Special paper-based new material energy consumption monitoring and intelligent management platform

Abstract

The invention discloses a special paper-based new material energy consumption monitoring and intelligent management platform, belongs to the technical field of energy-saving intelligent management, and can solve the technical problem that the energy consumption of a special paper-based new material cannot be accurately monitored and intelligently managed in a traditional energy consumption monitoring system. The method adopted by the management platform comprises the steps of obtaining energy consumption and load conditions in a historical period, and forming an energy consumption and load data set; establishing a grey prediction model; adjusting the grey prediction model by using a particle swarm optimization algorithm; obtaining a prediction data set through the material energy consumption and the load data set by using a grey prediction model; and adjusting an execution strategy of the management platform according to the prediction data set.

Description

Technical Field

[0001] The present invention relates to the field of intelligent management technology, in particular to the field of energy-saving intelligent management technology. Background Art

[0002] As the requirements for energy conservation and environmental protection in industrial production continue to increase, the demand for energy consumption monitoring in the production and management of various new materials is increasing. As a widely used environmentally friendly material, special paper-based new materials are gradually being widely used in packaging, construction, electronics and other fields due to their good mechanical properties, degradability and weather resistance. However, the production process of special paper-based materials usually involves complex process flows and high-energy consumption equipment, and its energy consumption distribution is dynamic and volatile, making it difficult to accurately monitor and manage.

[0003] Existing energy consumption monitoring systems are mostly used for general industrial materials. For materials with special physical and chemical properties such as special paper-based materials, their ability to capture and analyze energy consumption characteristics is relatively limited. In addition, traditional energy consumption monitoring methods mainly rely on fixed energy consumption models and manual experience, which are difficult to adapt to the real-time changing load and energy consumption requirements during the production process, and cannot achieve refined management of energy consumption. This situation leads to increased waste of resources in the production process, rising production costs, and difficulty in meeting the goals of energy conservation and emission reduction.

[0004] Therefore, there is an urgent need for an energy consumption monitoring platform based on advanced intelligent management technology, which uses cloud computing, the Internet of Things, data analysis and predictive models to achieve real-time monitoring, load analysis and intelligent management of energy consumption in the production process of special paper-based new materials, so as to achieve the goal of optimizing production processes, reducing energy consumption and reducing environmental pollution. Summary of the invention

[0005] The technical problem to be solved by the embodiments of the present invention is to provide an energy consumption monitoring and intelligent management platform for special paper-based new materials, which takes into account real-time monitoring of energy consumption and load optimization management, can accurately predict energy consumption trends and optimize resource allocation, thereby achieving the purpose of reducing energy consumption, improving production efficiency, and reducing resource waste.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides an energy consumption monitoring and intelligent management platform for special paper-based new materials. The intelligent management platform uses cloud computing to predict and monitor energy consumption, including the following steps:

[0007] S1 obtains the energy consumption and load conditions in the historical period to form an energy consumption and load data set;

[0008] S2 establishes a grey prediction model;

[0009] S3 uses particle swarm optimization algorithm to adjust the grey prediction model;

[0010] S4 uses the grey prediction model to obtain the prediction data set through the material energy consumption and load data set;

[0011] S5 adjusts the execution strategy of the energy management platform based on the predicted data set.

[0012] In step S1 , the energy consumption and load data set includes but is not limited to processor load, energy consumption status, production usage, material load, and production line flow.

[0013] The establishment of grey prediction model in S2 includes:

[0014] S21 performs cumulative generation processing on the energy consumption and load data sets to form the initial cumulative sequence x of the grey prediction model. (1) ;

[0015] S22 obtains the initial accumulation sequence x (1) The grey derivative dx (1) (i) Construct the mean generating sequence:

[0016]

[0017] z (1) (i) is the i-th element of the mean generating sequence, x (1) (i) and x (1) (i-1) is the initial cumulative sequence x (1) The values ​​of the i-th and i-1-th in ;

[0018] S23 uses the mean value to generate the series and the grey derivative to establish the grey prediction model differential equation:

[0019] dx (1) (i)+a·z (1) (i) = b

[0020] where dx (1) (i) is the grey derivative, z (1) (i) is the mean generating sequence, a and b are adjustment parameters.

[0021] Step S3 specifically includes:

[0022] S31 initializes the particle swarm, sets the value ranges of adjustment parameters a and b to the upper and lower bounds of the initial value range of the particle swarm, and obtains random initial values ​​by taking random numbers;

[0023] S32 controls the particle to move to a new position: Among them, the position update speed is: is the velocity of the particle at time t+1, is the position of the particle at time t+1, c1 and c2 are learning factors, and rand() is a random number between [0, 1]. is the optimal position of the particle in the individual, is the global optimal position.

[0024] The learning factors c1 and c2 are obtained using a fuzzy logic controller:

[0025] S321 obtains the global optimal change rate:

[0026]

[0027] in is the global optimal solution of the tth iteration;

[0028] Get the particle swarm distribution convergence:

[0029]

[0030] Where N is the number of particles, x i is the position of the ith particle, and x is the average value.

[0031] S322 fuzzifies the input variables ΔG and D into fuzzy sets: {Low, Medium, High}, establishes a rule base, converts the input variables into fuzzy outputs, and the rule base includes the mapping relationship between the input variables and the fuzzy outputs and the input variables and the fuzzy outputs;

[0032] S323 performs fuzzy reasoning to obtain the membership of the fuzzy set, and performs defuzzification based on the membership:

[0033]

[0034] Among them, μ rulei is the membership degree of the ith rule, c 1,i With c 2,i is the learning factor output value of the i-th rule.

[0035] Step S4 specifically includes:

[0036] The learning factors c1 and c2 are used to obtain the optimal combination of ab through the particle swarm algorithm, and the prediction and evaluation are performed through the grey model. The prediction formula is:

[0037]

[0038] Get the predicted series X through the prediction formula (1) .

[0039] On the other hand, an embodiment of the present invention provides an energy consumption monitoring and intelligent management system for special paper-based new materials. The energy consumption monitoring and intelligent management system for special paper-based new materials includes: a data set acquisition module, a gray prediction model module, a particle swarm algorithm module, an algorithm adjustment module, and an optimization strategy execution module. The data set acquisition module executes: acquiring energy consumption and load conditions in a historical period to form an energy consumption and load data set; the gray prediction model module executes: establishing a gray prediction model; the particle swarm algorithm module executes: using a particle swarm optimization algorithm to adjust the gray prediction model; the algorithm adjustment module executes: using the gray prediction model to obtain a prediction data set through the material energy consumption and load data set; the optimization strategy execution module executes: adjusting the execution strategy of the energy management platform according to the prediction data set.

[0040] Implementing the embodiments of the present invention has the following beneficial effects:

[0041] Real-time monitoring and precise control: Through the real-time monitoring function of the platform, the energy consumption in the production process of special paper-based new materials can be accurately monitored and data collected to ensure the timeliness and accuracy of energy consumption data.

[0042] Improve the accuracy of energy consumption prediction: The grey prediction model and particle swarm optimization algorithm are used to intelligently analyze energy consumption data, which improves the accuracy of energy consumption prediction and enables the management system to predict high energy consumption periods in advance and take countermeasures.

[0043] Optimize resource allocation: The platform dynamically adjusts the allocation and scheduling of production resources based on energy consumption load forecast results, realizes intelligent optimization of energy consumption, reduces resource waste, and reduces production costs.

[0044] Improve production efficiency: By monitoring and managing key indicators such as equipment load and production line flow, the overall efficiency of the production process is effectively improved, and downtime and unnecessary equipment losses are reduced.

[0045] Support energy conservation and emission reduction goals: The platform reduces energy consumption and carbon emissions by reducing production energy consumption and optimizing management, which helps enterprises achieve energy conservation and emission reduction goals and meet the requirements of environmental protection and sustainable development.

[0046] Enhanced system flexibility: The platform is designed to be highly adaptable and can flexibly adjust monitoring and management parameters according to the different production processes and load requirements of specialty paper-based materials to meet diverse production needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A schematic diagram of a special paper-based new material energy consumption monitoring and intelligent management platform provided in an embodiment of the present application using cloud computing to predict and monitor energy consumption. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0049] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0050] like Figure 1 As shown, the method includes: obtaining energy consumption and load conditions in a historical period to form an energy consumption and load data set; establishing a grey prediction model; using a particle swarm optimization algorithm to adjust the grey prediction model; using the grey prediction model to obtain a prediction data set through material energy consumption and load data sets; and adjusting the execution policy of the energy management platform according to the prediction data set.

[0051] In conjunction with the accompanying drawings, a special paper-based new material energy consumption monitoring and intelligent management platform provided in the embodiments of the present application is described in detail through specific embodiments and application scenarios.

[0052] like Figure 1 As shown, the present application provides a method for predicting and monitoring energy consumption of a special paper-based new material energy consumption monitoring and intelligent management platform using cloud computing. The method may include the following steps S1 to S6.

[0053] Step S1 obtains the energy consumption and load conditions in the historical period to form an energy consumption and load data set;

[0054] Specifically, the energy consumption and load data set includes, but is not limited to, processor load, energy consumption status, production usage, material load, and production line flow.

[0055] Preferably, the energy consumption and load data sets are organized based on fixed time intervals to form a data set with a time series structure, which is convenient for subsequent analysis and processing. By setting the time interval T, the energy consumption data and load data in the historical period are divided according to the time series X = {x1, x2, x3, ..., xn}, where xi represents the data point in the i-th time period. This processing method not only improves the structuring of the data, but also provides an accurate time reference for subsequent model training and predictive analysis.

[0056] Step S2 establishes a grey prediction model;

[0057] Specifically, it also includes steps S21 to S23:

[0058] S21 performs cumulative generation processing on the energy consumption and load data sets to form the initial cumulative sequence x of the grey prediction model. (1) ;

[0059] S22 obtains the initial accumulation sequence x (1) The grey derivative dx (1) (i) Construct the mean generating sequence:

[0060]

[0061] z (1) (i) is the i-th element of the mean generating sequence, x (1) (i) and x (1) (i-1) is the initial cumulative sequence x (1) The values ​​of the i-th and i-1-th in ;

[0062] S23 uses the mean value to generate the series and the grey derivative to establish the grey prediction model differential equation:

[0063] dx (1) (i)+a·z (1) (i) = b

[0064] where dx (1) (i) is the grey derivative, z (1) (i) is the mean generating sequence, a and b are adjustment parameters.

[0065] Step S3 uses particle swarm optimization algorithm to adjust the grey prediction model;

[0066] Specifically, it also includes S31 to S32, wherein S32 includes steps S321 to S323.

[0067] S31 initializes the particle swarm, sets the value ranges of adjustment parameters a and b to the upper and lower bounds of the initial value range of the particle swarm, and obtains random initial values ​​by taking random numbers;

[0068] S32 controls the particle to move to a new position: Among them, the position update speed is: is the velocity of the particle at time t+1, is the position of the particle at time t+1, c1 and c2 are learning factors, and rand() is a random number between [0, 1]. is the optimal position of the particle in the individual, is the global optimal position.

[0069] S321 obtains the global optimal change rate:

[0070]

[0071] in is the global optimal solution of the tth iteration;

[0072] Get the particle swarm distribution convergence:

[0073]

[0074] Where N is the number of particles, x i is the position of the ith particle, and x is the average value.

[0075] S322 fuzzifies the input variables ΔG and D into fuzzy sets: {Low, Medium, High}, establishes a rule base, converts the input variables into fuzzy outputs, and the rule base includes the mapping relationship between the input variables and the fuzzy outputs and the input variables and the fuzzy outputs;

[0076] Specifically, a rule base is established based on experience or experiments to determine the mapping relationship from fuzzy input to fuzzy output. For example:

[0077] If ΔG is Low and D is High, then c1 is high and c2 is low (encouraging exploration);

[0078] If ΔG is High and D is Low, c1 is low and c2 is high (encouraging development).

[0079] S323 performs fuzzy reasoning to obtain the membership of the fuzzy set, and performs defuzzification based on the membership:

[0080]

[0081] Among them, μ rule i is the membership degree of the ith rule, c 1,i With c 2,i is the learning factor output value of the i-th rule.

[0082] Specifically, the Min-Max method or the product rule method is used for fuzzy reasoning.

[0083] IF ΔG is Low AND D is High THEN c 1 =High,c 2 =Low

[0084] For example, for the rule of “ΔG is Low, D is High”, the minimum value is used as the membership degree of the rule.

[0085] Furthermore, in order to improve the adaptability of the particle swarm at different optimization stages, the learning factors c1 and c2 can be set as dynamically adjusted adaptive parameters, that is, they are gradually updated with the iteration process and convergence of the particle swarm to achieve stronger exploration capabilities in the early stage of optimization and more concentrated development capabilities in the later stage. This adaptive adjustment can be based on the changes in the global optimal change rate ΔG and the particle distribution convergence degree D, and improve the optimization effect through the dynamic balance between exploration and development.

[0086] In addition, a stopping criterion can be introduced, such as setting the particle swarm iteration to stop when the rate of change of the global optimal solution ΔG is less than a certain threshold and the particle swarm distribution convergence D is close to zero. This criterion can prevent the algorithm from falling into invalid iterations, save computing resources and speed up convergence.

[0087] Step S4 uses a grey prediction model to obtain a prediction data set through material energy consumption and load data sets;

[0088] Specifically, the learning factors c1 and c2 are used to obtain the optimal combination of ab through the particle swarm algorithm, and the grey model is used for prediction and evaluation. The prediction formula is:

[0089]

[0090] Get the predicted series X through the prediction formula (1) .

[0091] Step S5 adjusts the execution strategy of the energy management platform according to the predicted data set.

[0092] Preferably, in step S5, the execution strategy of the energy management platform is dynamically adjusted according to the forecast data set to achieve optimal control of energy consumption. Specifically, the forecast data set provides energy consumption trends and load changes in future time periods. The platform can perform resource allocation and strategy adjustments in advance based on this information to achieve the goal of energy saving and efficiency improvement. Furthermore, the platform can take the following optimization measures:

[0093] Dynamic load balancing Based on the predicted peak and valley periods of energy consumption, the platform can automatically adjust the workload of different production equipment or system modules, disperse high-energy consumption tasks to low-energy consumption periods, balance the overall energy consumption, and avoid excessive instantaneous energy consumption peaks.

[0094] Early warning mechanism If the forecast data set shows that abnormal energy consumption or excessive load is about to occur, the platform can issue an early warning to remind relevant managers to take countermeasures. In addition, the system can automatically trigger preset energy consumption control strategies, such as reducing the power of some equipment or suspending non-critical tasks to ensure the stability of the overall system.

[0095] Resource Scheduling Optimization Based on the forecast data set, the platform can adjust the resource scheduling of the production line, such as limiting the number of production lines running during periods of high energy consumption, or concentrating high-energy consumption processing during periods of low energy consumption. This can make full use of resources during low-energy consumption periods, improve production efficiency and reduce unit energy consumption costs.

[0096] Adaptive control strategy

[0097] Combining real-time monitoring data with forecast data, the platform can implement adaptive control strategies. Specifically, the platform can dynamically adjust control parameters (such as temperature, pressure, speed, etc.) according to the forecast values, so that the equipment always runs at the optimal energy consumption level to reduce unnecessary energy waste.

[0098] Intelligent deployment of energy sources

[0099] In scenarios with multiple energy sources (such as electricity, solar energy, and natural gas), the platform can intelligently select energy supply methods based on energy consumption forecast results. For example, it can prioritize the use of lower-cost energy during peak energy consumption periods, or store renewable energy when the load is low to provide support for subsequent high-energy consumption periods.

[0100] Decision support and report generation

[0101] The platform can convert the forecast results into visual reports and charts to provide decision support for management. These reports may include energy consumption trend analysis, equipment efficiency, load forecast, etc., providing data basis for management's energy consumption management and optimization. At the same time, the system can generate reports according to the set period to facilitate long-term energy consumption optimization strategy adjustment and effect evaluation.

[0102] Furthermore, the platform's execution strategy can achieve closed-loop optimization, that is, after each execution of the strategy, the system will re-collect and analyze the actual energy consumption data to verify the accuracy of the prediction and the effectiveness of the strategy. If the actual result deviates greatly from the prediction, the platform will automatically update the prediction model and execution strategy to improve the subsequent prediction accuracy and management effect.

[0103] A special paper-based new material energy consumption monitoring and intelligent management system, the special paper-based new material energy consumption monitoring and intelligent management system comprises: a data set acquisition module, a grey prediction model module, a particle swarm algorithm module, an algorithm adjustment module, and an optimization strategy execution module. The data set acquisition module executes: acquiring energy consumption and load conditions in a historical period to form an energy consumption and load data set; the grey prediction model module executes: establishing a grey prediction model; the particle swarm algorithm module executes: using a particle swarm optimization algorithm to adjust the grey prediction model; the algorithm adjustment module executes: using the grey prediction model to obtain a prediction data set through a material energy consumption and load data set; the optimization strategy execution module executes: adjusting the execution strategy of an energy management platform according to the prediction data set.

[0104] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of each embodiment of the present application.

[0105] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A special paper-based new material energy consumption monitoring and intelligent management platform, the management platform uses cloud computing to predict and monitor energy consumption, characterized in that: The method adopted by the management platform includes: S1 obtains the energy consumption and load conditions in the historical period to form an energy consumption and load data set; S2 establishes a grey prediction model; S3 uses a particle swarm optimization algorithm to adjust the grey prediction model; S4 uses the grey prediction model to obtain a prediction data set through the material energy consumption and load data set; S5: adjusting the execution strategy of the energy management platform according to the predicted data set.

2. The energy consumption monitoring and intelligent management platform for special paper-based new materials according to claim 1 is characterized in that: In the step S1, the energy consumption and load data set includes but is not limited to processor load, energy consumption status, production usage, material load, and production line flow.

3. The energy consumption monitoring and intelligent management platform for special paper-based new materials according to claim 1 is characterized in that: The establishment of the grey prediction model in S2 includes: S21 performs accumulation generation processing on the energy consumption and load data sets to form an initial accumulation sequence x of the grey prediction model. (1) ; S22 obtains the initial accumulation sequence x (1) The grey derivative dx (1) (i) Construct the mean generating sequence: z (1) (i) is the i-th element of the mean generating sequence, x (1) (i) and x (1) (i-1) is the initial accumulation sequence x (1) The values ​​of the i-th and i-1-th in ; S23 uses the mean value generation sequence and the grey derivative to establish the grey prediction model differential equation: dx (1) (i)+a·z (1) (i)=b where dx (1) (i) is the grey derivative, z (1) (i) is the mean generating sequence, a and b are the adjustment parameters.

4. The energy consumption monitoring and intelligent management platform for special paper-based new materials according to claim 3 is characterized in that: The step S3 specifically includes: S31 initializes the particle swarm, sets the value ranges of the adjustment parameters a and b to the upper and lower bounds of the initial value range of the particle swarm, and obtains a random initial value by taking a random number; S32 controls the particle to move to a new position: Among them, the position update speed is: is the velocity of the particle at time t+1, is the position of the particle at time t+1, c1 and c2 are learning factors, rand() is a random number between [0, 1], is the optimal position of the particle in the individual, is the global optimal position.

5. The energy consumption monitoring and intelligent management platform for special paper-based new materials according to claim 4 is characterized in that: The learning factors c1 and c2 are obtained using a fuzzy logic controller: S321 obtains the global optimal change rate: in is the global optimal solution of the tth iteration; Get the particle swarm distribution convergence: Where N is the number of particles, x i is the position of the ith particle, and x is the average value. S322 fuzzifies the input variables ΔG and D into a fuzzy set: {Low, Medium, High}, establishes a rule base, and converts the input variables into fuzzy outputs, wherein the rule base includes a mapping relationship between the input variables and the fuzzy outputs and between the input variables and the fuzzy outputs; S323 performs fuzzy reasoning to obtain the membership of the fuzzy set, and performs defuzzification according to the membership: Among them, μ rulei is the membership degree of the ith rule, c 1,i With c 2,i is the learning factor output value of the i-th rule.

6. The energy consumption monitoring and intelligent management platform for special paper-based new materials according to claim 4 is characterized in that: The step S4 specifically includes: The learning factors c1 and c2 are used to obtain the optimal combination of ab through the particle swarm algorithm, and the prediction and evaluation are performed through the grey model. The prediction formula is: The prediction series X is obtained by the prediction formula (1) .

Images