Industrial electrical control systems, methods, and media based on the Internet of Things and big data

Abstract

This invention provides an industrial electrical control system, method, and medium based on the Internet of Things and big data, applicable to the field of electrical control technology. By real-time acquisition and preprocessing of full-dimensional operational and environmental data at the edge, this invention reduces data transmission volume. By improving the energy consumption prediction model using a particle swarm optimization long short-term memory network, the accuracy of energy consumption prediction is effectively improved. After generating a target electrical load scheduling scheme through a multi-objective dynamic load optimization model, the electrical automation linkage control unit automatically adjusts the field electrical equipment components according to the target electrical load scheduling scheme. Then, the energy efficiency closed-loop optimization unit optimizes the model parameters based on the actual operating parameters of the automatically adjusted field electrical equipment components, thereby further improving the model processing accuracy, enhancing the precision and automation of electrical equipment control, and meeting the needs of intelligent development.

Description

Technical Field

[0001] This invention relates to the field of electrical control technology, and in particular to an industrial electrical control system, method, and medium based on the Internet of Things and big data. Background Technology

[0002] Industrial electrical equipment, as the core power carrier of industrial production, accounts for more than half of the total energy consumption of industry. However, traditional industrial electrical energy management technologies, which only collect basic electrical parameters such as voltage and current, result in fragmented data perception. Furthermore, existing Long Short-Term Memory (LSTM) networks and inverse ship neural network models rely on manual parameter adjustment, leading to low accuracy in energy consumption model prediction. In addition, load energy consumption optimization focuses solely on reducing energy consumption, resulting in simplistic load scheduling. Moreover, the reliance on manual operation or fixed logic control of individual electrical components after the fact leads to lagging electrical automation linkage and the inability to achieve closed-loop optimization. This results in slow emergency fault response, significant waste of idle energy, and ultimately fails to meet the intelligent development needs of electrical equipment. Summary of the Invention

[0003] The main objective of this invention is to provide an industrial electrical control system, method, and medium based on the Internet of Things and big data, which can effectively improve the accuracy and automation of electrical equipment control, thereby reducing electrical energy consumption and meeting the needs of intelligent development.

[0004] To achieve the above objectives, the present invention provides an industrial electrical control system based on the Internet of Things and big data, the system comprising:

[0005] The Internet of Things (IoT) multimodal sensing unit is used to collect real-time operational data and environmental data of industrial electrical equipment to form the first real-time data.

[0006] An edge data preprocessing unit is used to remove outliers and standardize and reduce the dimensionality of the first real-time data to obtain the second real-time data.

[0007] The big data cloud analysis unit is pre-configured with an improved particle swarm optimization long short-term memory network energy consumption prediction model and a multi-objective dynamic load optimization model. The improved particle swarm optimization long short-term memory network energy consumption prediction model is used to predict electrical energy consumption based on the second real-time data. The multi-objective dynamic load optimization model is used to generate a target electrical load scheduling scheme based on the electrical energy consumption prediction results.

[0008] An electrical automation linkage control unit is connected to the field electrical equipment components and is used to automatically regulate the field electrical equipment components according to the target electrical load scheduling scheme;

[0009] An energy efficiency closed-loop optimization unit is used to optimize the improved particle swarm optimization long short-term memory network energy consumption prediction model and the multi-objective dynamic load optimization model based on the actual operating parameters of the field electrical equipment components after automatic adjustment.

[0010] In some embodiments, the real-time acquisition of full-dimensional operational data and environmental data of industrial electrical equipment includes:

[0011] Obtain the actual operating conditions of industrial electrical equipment;

[0012] The sampling frequency is determined based on the actual operating conditions.

[0013] The industrial electrical system collects comprehensive operational and environmental data based on the sampling frequency.

[0014] The comprehensive operational data includes three-phase voltage or current data, active or reactive power, power factor, harmonic distortion rate, equipment switching status, winding temperature, and dust concentration; the environmental data includes ambient temperature and humidity.

[0015] In some embodiments, obtaining the second real-time data by performing outlier removal and standardization dimensionality reduction on the first real-time data includes:

[0016] Use 3 The criteria involve removing outliers from the first real-time data, followed by data normalization and dimensionality reduction to obtain the second real-time data; the 3 The criterion is that the first real-time data falls within the anomaly detection threshold range; the anomaly detection threshold range is... ;

[0017] in, ;

[0018] ;

[0019] In the formula, This represents the mean of all first-real-time data. represents the standard deviation of all first-real-time data; n represents the total number of first-real-time data. This represents the i-th first real-time data.

[0020] In some embodiments, the step of predicting electrical energy consumption based on the second real-time data includes:

[0021] By improving the particle swarm optimization algorithm, the hyperparameter combinations of the long short-term memory network are traversed.

[0022] The second real-time data is vectorized.

[0023] The vectorized second real-time data is input into the long short-term memory network corresponding to the hyperparameter combination to obtain the electrical energy consumption prediction result.

[0024] In some embodiments, the multi-objective function of the multi-objective dynamic load optimization model is as follows:

[0025] ;

[0026] In the formula, Indicates the total energy consumption target. , Indicates that the i-th electrical device is in Active power at any given time , , The energy consumption coefficient is represented by N; N represents the total number of electrical devices; and T represents the total duration.

[0027] Indicates the target of harmonic distortion. , Indicates the first Second harmonic voltage amplitude H represents the fundamental voltage amplitude, and H represents the total number of times the harmonic voltage amplitude was collected.

[0028] Indicates the overall energy efficiency target. , Indicates the effective output power. Indicates the input electrical power;

[0029] The constraints of the multi-objective dynamic load optimization model include power balance constraints, voltage constraints, and equipment output constraints.

[0030] In some embodiments, the electrical automation linkage control unit includes a primary emergency control module, a secondary optimization control module, and a tertiary control module;

[0031] The primary emergency control module is used to immediately cut off the circuit power supply of electrical equipment and trigger an audible and visual alarm according to the target electrical load dispatching scheme.

[0032] The secondary optimization and control module is used to adjust the frequency of the frequency converter and switch the reactive power compensation device in the electrical equipment according to the target electrical load dispatching scheme.

[0033] The three-level control module is used to reduce the power supply of unloaded equipment in the electrical equipment according to the target electrical load scheduling scheme.

[0034] In some embodiments, the energy efficiency closed-loop optimization unit uses an incremental learning iterative mechanism to optimize the improved particle swarm optimization long short-term memory network energy consumption prediction model and the multi-objective dynamic load optimization model.

[0035] In some embodiments, optimizing the improved particle swarm optimization long short-term memory network energy consumption prediction model and the multi-objective dynamic load optimization model based on the actual operating parameters of the automatically adjusted field electrical equipment components includes:

[0036] The actual energy consumption value is determined based on the actual operating parameters of the on-site electrical equipment components after automatic control.

[0037] The comprehensive energy efficiency coefficient is calculated based on the actual energy consumption value and the standard energy consumption value corresponding to the on-site electrical equipment components.

[0038] When the overall energy efficiency coefficient is less than the energy efficiency coefficient threshold, the incremental learning iteration mechanism is triggered to run.

[0039] Another aspect of the present invention provides an industrial electrical control method based on the Internet of Things and big data, the method comprising the following steps:

[0040] The first real-time data is composed of real-time collection of comprehensive operational data from industrial electrical equipment and environmental data.

[0041] The second real-time data is obtained by removing outliers and standardizing and reducing dimensionality of the first real-time data.

[0042] Based on the second real-time data, an improved particle swarm optimization long short-term memory network energy consumption prediction model is used to predict electrical energy consumption.

[0043] A target electrical load scheduling scheme is generated based on the electrical energy consumption prediction results using a multi-objective dynamic load optimization model;

[0044] The on-site electrical equipment components are automatically controlled according to the target electrical load dispatching scheme;

[0045] The improved particle swarm optimization long short-term memory network energy consumption prediction model and the multi-objective dynamic load optimization model are optimized based on the actual operating parameters of the on-site electrical equipment components after automatic control.

[0046] Another aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described herein.

[0047] The present invention provides the following beneficial effects: Real-time acquisition and preprocessing of full-dimensional operational and environmental data through an IoT multimodal sensing unit and edge data preprocessing unit at the edge reduces data transmission volume and consequently reduces equipment energy consumption. Improving the particle swarm optimization long short-term memory network energy consumption prediction model enhances the accuracy of energy consumption prediction. After generating a target electrical load scheduling scheme through a multi-objective dynamic load optimization model, the electrical automation linkage control unit automatically adjusts the on-site electrical equipment components according to the target electrical load scheduling scheme, effectively improving the precision and automation of electrical equipment control and reducing electrical energy consumption. Furthermore, the energy efficiency closed-loop optimization unit optimizes model parameters based on the actual operating parameters of the automatically adjusted on-site electrical equipment components, further improving model processing accuracy and thus enhancing the precision and automation of electrical equipment control, meeting the needs of intelligent development. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0049] Figure 1 This is a schematic diagram of a module of an industrial electrical control system based on the Internet of Things and big data, provided in an embodiment of this application;

[0050] Figure 2 This is a flowchart of an industrial electrical control method based on the Internet of Things and big data, provided in an embodiment of this application. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0052] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The terms "upper," "lower," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Unless otherwise expressly specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly, for example, as a fixed connection, a detachable connection, or an integral connection; a mechanical connection or an electrical connection; a direct connection or an indirect connection through an intermediate medium; or a connection within two elements. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0053] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class, without limiting the number of objects; for example, a first object can be one or more. Furthermore, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects have an "or" relationship.

[0054] In related technologies, industrial electrical equipment, as the core power carrier of industrial production, accounts for more than half of the total energy consumption of industry. However, traditional industrial electrical energy management technologies have the following problems:

[0055] 1. Fragmented data perception and lack of collaborative acquisition capabilities: Only basic electrical parameters such as voltage and current are collected, without integrating equipment status and environmental parameters. The sampling frequency is fixed, and data loss is severe under abnormal operating conditions, forming data silos.

[0056] 2. Low energy consumption prediction accuracy and poor model adaptability: Traditional LSTM and BP neural network models rely on manual adjustment of hyperparameters, and the prediction error is generally ≥5%, which cannot adapt to the scenarios with large fluctuations in industrial electrical load and complex operating conditions.

[0057] 3. Load dispatching is too simplistic and lacks multi-objective optimization capabilities: It only aims to reduce energy consumption without taking into account harmonic control and energy efficiency maximization, which can easily lead to a decline in power quality and an increase in equipment wear and tear.

[0058] 4. Lagging electrical automation linkage and extensive control: relying on manual operation or fixed logic control, lacking hierarchical and precise control, slow response to emergency faults, and serious waste of no-load energy consumption;

[0059] 5. Lack of closed-loop optimization mechanism leads to continuous energy efficiency degradation: Only single-time scheduling is implemented, and the model and strategy are not iterated based on actual operating data, resulting in a continuous decline in long-term energy efficiency management effectiveness.

[0060] Based on this, the embodiments of this application provide an industrial electrical control system, method and medium based on the Internet of Things and big data, which can effectively improve the accuracy and automation of electrical equipment control, thereby reducing the energy consumption of electrical work and meeting the needs of intelligent development.

[0061] The embodiments of this application will be described in detail below with reference to the accompanying drawings:

[0062] Reference Figure 1 This application provides an industrial electrical control system based on the Internet of Things and big data. The system includes:

[0063] The Internet of Things (IoT) multimodal sensing unit is used to collect real-time operational data and environmental data from industrial electrical equipment to form the first real-time data.

[0064] An edge data preprocessing unit is used to remove outliers and standardize and reduce the dimensionality of the first real-time data to obtain the second real-time data.

[0065] The big data cloud analysis unit is pre-configured with an improved particle swarm optimization long short-term memory network energy consumption prediction model and a multi-objective dynamic load optimization model. The improved particle swarm optimization long short-term memory network energy consumption prediction model is used to predict electrical energy consumption based on second real-time data, and the multi-objective dynamic load optimization model is used to generate target electrical load scheduling schemes based on the electrical energy consumption prediction results.

[0066] An electrical automation linkage control unit is connected to the field electrical equipment components and is used to automatically regulate the field electrical equipment components according to the target electrical load scheduling scheme;

[0067] The energy efficiency closed-loop optimization unit is used to optimize and improve the particle swarm optimization long short-term memory network energy consumption prediction model and the multi-objective dynamic load optimization model based on the actual operating parameters of the field electrical equipment components after automatic regulation, thereby forming a fully closed-loop electrical equipment energy management and control process of acquisition, preprocessing, analysis, regulation and iteration.

[0068] It is understood that the IoT multimodal sensing unit and edge data preprocessing unit in this embodiment can be set at the edge of the electrical equipment application, and the big data cloud analysis unit, electrical automation linkage control unit and energy efficiency closed-loop optimization unit can be set in the cloud. The edge and the cloud can interact with each other via wireless network.

[0069] It is understood that the IoT multimodal sensing unit in this embodiment includes, but is not limited to, voltage and current transformers, power quality analyzers, equipment temperature / vibration sensors, and ambient temperature and humidity sensors. The full-dimensional operational data includes three-phase voltage or current data, active or reactive power, power factor, harmonic distortion rate, equipment switching status, winding temperature, and dust concentration; the environmental data includes ambient temperature and humidity. Specifically, in this embodiment, when collecting full-dimensional operational data and environmental data of industrial electrical equipment, the actual operating conditions of the industrial electrical equipment can be obtained, and the sampling frequency can be determined based on these conditions. For example, when the actual operating conditions are normal, the sampling frequency can be set to 1 time / 5s; when the actual operating conditions are abnormal, the sampling frequency can be set to 1 time / 100ms. This embodiment ensures a balance between data integrity and transmission efficiency by setting different sampling frequencies according to the actual operating conditions.

[0070] It is understood that, after obtaining the first real-time data acquired in real time, this embodiment can perform outlier removal and standardization dimensionality reduction processing on the first real-time data through an edge data preprocessing unit. Specifically, this embodiment uses 3 After outlier removal from the first real-time data, the criteria are followed by data normalization and dimensionality reduction to obtain the second real-time data. (This is from embodiment 3.) The criterion is that the first real-time data falls within the anomaly detection threshold range; the anomaly detection threshold range is... .in, ; ;In the formula, This represents the mean of all first-real-time data. represents the standard deviation of all first-real-time data; n represents the total number of first-real-time data. This represents the i-th first real-time data. This embodiment uses 3... The guidelines preprocess the real-time collected data, which can effectively reduce the amount of data transmitted and thus reduce the energy consumption of the equipment.

[0071] It is understood that the improved particle swarm optimization long short-term memory network energy consumption prediction model in this embodiment includes particle iterative update formulas and fitness functions. The particle velocity and position update formulas are as follows:

[0072] ;

[0073] ;

[0074] In the formula, For the first The first particle Dimensional speed, For the first The first particle Dimensional position; The dynamic nonlinear inertia weight is given by the following formula:

[0075] ;

[0076] =0.9, =0.4; , For adaptive learning factors, , A random number in the range [0,1]. For the optimal position of an individual, The optimal position globally. This represents the current iteration number. This represents the maximum number of iterations.

[0077] The fitness function in this embodiment is as follows:

[0078] ;

[0079] In the formula, To predict energy consumption, This represents the actual energy consumption value. This represents the number of samples.

[0080] In this embodiment, the improved particle swarm optimization long short-term memory network energy consumption prediction model optimizes the number of neurons, learning rate, and batch size hyperparameters of the LSTM (Long Short-Term Neural Network) hidden layer using IPSO (Improved Particle Swarm Optimization). The mean absolute percentage error (MAPE) of energy consumption prediction is ≤1.2%.

[0081] It is understood that, in the process of predicting electrical energy consumption based on the second real-time data, the improved particle swarm optimization long short-term memory network energy consumption prediction model of this embodiment can traverse the hyperparameter combination of the long short-term memory network by improving the particle swarm optimization algorithm, with the goal of minimizing the fitness function. At the same time, the second real-time data is vectorized, and then the hyperparameter combination is substituted into the long short-term memory network. The vectorized second real-time data (including feature vectors such as voltage, power, and temperature) is then input into the current long short-term memory network to perform multi-scale energy consumption prediction and obtain the electrical energy consumption prediction result.

[0082] It is understood that, after obtaining the electrical energy consumption prediction results from the improved particle swarm optimization long short-term memory network energy consumption prediction model, this embodiment generates a target electrical load scheduling scheme based on the electrical energy consumption prediction results through a multi-objective dynamic load optimization model. Specifically, the multi-objective dynamic load optimization model in this embodiment is constructed with the optimization objectives of minimizing total energy consumption, minimizing harmonic distortion rate, and maximizing overall energy efficiency, and uses the following formula to construct a multi-objective function:

[0083] ;

[0084] In the formula, Indicates the total energy consumption target. , Indicates that the i-th electrical device is in Active power at any given time , , The energy consumption coefficient is represented by N; N represents the total number of electrical devices; and T represents the total duration.

[0085] Indicates the target of harmonic distortion. , Indicates the first Second harmonic voltage amplitude H represents the fundamental voltage amplitude, and H represents the total number of times the harmonic voltage amplitude was collected.

[0086] Indicates the overall energy efficiency target. , Indicates the effective output power. This indicates the input electrical power.

[0087] The constraints of the multi-objective dynamic load optimization model in this embodiment include power balance constraints, voltage constraints, and equipment output constraints. Among these, the power balance constraints... Voltage constraint Equipment output constraints . In the formula, and Let represent the total loaded power and power loss of the electrical equipment at time t, respectively. and These represent the minimum and maximum voltage values ​​corresponding to the electrical equipment, respectively. and Let represent the maximum and minimum output power values ​​of the i-th electrical device, respectively.

[0088] It is understood that the electrical automation linkage control unit in this embodiment includes a primary emergency control module, a secondary optimization control module, and a tertiary throttling control module. The primary emergency control module is used to immediately cut off the circuit power supply of electrical equipment and issue audible and visual alarms in response to operating conditions such as leakage, overvoltage, and overtemperature faults, according to the target electrical load scheduling plan. The secondary optimization control module is used to adjust the frequency of the frequency converters in the electrical equipment and switch on and off reactive power compensation devices according to the target electrical load scheduling plan. The tertiary throttling control module is used to automatically reduce the power supply of unloaded equipment in the electrical equipment during low-load periods according to the target electrical load scheduling plan, thereby achieving the control function of reducing unloaded energy consumption.

[0089] It is understood that the energy efficiency closed-loop optimization unit in this embodiment can use an incremental learning iterative mechanism to optimize and improve the particle swarm optimization long short-term memory network energy consumption prediction model and the multi-objective dynamic load optimization model. Specifically, this embodiment can determine the actual energy consumption value based on the actual operating parameters of the field electrical equipment components after automatic adjustment, and then calculate the comprehensive energy efficiency coefficient based on the actual energy consumption value and the standard energy consumption value corresponding to the field electrical equipment components; when the comprehensive energy efficiency coefficient is less than the energy efficiency coefficient threshold, the incremental learning iterative mechanism is triggered. The calculation process of the comprehensive energy efficiency coefficient is as follows:

[0090] ;

[0091] In the formula, η is the overall energy efficiency coefficient. This is the standard energy consumption value. This represents the actual energy consumption value.

[0092] For example, when The model iteration is automatically triggered to update the model weights and load optimization constraint parameters of IPSO-LSTM using an incremental learning iteration mechanism.

[0093] As can be seen from the above, the system of this application embodiment has the following beneficial effects:

[0094] First, by improving the IPSO-LSTM model and dynamically optimizing hyperparameters, the MAPE (mean absolute percentage error) of energy consumption prediction can be less than or equal to 1.2%, which is an improvement in accuracy compared to traditional models.

[0095] Second, through multi-objective optimization and collaborative processing, low energy consumption, low harmonics, and high energy efficiency can be achieved, the harmonic distortion rate of power quality is reduced, and the overall energy efficiency is improved.

[0096] Third, through three-level hierarchical control, the emergency fault response time can be less than or equal to 100ms, thereby reducing no-load energy consumption;

[0097] Fourth, reduce data transmission volume through edge preprocessing and achieve global optimization through cloud-based big data analysis;

[0098] Fifth, through the energy efficiency closed-loop optimization mechanism, the model can be continuously iterated, thereby enabling the energy efficiency management effect to be steadily improved in the long term;

[0099] Sixth, it is compatible with various industrial electrical automation scenarios, requires no large-scale equipment modification, has low deployment costs, and is highly scalable.

[0100] Reference Figure 2 This application provides an industrial electrical control method based on the Internet of Things and big data, which includes, but is not limited to, the following steps:

[0101] Step S210: Collect all dimensions of operational data and environmental data of industrial electrical equipment in real time to form the first real-time data;

[0102] Step S220: After removing outliers and standardizing and reducing dimensionality of the first real-time data, the second real-time data is obtained;

[0103] Step S230: Based on the second real-time data, predict electrical energy consumption by improving the energy consumption prediction model of the long short-term memory network through particle swarm optimization.

[0104] Step S240: Generate a target electrical load dispatching scheme based on the electrical energy consumption prediction results using a multi-objective dynamic load optimization model;

[0105] Step S250: Automatically control the on-site electrical equipment components according to the target electrical load dispatching scheme;

[0106] Step S260: Optimize and improve the particle swarm optimization long short-term memory network energy consumption prediction model and the multi-objective dynamic load optimization model based on the actual operating parameters of the field electrical equipment components after automatic control.

[0107] It is understood that the content of the above system embodiments is applicable to this method embodiment. The specific functions implemented in this method embodiment are the same as those in the above system embodiments, and the beneficial effects achieved are also the same as those achieved in the above system embodiments.

[0108] Furthermore, embodiments of this application also provide a computer-readable storage medium storing a computer program, which is implemented when executed by a processor. Figure 2 The method shown.

[0109] It is understood that the content of the above method embodiments is applicable to this medium embodiment. The specific functions implemented in this medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0110] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0111] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the system described in the various embodiments or some parts of the embodiments.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical coding feature maps; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An industrial electrical control system based on the Internet of Things and big data, characterized in that, The system includes: The Internet of Things (IoT) multimodal sensing unit is used to collect real-time operational data and environmental data of industrial electrical equipment to form the first real-time data. An edge data preprocessing unit is used to perform outlier removal and standardization dimensionality reduction on the first real-time data to obtain the second real-time data. The big data cloud analysis unit is pre-configured with an improved particle swarm optimization long short-term memory network energy consumption prediction model and a multi-objective dynamic load optimization model. The improved particle swarm optimization long short-term memory network energy consumption prediction model is used to predict electrical energy consumption based on the second real-time data. The multi-objective dynamic load optimization model is used to generate a target electrical load scheduling scheme based on the electrical energy consumption prediction results. An electrical automation linkage control unit is connected to the field electrical equipment components and is used to automatically regulate the field electrical equipment components according to the target electrical load scheduling scheme; An energy efficiency closed-loop optimization unit is used to optimize the improved particle swarm optimization long short-term memory network energy consumption prediction model and the multi-objective dynamic load optimization model based on the actual operating parameters of the field electrical equipment components after automatic adjustment.

2. The system according to claim 1, characterized in that, The real-time acquisition of comprehensive operational and environmental data from industrial electrical equipment includes: Obtain the actual operating conditions of industrial electrical equipment; The sampling frequency is determined based on the actual operating conditions. The industrial electrical system collects comprehensive operational and environmental data based on the sampling frequency. The comprehensive operational data includes three-phase voltage or current data, active or reactive power, power factor, harmonic distortion rate, equipment switching status, winding temperature, and dust concentration; the environmental data includes ambient temperature and humidity.

3. The system according to claim 1, characterized in that, The process of removing outliers and standardizing / reducing dimensionality from the first real-time data to obtain the second real-time data includes: Adopt 3 The criteria involve removing outliers from the first real-time data, followed by data normalization and dimensionality reduction to obtain the second real-time data; the 3 The criterion is that the first real-time data falls within the anomaly detection threshold range; the anomaly detection threshold range is... ; in, ; ； In the formula, This represents the mean of all first-real-time data. represents the standard deviation of all first-real-time data; n represents the total number of first-real-time data. This represents the i-th first real-time data.

4. The system according to claim 1, characterized in that, The step of predicting electrical energy consumption based on the second real-time data includes: By improving the particle swarm optimization algorithm, the hyperparameter combinations of the long short-term memory network are traversed. The second real-time data is vectorized. The vectorized second real-time data is input into the long short-term memory network corresponding to the hyperparameter combination to obtain the electrical energy consumption prediction result.

5. The system according to claim 1, characterized in that, The multi-objective function of the multi-objective dynamic load optimization model is as follows: ； In the formula, Indicates the total energy consumption target. , Indicates that the i-th electrical device is in Active power at any given time , , The energy consumption coefficient is represented by N; N represents the total number of electrical devices; and T represents the total duration. Indicates the target of harmonic distortion. , Indicates the first Second harmonic voltage amplitude H represents the fundamental voltage amplitude, and H represents the total number of times the harmonic voltage amplitude was collected. Indicates the overall energy efficiency target. , Indicates the effective output power. Indicates input electrical power; The constraints of the multi-objective dynamic load optimization model include power balance constraints, voltage constraints, and equipment output constraints.

6. The system according to claim 1, characterized in that, The electrical automation linkage control unit includes a primary emergency control module, a secondary optimization control module, and a tertiary control module. The primary emergency control module is used to immediately cut off the circuit power supply of electrical equipment and trigger an audible and visual alarm according to the target electrical load dispatching scheme. The secondary optimization and control module is used to adjust the frequency of the frequency converter and switch the reactive power compensation device in the electrical equipment according to the target electrical load dispatching scheme. The three-level control module is used to reduce the power supply of unloaded equipment in the electrical equipment according to the target electrical load scheduling scheme.

7. The system according to claim 1, characterized in that, The energy efficiency closed-loop optimization unit uses an incremental learning iterative mechanism to optimize the improved particle swarm optimization long short-term memory network energy consumption prediction model and the multi-objective dynamic load optimization model.

8. The system according to claim 7, characterized in that, The optimization of the improved particle swarm optimization long short-term memory network energy consumption prediction model and the multi-objective dynamic load optimization model based on the actual operating parameters of the field electrical equipment components after automatic adjustment includes: The actual energy consumption value is determined based on the actual operating parameters of the on-site electrical equipment components after automatic control. The comprehensive energy efficiency coefficient is calculated based on the actual energy consumption value and the standard energy consumption value corresponding to the on-site electrical equipment components. When the overall energy efficiency coefficient is less than the energy efficiency coefficient threshold, the incremental learning iteration mechanism is triggered to run.

9. An industrial electrical control method based on the Internet of Things and big data, characterized in that, The method includes the following steps: The first real-time data is composed of real-time collection of comprehensive operational data from industrial electrical equipment and environmental data. The second real-time data is obtained by removing outliers and standardizing and reducing dimensionality of the first real-time data. Based on the second real-time data, an improved particle swarm optimization long short-term memory network energy consumption prediction model is used to predict electrical energy consumption. A target electrical load scheduling scheme is generated based on the electrical energy consumption prediction results using a multi-objective dynamic load optimization model; The on-site electrical equipment components are automatically controlled according to the target electrical load dispatching scheme; The improved particle swarm optimization long short-term memory network energy consumption prediction model and the multi-objective dynamic load optimization model are optimized based on the actual operating parameters of the on-site electrical equipment components after automatic control.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of claim 9.

Images