 50 historical production processes before the current production process, only the process production start and stop periods of the existing historical production processes are analyzed. The steam consumption of the historical process production start and stop periods is arranged according to the production order from front to back of the corresponding historical production process to obtain the historical steam consumption sequence of the process production start and stop periods; according to the historical steam consumption sequence, the steam consumption prediction model of the process production start and stop period is constructed through the autoregressive integrated moving average (ARIMA) model to predict the first steam consumption of the process production start and stop period of the current production process. Among them, the autoregressive integrated moving average (ARIMA) model is a well-known technology and will not be described in detail.

[0036] The ARIMA model is a statistical model used for time series analysis. The ARIMA model is used to describe the relationship between data points in a time series in order to predict or understand the data. The ARIMA model consists of three main parts: autoregression (AR), differencing (I), and moving average (MA). Among them, the first part, autoregression, refers to the relationship between the current value of a variable and its past value. In mathematical expression, it is a regression model. The target variable and the predictor variable of the regression are the steam consumption of the historical steam consumption series in the process production start and stop period in different production processes; the second part, differencing, refers to subtracting consecutive data points in the historical steam consumption series to stabilize the time series; the third part, moving average, focuses on the dependency between the error terms of the historical steam consumption series. The formula of the steam consumption prediction model for the process production start and stop period can be expressed as: ; In the formula, is the steam consumption during the process production start and stop period; t is the production sequence of the production process corresponding to the process production start and stop period; arrive is the autoregressive coefficient; arrive is the moving average coefficient; is the error term; is a constant term, which can be set by the implementer according to the actual situation and is not limited here; p is the number of autoregressive terms in the AR model; q is the number of moving average terms in the MA model; d is the number of difference terms.

[0037] The specific prediction method for steam consumption during the start and stop period of process production is as follows: first, the steam consumption during the start and stop period of historical process production is obtained as the original sequence of the ARIMA model (p, d, q); then, the autocorrelation diagram and partial autocorrelation diagram are used to determine the order of AR and MA (p and q); and then the parameters of the ARIMA model are determined by maximum likelihood estimation. and ; Finally, the steam consumption during the process production start and stop period is predicted using the steam consumption prediction model for the process production start and stop period of the current production process, and the first steam consumption during the process production start and stop period of the current production process is predicted.

[0038] Step S202: predicting the second steam consumption during the stable operation period of the process production of the current production process.

[0039] The steam consumption during the stable operation period of process production is jointly affected by external environmental factors, process factors and time factors. Among them, external environmental factors include workshop ambient temperature, humidity, air moisture, etc.; process factors include process parameters, production scheduling, etc.; time factors are manifested as the influence of steam consumption during the stable operation period of historical process production. Among them, process factors and external environmental factors are certain, and the core of predicting the steam consumption during the stable operation period of process production lies in the time factor that uses the steam consumption during the stable operation period of historical process production as a reference. It is known that the production process has obvious trend and seasonality. Therefore, this embodiment divides the time factor into trend mode and seasonal mode.

[0040] In order to analyze the trend pattern of steam consumption during the period of stable process production operation, this embodiment analyzes the steam consumption during the period of stable process production operation of historical production processes adjacent to the current production process, and obtains the trend change of steam consumption during the period of stable process production operation, which is conducive to accurately predicting the steam consumption during the period of stable process production operation of the current production process.

[0041] In order to analyze the seasonal pattern of steam consumption during the stable operation period of process production, this embodiment analyzes the steam consumption during the stable operation period of process production in a preset number of historical quarters that are the same quarter as the current quarter, obtains the seasonal changes in steam consumption during the stable operation period of process production, and then more accurately predicts the steam consumption during the stable operation period of process production in the current production process. Therefore, this embodiment obtains the time factor characteristic value of the stable operation period of process production based on the steam consumption during the stable operation period of process production in the historical production process, and then predicts the second steam consumption during the stable operation period of process production in the current production process based on the time factor characteristic value of the stable operation period of process production, the characteristic value of the external environment factor, and the characteristic value of the process factor.

[0042] Preferably, in one possible implementation of this embodiment, the method for obtaining the second steam consumption is as follows: Figure 3 , which shows a flow chart of a method for obtaining the second steam consumption provided in this embodiment, the method comprising the following steps: Step S301: Obtain a trend reference value according to the steam consumption of a second preset number of historical production processes adjacent to the current production process during a period of stable process production operation.

[0043] The trend reference value reflects the degree to which the steam consumption during the stable operation period of process production is affected by the time trend. The larger the trend reference value, the greater the degree to which the steam consumption during the stable operation period of process production is affected by the time factor.

[0044] Among them, the method for obtaining the trend reference value is: construct the steam consumption of the second preset number of historical production processes adjacent to the current production process during the stable operation period of the process production into a row matrix as a trend matrix; this embodiment sets the second preset number to 30, and the implementer can set the size of the second preset number according to the actual situation, which is not limited here; obtain the mean of all steam consumption in the trend matrix as the first reference value; negatively correlate and normalize the difference between each steam consumption in the trend matrix and the first reference value as the first weight of the corresponding steam consumption; the larger the first weight, the more reasonable the corresponding steam consumption. This embodiment is through The absolute value of the difference between each steam consumption in the trend matrix and the first reference value is negatively correlated and normalized, wherein exp is an exponential function with a natural constant as the base; is the first unknown number, which refers to the absolute value of the difference between each steam consumption in the trend matrix and the first reference value in this embodiment. The first weights are arranged vertically from left to right in the trend matrix according to the corresponding steam consumption, and a column matrix is ​​constructed as a trend weight matrix; the product of the trend weight matrix and the trend matrix is ​​used as the trend reference value.

[0045] Step S302: Taking the quarter in which the current production process is located as the target quarter, obtaining a seasonal reference value based on the steam consumption during the stable operation period of process production in a third preset number of historical target quarters adjacent to the current production process.

[0046] The seasonal reference value reflects the extent to which the steam consumption during the stable operation period of process production is affected by the quarterly trend. The larger the seasonal reference value, the greater the extent to which the steam consumption during the stable operation period of process production is affected by time factors.

[0047] Among them, the method for obtaining the seasonal reference value is: for any historical target quarter, obtain the sum of the steam consumption of all process production stable operation periods in the historical target quarter as the target steam consumption of the historical target quarter; construct the target steam consumption of the third preset number of historical target quarters adjacent to the current production process into a row matrix as a seasonal matrix; this embodiment sets the third preset number to 10, and the implementer can set the size of the third preset number according to actual conditions, which is not limited here. Obtain the mean of all target steam consumptions in the seasonal matrix as the second reference value; negatively correlate and normalize the difference between each target steam consumption in the seasonal matrix and the second reference value as the second weight of the corresponding target steam consumption; the larger the second weight, the more reasonable the corresponding target steam consumption. This embodiment is achieved through The absolute value of the difference between each target steam consumption in the seasonal matrix and the second reference value is negatively correlated and normalized, wherein exp is an exponential function with a natural constant as the base; is the second unknown number, which refers to the absolute value of the difference between each target steam consumption in the seasonal matrix and the second reference value in this embodiment. The second weights are arranged vertically from left to right in the seasonal matrix according to the corresponding target steam consumption, and a column matrix is ​​constructed as a seasonal weight matrix; the product of the seasonal weight matrix and the seasonal matrix is ​​used as the seasonal reference value.

[0048] Step S303: normalize the sum of the trend reference value and the season reference value, and use the result as the time factor characteristic value of the stable operation period of the process production.

[0049] In this embodiment, the sum of the trend reference value and the season reference value is normalized by a sigmoid function. The larger the characteristic value of the time factor is, the stronger the correlation between the time factor and the steam consumption prediction is.

[0050] Step S304: using the time factor characteristic value, the external environment factor characteristic value and the process factor characteristic value during the stable operation period of the process production as inputs of the long short-term memory network to predict the second steam consumption during the stable operation period of the process production of the current production process.

[0051] It is known that the characteristic values ​​of external environmental factors and process factors can be directly obtained during the stable operation period of process production, and then the characteristic values ​​of time factors, external environmental factors and process factors are integrated to predict the steam consumption during the stable operation period of process production. This embodiment uses a long short-term memory network to predict the steam consumption during the stable operation period of process production, that is, the characteristic values ​​of time factors, external environmental factors and process factors during the stable operation period of process production are used as the input of the long short-term memory network. Since the above three factor characteristic values ​​exist in the prediction process of steam consumption, it is a nonlinear problem. Therefore, this embodiment uses a hyperbolic tangent function to nonlinearly integrate the characteristic values ​​of time factors, external environmental factors and process factors. Among them, the activation function of the long short-term memory network is: ; In the formula, To predict the steam consumption during the stable operation period of the process production, is the characteristic value of time factor, is the characteristic value of external environmental factors, is the characteristic value of process factors; is a hyperbolic tangent function. Among them, the long short-term memory network is a well-known technology and will not be described in detail.

[0052] At this point, the second steam consumption during the stable operation period of the process production of the current production process is predicted.

[0053] Step S203: Obtain the predicted steam consumption of the current production process.

[0054] It is known that a complete production process includes a process production start and stop period and a process production stable operation period. Therefore, in this implementation, the sum of the first steam consumption and the second steam consumption is used as the predicted steam consumption of the current production process.

[0055] Step S2: In a production process, the fuel consumption of each boiler is obtained according to the actual amount of steam generated by each boiler, the fuel consumption energy per unit steam generated, and the thermal efficiency of the boiler; the energy consumption cost is obtained according to the fuel consumption and start-stop operation cost of each boiler, and the unit price of fuel.

[0056] The costs incurred for steam production can be divided into two aspects: energy consumption cost and environmental protection cost. The energy consumption cost of boiler steam production includes the fuel combustion cost and the boiler start-up and shutdown operation cost; the environmental protection cost refers to the environmental protection fee paid for the pollutant emissions generated by steam production. In order to analyze the energy consumption cost of boiler steam production in a production process, this embodiment constructs a method for obtaining energy consumption cost, and then obtains the fuel consumption of each boiler in a production process according to the actual amount of steam generated by each boiler and the fuel consumption energy per unit steam generated, as well as the thermal efficiency of the boiler. It should be noted that the fuels in different boilers can be different, but the fuel in each boiler is a single fuel. Then, the energy consumption cost is obtained based on the fuel consumption and start-up and shutdown operation cost of each boiler, as well as the unit price of the fuel.

[0057] Preferably, in a method that can be implemented in this embodiment, the method for obtaining the fuel consumption is: obtaining the difference between the steam enthalpy and the feed water enthalpy as the enthalpy difference; taking the ratio of the enthalpy difference to the unit calorific value of the fuel as the fuel consumption energy for generating unit steam; taking into account the thermal efficiency of the boiler, and then for any boiler, taking the ratio of the fuel consumption energy for generating unit steam to the thermal efficiency of the boiler as the actual fuel consumption energy for generating unit steam by the boiler; then taking the product of the actual amount of steam generated by the boiler and the actual fuel consumption energy for generating unit steam as the fuel consumption of the boiler. It should be noted that the steam enthalpy, feed water enthalpy, unit calorific value of the fuel and the thermal efficiency of the boiler are all known data and can be directly obtained and used. At this point, the fuel consumption of each boiler in the production process is obtained.

[0058] Preferably, in a method that can be implemented in this embodiment, the method for obtaining the energy consumption cost is: for any boiler, the product of the fuel consumption of the boiler and the fuel unit price corresponding to the fuel of the boiler is used as the first fuel cost of the boiler; wherein the fuel unit price of each fuel is known and can be used directly. The known energy consumption cost also includes the start-stop operation cost of the boiler, wherein the start-stop operation cost of the boiler can be directly obtained through experience, and then the sum of the first fuel cost of the boiler and the start-stop operation cost is used as the energy consumption reference cost of the boiler; in order to determine the energy consumption cost of the entire production process, the relevant results of the energy consumption reference costs of all boilers in a production process are used as the energy consumption cost. The larger the energy consumption cost, the more energy is consumed by the corresponding production process.

[0059] Step S3: Obtain the environmental protection cost according to the fuel consumption, fuel emission coefficient, pollutant treatment efficiency and unit pollutant treatment cost of each boiler in a production process.

[0060] It is known that pollutants are emitted during the process of burning fuel to generate steam in a boiler. Therefore, this embodiment obtains the environmental protection cost based on the fuel consumption, fuel emission coefficient, pollutant treatment efficiency and unit pollutant treatment cost of each boiler in a production process.

[0061] Preferably, in a method that can be implemented in this embodiment, the method for obtaining the environmental protection cost is: taking the sum of the fuel consumption of each boiler in a production process as the overall fuel consumption, and determining the total fuel consumption corresponding to a production process; this embodiment sets the fuel emission coefficients of all types of fuels to be the same, and then the pollutant emissions can be determined based on the product of the overall fuel consumption and the fuel emission coefficient. Considering that the manufacturing enterprise has a pollutant treatment system to treat the pollutants generated by the fuel during the production process of the product, this embodiment takes the negative correlation result of the pollutant treatment efficiency as the first result, and then takes the product of the overall fuel consumption, the fuel emission coefficient and the first result as the pollutant emissions; wherein, the calculation formula for the pollutant emissions is: ; In the formula, P is the pollutant emission; F is the overall fuel consumption; is the fuel emission coefficient; To treat pollutants efficiently; is the first result. It should be noted that the fuel emission coefficient and pollutant treatment efficiency are known data and can be used directly. Then the product of pollutant emissions and the unit treatment cost of pollutants is used as the environmental protection cost. At this point, the environmental protection cost of the production process is obtained. It should be noted that the unit treatment cost of pollutants has different standards in different regions, and implementers can set it according to actual conditions, which is not limited here.

[0062] Step S4: The function formed by adding the energy consumption cost and the environmental protection cost is used as the objective function.

[0063] The goal of steam production optimization strategy scheduling is to minimize energy consumption and environmental protection costs by regulating the operating parameters of the boiler unit under the condition of meeting the steam supply. Therefore, the goal of obtaining the objective function in this embodiment is to construct a mathematical model. Under the condition of meeting the steam supply in a production process, the smaller the corresponding objective function, the more reasonable the fuel corresponding to each boiler.

[0064] Step S5: According to the predicted steam consumption of the current production process and the objective function, the fuel scheduling strategy of the boiler in the current production process is obtained.

[0065] In order to analyze the fuel scheduling strategy of the boiler in the current production process so as to lower the production cost of the current production process while meeting the overall steam consumption, this embodiment obtains the fuel scheduling strategy of the boiler in the current production process based on the predicted steam consumption and objective function of the current production process.

[0066] In order to ensure that the fuel scheduling strategy of the boilers in the current production process is reasonable, the constraints of the objective function are set in this embodiment as follows: (1) The sum of the actual steam generated by all boilers in the current production process is greater than or equal to the predicted steam consumption of the current production process; energy consumption benchmarking is achieved; (2) The environmental protection cost is less than or equal to the preset maximum environmental protection cost; ensuring that the environmental protection cost is within a controllable range. Among them, the preset maximum environmental protection cost can be set according to the actual situation of the manufacturing enterprise and is not limited here.

[0067] This embodiment predicts the steam consumption of the current production process based on the steam consumption in the historical production process to construct a steam intelligent prediction model; with the goal of ensuring energy consumption benchmarking and environmental protection cost control, a steam production balance optimization model is constructed, and by solving the objective function of the steam production balance optimization model, the fuel scheduling strategy for the boiler unit that minimizes the total cost while ensuring production demand, that is, the control plan for each boiler unit, can be obtained.

[0068] Before the final implementation of the fuel scheduling strategy, in order to further ensure that the fuel scheduling strategy is reasonable, it is also necessary for expert consultants in related fields to diagnose and analyze the above-obtained fuel scheduling strategy. Specifically, by analyzing the above-mentioned steam consumption prediction and steam production, it can be found that, except for the predicted data, the remaining data and other parameters are all determined quantities. Then, this embodiment performs a credibility test on the fuel scheduling strategy. The specific method is: The process of predicting steam consumption is packaged as a scheduling node, and a fourth preset number of scheduling nodes is constructed under the premise of satisfying the constraints of the objective function; in this embodiment, the fourth preset number is set to 60, and the implementer can set the size of the fourth preset number according to the actual situation, which is not limited here. Since the offset of the predicted data of the scheduling node will be different, the secondary node is constructed to perform consistency check on the predicted steam consumption corresponding to the scheduling node to ensure the feasibility of the steam production balance optimization model. Furthermore, in this embodiment, according to the predicted steam consumption corresponding to each scheduling node, the scheduling node is divided by a hierarchical clustering algorithm to obtain the node category. Among them, the hierarchical clustering algorithm is a well-known technology and will not be repeated here. According to the predicted steam consumption of each scheduling node in each node category, the inter-class variance between all node categories is obtained. When the inter-class variance is smaller, the steam production balance optimization model is more reasonable. Then, in this embodiment, the preset inter-class variance threshold is set to 0.3, and the implementer can set the size of the preset inter-class variance threshold according to the actual situation, which is not limited here.

[0069] When the inter-class variance is less than the preset inter-class variance threshold, the steam production balance optimization model is determined to be reasonable, and then the variance of the predicted steam consumption of all scheduling nodes in each node category is obtained as the first variance; the fuel scheduling strategy corresponding to the scheduling node corresponding to the center point of the node category corresponding to the minimum first variance is used as the final fuel scheduling strategy. It should be noted that if there are multiple node categories corresponding to the minimum first variance, the fuel scheduling strategy corresponding to the scheduling node corresponding to the center point of any node category is selected as the final fuel scheduling strategy.

[0070] It should be noted that the clustering parameters and other data in the above consistency test are selected by experts based on actual needs in order to achieve diagnostic results with clear goals.

[0071] At this point, fuel consumption has been rationally managed, resource waste has been avoided, and the production costs of manufacturing companies have been effectively reduced.

[0072] In summary, this embodiment obtains the predicted steam consumption of the current production process based on the steam consumption in the historical production process; obtains the fuel consumption of the boiler in a production process based on the actual amount of steam generated by the boiler and the fuel consumption energy for generating unit steam, as well as the thermal efficiency of the boiler; constructs an objective function based on fuel consumption, start-stop operation cost, fuel unit price, fuel emission coefficient, pollutant treatment efficiency and pollutant unit treatment cost; obtains the fuel scheduling strategy of the boiler in the current production process based on the predicted steam consumption of the current production process and the objective function. The present invention predicts the fuel scheduling strategy of the boiler in the current production process, so that the fuel is reasonably allocated, avoiding waste of resources while effectively reducing the production cost of the enterprise.

[0073] Embodiment 2: The present invention also proposes a digital energy management and control platform, which includes a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute a digital energy consumption management method provided in an embodiment of the present application. The device can be a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a digital energy consumption management method provided in the above embodiment.

[0074] Embodiment 3: The present invention also proposes a digital energy consumption management system, please refer to Figure 4 , which shows a structural diagram of a digital energy consumption management system provided by an embodiment of the present invention, the system includes: a predicted steam consumption acquisition module 10, an energy consumption cost acquisition module 20, an environmental protection cost acquisition module 30, an objective function acquisition module 40 and a fuel scheduling strategy acquisition module 50.

[0075] The predicted steam consumption acquisition module 10 is used to predict the first steam consumption of the process production start and stop period and the second steam consumption of the process production stable operation period of the current production process based on the steam consumption of the process production start and stop period and the steam consumption of the process production stable operation period in the historical production process, and then determine the predicted steam consumption of the current production process.

[0076] The energy consumption cost acquisition module 20 is used to obtain the fuel consumption of each boiler in a production process based on the actual amount of steam generated by each boiler, the fuel consumption energy for generating unit steam, and the thermal efficiency of the boiler; and to obtain the energy consumption cost based on the fuel consumption and start-up and shutdown operation costs of each boiler, as well as the unit price of fuel.

[0077] The environmental cost acquisition module 30 is used to obtain the environmental cost based on the fuel consumption, fuel emission coefficient, pollutant treatment efficiency and unit pollutant treatment cost of each boiler in a production process; wherein the fuel consumption, fuel emission coefficient and unit pollutant treatment cost are all positively correlated with the environmental cost, and the pollutant treatment efficiency is negatively correlated with the environmental cost.

[0078] The objective function acquisition module 40 is used to take the function formed by adding the energy consumption cost and the environmental protection cost as the objective function.

[0079] The fuel scheduling strategy acquisition module 50 is used to acquire the fuel scheduling strategy of the boiler in the current production process according to the predicted steam consumption and the objective function of the current production process.

[0080] It should be noted that: the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the digital energy consumption management system and the digital energy consumption management method embodiment provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0081] Embodiment 4: The present invention also provides a computer device, see Figure 5 The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402, wherein when the processor 402 executes the computer program 403, the computer device can execute any one of the digital energy consumption management methods introduced above.

[0082] Embodiment 5: This embodiment also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement a digital energy consumption management method provided in the above embodiment.

[0083] Embodiment 6: This embodiment further provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the above-mentioned related steps to implement a digital energy consumption management method provided in the above embodiment.

[0084] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.

[0085] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0086] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A digital energy consumption management method, characterized in that: The method comprises the following steps: According to the steam consumption during the process production start and stop period and the steam consumption during the process production stable operation period in the historical production process, the first steam consumption during the process production start and stop period and the second steam consumption during the process production stable operation period of the current production process are predicted to determine the predicted steam consumption of the current production process; In a production process, the fuel consumption of each boiler is obtained based on the actual amount of steam generated by each boiler, the fuel consumption energy per unit of steam generated, and the thermal efficiency of the boiler; the energy consumption cost is obtained based on the fuel consumption of each boiler, the start-up and shutdown operation cost, and the unit price of fuel; The environmental protection cost is obtained based on the fuel consumption, fuel emission coefficient, pollutant treatment efficiency and unit pollutant treatment cost of each boiler in a production process; among them, the fuel consumption, fuel emission coefficient and unit pollutant treatment cost are all positively correlated with the environmental protection cost, and the pollutant treatment efficiency is negatively correlated with the environmental protection cost; The function formed by adding energy consumption cost and environmental protection cost is used as the objective function; According to the predicted steam consumption and objective function of the current production process, the fuel scheduling strategy of the boiler in the current production process is obtained.

2. A digital energy consumption management method as claimed in claim 1, characterized in that: The method for obtaining the first steam consumption is: The process production start and stop periods of the first preset number of historical production processes adjacent to the current production process are all used as the historical process production start and stop periods; The steam consumption during the start and stop periods of historical process production is arranged according to the production order from front to back of the corresponding historical production process to obtain the historical steam consumption sequence during the start and stop periods of process production; According to the historical steam consumption sequence, the steam consumption prediction model for the process production start and stop period is constructed through the ARIMA model to predict the first steam consumption of the process production start and stop period of the current production process.

3. A digital energy consumption management method as claimed in claim 1, characterized in that: The method for obtaining the second steam consumption is: Obtaining a trend reference value according to steam consumption during a period of stable process production operation of a second preset number of historical production processes adjacent to the current production process; Taking the quarter in which the current production process is located as the target quarter, obtaining a seasonal reference value based on the steam consumption during the stable operation period of process production in the third preset number of historical target quarters adjacent to the current production process; The result of normalizing the sum of the trend reference value and the season reference value is used as the time factor characteristic value of the stable operation period of the process production; The time factor characteristic value, external environment factor characteristic value and process factor characteristic value during the stable operation period of process production are used as the input of the long short-term memory network to predict the second steam consumption during the stable operation period of process production in the current production process.

4. A digital energy consumption management method as claimed in claim 3, characterized in that: The method for obtaining the trend reference value is: The steam consumption of a second preset number of historical production processes adjacent to the current production process during the process production stable operation period is constructed into a row matrix as a trend matrix; Obtain the mean value of all steam consumption in the trend matrix as the first reference value; The result of negatively correlating and normalizing the difference between each steam consumption in the trend matrix and the first reference value is used as the first weight of the corresponding steam consumption; Arrange the first weights vertically from left to right in the trend matrix according to the corresponding steam consumption to construct a column matrix as a trend weight matrix; The product of the trend weight matrix and the trend matrix is ​​used as the trend reference value; The method for obtaining the seasonal reference value is: For any historical target quarter, the sum of steam consumption during stable production periods of all processes in the historical target quarter is obtained as the target steam consumption for the historical target quarter; constructing the target steam consumption of the third preset number of historical target quarters adjacent to the current production process into a row matrix as a seasonal matrix; Obtain the mean of all target steam consumptions in the seasonal matrix as a second reference value; The result of negatively correlating and normalizing the difference between each target steam consumption in the seasonal matrix and the second reference value is used as the second weight of the corresponding target steam consumption; Arrange the second weights vertically from left to right in the seasonal matrix according to the corresponding target steam consumption to construct a column matrix as a seasonal weight matrix; The product of the seasonal weight matrix and the seasonal matrix is ​​used as the seasonal reference value.

5. A digital energy consumption management method as claimed in claim 1, characterized in that: The method for obtaining the fuel consumption is: The difference between the thermal enthalpy of steam and the thermal enthalpy of feed water is obtained as the enthalpy difference; The ratio of the enthalpy difference to the unit calorific value of the fuel is taken as the fuel consumption energy for producing unit steam; For any boiler, the ratio of the fuel consumption energy to produce unit steam to the thermal efficiency of the boiler is taken as the actual fuel consumption energy to produce unit steam by the boiler; The product of the actual amount of steam generated by the boiler and the actual fuel consumption energy for generating unit steam is taken as the fuel consumption of the boiler.

6. A digital energy consumption management method as claimed in claim 1, characterized in that: The method for obtaining the energy consumption cost is: For any boiler, the product of the fuel consumption of the boiler and the fuel unit price corresponding to the fuel of the boiler is used as the first fuel cost of the boiler; The sum of the first fuel cost and the start-stop operation cost of the boiler is used as the energy consumption reference cost of the boiler; The relevant results of the energy consumption reference costs of all boilers in a production process are taken as energy consumption costs.

7. A digital energy consumption management method as claimed in claim 1, characterized in that: The method for obtaining the environmental protection cost is: The sum of the fuel consumption of each boiler in a production process is taken as the overall fuel consumption; The negative correlation result of the pollutant treatment efficiency is taken as the first result, and the product of the overall fuel consumption, the fuel emission coefficient and the first result is taken as the pollutant emission; The product of pollutant emissions and the unit cost of pollutant treatment is taken as the environmental protection cost.

8. A digital energy consumption management method as claimed in claim 1, characterized in that: The method for obtaining the fuel scheduling strategy of the boiler in the current production process according to the predicted steam consumption and the objective function of the current production process is: The constraint conditions of the objective function are set as follows: the sum of the actual steam generated by all boilers in the current production process is greater than or equal to the predicted steam consumption of the current production process; The environmental protection cost is less than or equal to the preset maximum environmental protection cost; When the objective function is minimized while satisfying the constraints, the fuel corresponding to each boiler at this time is used as the fuel scheduling strategy for each boiler in the current production process.

9. A digital energy consumption management method as claimed in claim 1, characterized in that: The method for obtaining the predicted steam consumption is: The sum of the first steam consumption and the second steam consumption is used as the predicted steam consumption of the current production process.

10. A digital energy management and control platform, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When executing the computer program, the processor implements the steps of a digital energy consumption management method as described in any one of claims 1 to 9.

Images