Fully mechanized coal mining face equipment power load monitoring method and electronic equipment
By obtaining the power load data of the comprehensive mining working face equipment, establishing a type identification model and optimizing the electricity cost, it solves the problem of inability to monitor the equipment's electricity consumption data in real time and the difference in electricity bills, and realizes the electricity consumption control and electricity bill optimization of the comprehensive mining working face equipment. , improves electricity efficiency and reduces costs.
Patent Information
- Application Number
- CN202411023033.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-29
- Publication Date
- 2024-11-15
AI Technical Summary
The electricity consumption data of comprehensive mining working face equipment cannot be monitored in real time, and the difference in electricity bills of power consumption equipment at different times leads to the inability to participate in complex power load characteristics monitoring and peak-to-valley optimization regulation.
By obtaining the power load data of multiple devices in the comprehensive mining working face, establishing a type identification model, calculating the optimal daily total electricity cost, setting up a mixed integer nonlinear planning model to optimize the electricity cost, and solving it under constraints, and finally achieving the Regulation of equipment electricity use.
Real-time monitoring of electricity consumption data of comprehensive mining working face equipment and calculation of optimal electricity cost are realized, helping enterprises improve the efficiency of electricity consumption, reduce electricity consumption costs, extend equipment life, and promote enterprises to reduce consumption and increase efficiency.
Smart Images

Figure CN118966920A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field related to coal mines, and in particular to a method for monitoring the electric load of fully mechanized working face equipment, electronic equipment, storage medium and computer program product. Background Art
[0002] The energy and power sector shoulders important tasks in the work of carbon peak and carbon neutrality. It has become an inevitable trend to do a good job in the "dual control" of energy consumption and improve the level of power demand side management.
[0003] Promoting the construction of an integrated power management system for fully mechanized mining faces is the basis and prerequisite for coal enterprises to optimize the power energy management system and improve management and energy conservation.
[0004] However, the current power load characteristics monitoring and peak-valley optimization and control system for key equipment in comprehensive mining working faces is prone to problems such as the inability to monitor equipment power consumption data in real time. At the same time, due to the differences in electricity charges for equipment in different time periods, it is unable to participate in the complex power load characteristics monitoring and peak-valley optimization and control of key equipment in comprehensive mining working faces. Summary of the invention
[0005] Based on this, it is necessary to provide a method, electronic equipment, storage medium and computer program product for monitoring the power load of comprehensive mining working face equipment in order to address the technical problem that the existing technology cannot monitor the power consumption data of comprehensive mining working face equipment.
[0006] The present invention provides a method for monitoring power load of fully mechanized mining working face equipment, comprising:
[0007] Obtain power load data of multiple equipment in fully mechanized mining face;
[0008] Inputting the power load data of each device into a type identification model to obtain the power load type of each device;
[0009] Calculate the optimal total daily electricity cost for the fully mechanized mining face.
[0010] Furthermore, it also includes:
[0011] Acquire training power load data and a training power load type corresponding to the training power load data;
[0012] Training is performed based on the training power load data and the training power load type to establish a type recognition model, and the type recognition model establishes a mapping relationship between the power load data and the power load type.
[0013] Furthermore, the calculation of the optimal daily total electricity cost of the fully mechanized mining face includes:
[0014] The objective function of the mixed integer nonlinear programming model is set to minimize the total daily electricity cost of the fully mechanized mining face;
[0015] The mixed integer nonlinear programming model is solved to obtain the optimal daily total electricity cost.
[0016] Furthermore, solving the mixed integer nonlinear programming model to obtain the optimal daily total electricity cost includes:
[0017] The mixed integer nonlinear programming model is solved based on the constraints to obtain the optimal daily total electricity cost.
[0018] Furthermore, solving the mixed integer nonlinear programming model based on constraints to obtain the optimal daily total electricity cost includes:
[0019] For each device, the constraint is set as follows: after adopting the optimal value of the peak-valley time-of-use electricity price, the average value of the load during the peak period is greater than the average value of the load during the valley period;
[0020] The mixed integer nonlinear programming model is solved based on the constraints to obtain the optimal daily total electricity cost.
[0021] Furthermore, the setting of the constraint that the average value of the load during the peak period is greater than the average value of the load during the valley period after the peak-valley time-of-use electricity price is implemented includes:
[0022] For each device, set the constraint to
[0023] y+(1-b)·M≥z≥y-(1-b)·M
[0024] b·M≥y
[0025] Among them, z is the optimal value of the peak and valley time-of-use electricity price of the equipment, b is the constant corresponding to each equipment, M is the maximum electricity price, and y is the mean value of the peak and valley time-of-use electricity price.
[0026] Furthermore, the setting of the constraint that the average value of the load during the peak period is greater than the average value of the load during the valley period after the peak-valley time-of-use electricity price is implemented also includes:
[0027] The constant corresponding to each device is set to the constant corresponding to the power load type of the device.
[0028] The present invention provides an electronic device, comprising:
[0029] at least one processor; and,
[0030] a memory communicatively connected to at least one of the processors; wherein,
[0031] The memory stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the method for monitoring the power load of the comprehensive mining working face equipment as described above.
[0032] The present invention provides a storage medium, which stores computer instructions. When a computer executes the computer instructions, it is used to execute all steps of the method for monitoring the power load of comprehensive mining working face equipment as described above.
[0033] The present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-mentioned method for monitoring the power load of equipment in a comprehensive mining working face.
[0034] The present invention obtains the power load data of multiple equipment in the comprehensive mining working face, inputs the power load data of each equipment into the type recognition model, and obtains the power load type of each equipment, thereby realizing the monitoring of the power consumption data of the comprehensive mining working face equipment. At the same time, by calculating the optimal daily total electricity cost of the comprehensive mining working face, the enterprise can understand its optimal daily total electricity cost, and regulate the power consumption of the comprehensive mining working face equipment according to the optimal daily electricity cost, which is of great significance to improving the efficiency of power consumption, reducing the electricity cost of the enterprise, extending the life of the equipment, and promoting the enterprise to reduce consumption and increase efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] Figure 1 This is a working flow chart of a method for monitoring power load of equipment in a fully mechanized mining face according to an embodiment of the present invention;
[0036] Figure 2 This is a work flow chart of a method for monitoring power load of equipment in a fully mechanized mining face according to another embodiment of the present invention;
[0037] Figure 3 A power supply circuit diagram of a fully mechanized mining face as an example of the present invention;
[0038] Figure 4 A design diagram of a power load collection device according to an example of the present invention;
[0039] Figure 5 This is a network structure diagram of an ELM model of an example of the present invention;
[0040] Figure 6 The single load recognition performance comparison of three activation functions is an example of the present invention;
[0041] Figure 7 The single load recognition rate of different numbers of hidden layer neurons for an example of the present invention;
[0042] Figure 8A flow chart of power load identification based on ELM as an example of the present invention;
[0043] Fig. 9 An object-oriented analysis process model as an example of the present invention;
[0044] Fig.10 The figure is a schematic diagram of the hardware structure of an electronic device of the present invention. DETAILED DESCRIPTION
[0045] The specific embodiments of the present invention are further described below in conjunction with the accompanying drawings. The same components are represented by the same reference numerals. It should be noted that the words "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to directions in the accompanying drawings, and the words "inner" and "outer" refer to directions toward or away from the geometric center of a specific component, respectively.
[0046] like Figure 1 The figure shows a working flow chart of a method for monitoring power load of equipment in a fully mechanized mining face according to an embodiment of the present invention, comprising:
[0047] Step S101, obtaining power load data of multiple devices in a fully mechanized mining face;
[0048] Step S102, inputting the power load data of each device into a type identification model to obtain the power load type of each device;
[0049] Step S103, calculating the optimal daily total electricity cost of the fully mechanized mining face.
[0050] Specifically, the present invention can be applied to electronic devices with processing capabilities, such as computers, host computers, etc.
[0051] The present invention provides a method for monitoring the power load characteristics of key equipment in a fully mechanized mining face and optimizing the peak-valley control. The method aims to clarify the power load characteristics of key equipment in a fully mechanized mining face, find out the peak-valley optimization control measures, establish a power monitoring demand plan for key equipment in a fully mechanized mining face of a coal mine, establish a technical plan for power monitoring of key equipment, develop a power load characteristic monitoring system for key equipment, establish a peak-valley optimization control model for each key equipment in different electricity price periods on working days, develop an integrated power load characteristic monitoring and peak-valley optimization control system for key equipment in a fully mechanized mining face, and form a control and dispatching system for key power equipment in a fully mechanized mining face, thereby solving the problems of the inability to monitor the power consumption data of equipment in real time and the differences in electricity charges for power consumption equipment in different time periods.
[0052] The power load monitoring method of the comprehensive mining face equipment of this embodiment is applied to the power load characteristic monitoring and peak-valley optimization control system of the key equipment of the comprehensive mining face. The system includes a power load acquisition device and a host computer. The power load acquisition device is mainly divided into a data acquisition module, a power supply module, a main control module, and a communication module. The power load monitoring method of the comprehensive mining face equipment of this embodiment is executed in the host computer.
[0053] Among them, the design of the data acquisition module is the focus of the device. The accuracy of the collected data and the type of output data directly affect the performance of the device. Therefore, a sampling resistor that is not affected by the magnetic field is selected to collect the load electrical signal, and a new single-phase electric energy metering chip HLW8112 is selected to convert the electrical signal.
[0054] The power module is the basis for the operation of the device, and its voltage stabilization degree directly affects the working state of the device. Therefore, a switching power chip with the characteristics of high efficiency, good stability and small size is selected to convert the voltage.
[0055] The main control module is the core of the device, and its debugging and maintenance difficulty directly affects the engineering application value of the device. Therefore, a highly utilized STM32F103 microprocessor is selected to process the data output by the data acquisition module.
[0056] In order to realize the remote real-time collection of load data, the device selects a wireless communication module to upload the load data to a host computer. The power load monitoring method of the fully mechanized mining face equipment of this embodiment is applied in the host computer.
[0057] The method for monitoring the power load of equipment in the fully mechanized mining face of this embodiment first executes step S101 to obtain the power load data of multiple equipment in the fully mechanized mining face.
[0058] Specifically, the main control module of the power load characteristic monitoring and peak-valley optimization control system for key equipment in the comprehensive mining working face calculates and processes the load data into power load characteristic values, and the wireless communication module uploads the load characteristic values to the host computer.
[0059] Among them, the equipment is the key equipment of the comprehensive mining working face, and the specific key equipment is determined by the user.
[0060] Then the host computer executes step S102, inputs the power load data of each device into a type identification model to obtain the power load type of each device.
[0061] Specifically, a non-intrusive load identification study is completed on the host computer to determine the power load type of each device.
[0062] Finally, step S103 is executed on the host computer to calculate the optimal daily total electricity cost of the fully mechanized mining face.
[0063] In some embodiments, the total daily electricity cost is the total electricity cost of all equipment in the comprehensive mining face on a single day; or the total daily electricity cost is the total electricity cost of all key equipment in the comprehensive mining face on a single day.
[0064] The present invention obtains the power load data of multiple equipment in the comprehensive mining working face, inputs the power load data of each equipment into the type recognition model, and obtains the power load type of each equipment, thereby realizing the monitoring of the power consumption data of the comprehensive mining working face equipment. At the same time, by calculating the optimal daily total electricity cost of the comprehensive mining working face, the enterprise can understand its optimal daily total electricity cost, and regulate the power consumption of the comprehensive mining working face equipment according to the optimal daily electricity cost, which is of great significance to improving the efficiency of power consumption, reducing the electricity cost of the enterprise, extending the life of the equipment, and promoting the enterprise to reduce consumption and increase efficiency.
[0065] like Figure 2 The flowchart is a method for monitoring power load of fully mechanized working face equipment in another embodiment of the present invention, comprising:
[0066] Step S201, obtaining power load data of multiple devices in a fully mechanized mining face;
[0067] Step S202, inputting the power load data of each device into a type identification model to obtain the power load type of each device;
[0068] Step S203, setting the objective function of the mixed integer nonlinear programming model to minimize the total daily electricity cost of the fully mechanized mining face;
[0069] Step S204, solving the mixed integer nonlinear programming model to obtain the optimal daily total electricity cost.
[0070] Specifically, first, execute step S201 to obtain power load data of multiple equipment in the comprehensive mining face.
[0071] Then, step S202 is executed to input the power load data of each device into a type identification model to obtain the power load type of each device.
[0072] In one embodiment, it also includes:
[0073] Acquire training power load data and a training power load type corresponding to the training power load data;
[0074] Training is performed based on the training power load data and the training power load type to establish a type recognition model, and the type recognition model establishes a mapping relationship between the power load data and the power load type.
[0075] Specifically, based on the training power load data and the training power load type, the extreme learning machine (ELM) model is used for training to obtain the type equipment model. As a new type of single hidden layer neural network, the ELM model has the advantages of fast training speed, simple principle, strong generalization ability, etc., and is widely used in various fields such as image classification, mechanical fault prediction, and traffic sign recognition.
[0076] The electric load monitoring method of the fully-mechanized mining face equipment of this embodiment is applied to the electric load characteristic monitoring and peak-valley optimization control system of the key equipment of the fully-mechanized mining face. The system includes an electric load acquisition device which is mainly divided into a data acquisition module, a power supply module, a main control module, a communication module and a host computer. The electric load monitoring method of the fully-mechanized mining face equipment of this embodiment is executed in the host computer.
[0077] As an example, Figure 3 As shown in the figure, the power supply system used in the fully mechanized mining face of Qipanjing Coal Mine is powered by a mine flameproof mobile substation. The power supply voltage of the coal mining machine, scraper, crusher and transfer machine equipment in the fully mechanized mining face is 3300V, the power supply voltage of the pump station and belt conveyor equipment is 1140V; the power supply voltage of lighting, control and other equipment is 127V, and the power supply voltage of pumping and other equipment is 660V.
[0078] like Figure 4 As shown, the power load characteristic monitoring and peak-valley optimization control system of key equipment of the fully mechanized working face of the best embodiment of the present invention. The system includes a power load acquisition device 410 and a host computer 420. The power load acquisition device 410 is mainly divided into a data acquisition module 411, a power module 412, a main control module 413, and a communication module 414. The power load monitoring method of the fully mechanized working face equipment of this embodiment is executed in the host computer 420.
[0079] The overall working process of the power load acquisition device is: install a load monitoring device at the power supply entrance, the power module 412 provides working voltage to each module, the total voltage and total current of the load are converted into electrical signals through the high-precision resistor of the data acquisition module 411, HLW8112 converts the electrical signals into load data such as voltage and current effective values and stores them in the corresponding registers, the main control module 413 calculates and processes the load data into power load characteristic values, the wireless communication module 414 uploads the load characteristic values to the host computer 420, and completes the non-invasive load identification research on the host computer 420.
[0080] like Figure 5The figure shows a schematic diagram of the ELM model, which includes an input layer 501, a hidden layer 502 and an output layer 503. When using ELM to identify power loads, the main thing is to establish a n ) to power load type (y1, y2, ..., y m ), that is, to establish a functional mapping from load characteristics to power load types. Among them, the power load characteristics are preferably the peak-to-valley fluctuation range of power. Based on the theoretical and algorithmic research of the ELM model, a training model for power load characteristic samples is established, and then the actual power load data is identified and tested according to the trained model to demonstrate the feasibility and effectiveness of this method in power load identification. The performance analysis of the activation function is completed by the control variable method. The specific process is: when the number of hidden layer neurons is set to 40 in the ELM-based power load identification, the effects of the three activation functions on the performance of the single load identification model are compared and analyzed. The performance mainly includes training time, test time and recognition rate. The single load recognition performance comparison of the three activation functions is as follows: Figure 6 .from Figure 6 It can be seen that when the three activation functions are used to train the single load identification model, the Sigmoid function shows better performance in training time, test time and recognition rate. Therefore, the Sigmoid function is selected as the activation function of the ELM model. In order to ensure that the ELM power load identification model has the best performance, after completing the selection of sample data and activation function, it is necessary to further analyze the impact of different parameters on the model performance. According to the training steps of the ELM model, the number of hidden layer neurons L has a greater impact on the recognition performance of the model. Therefore, after the identification model is set with the above-mentioned load characteristic data, load type data and activation function, the selection of L is completed by comparing and analyzing the model performance under different L. The impact of different numbers of hidden layer neurons on the single load recognition rate is shown in the figure. Figure 7 shown.
[0081] The specific training process is mainly divided into the following three steps: ① Set the number of hidden layer neurons, and the model randomly generates the connection weights between the input layer and the hidden layer and the threshold of the hidden layer neurons; ② Select the activation function of the hidden layer, and calculate the hidden layer output matrix based on the connection weights in the function, the threshold of the hidden layer neurons and the training samples; ③ Calculate the connection weights of the output layer.
[0082] The trained ELM power load identification model is used to identify the load of the test set, output the identification results of the test, and analyze the load identification results.
[0083] After completing the selection of sample data and activation functions and setting of model parameters, an object-oriented programming method is used to develop a key equipment power load characteristic monitoring subsystem using development languages such as Java and JavaScript to realize power load identification based on the ELM model. The power load identification model process is as follows: Figure 8 As shown, including:
[0084] Step S801, obtaining power load data for training;
[0085] Step S802, preprocessing data according to the extracted load characteristics and load types;
[0086] Step S803, establishing training sample data;
[0087] Step S804, selecting an activation function and setting the number of neurons in the hidden layer L;
[0088] Step S805, training the ELM model;
[0089] Step S806, saving the trained recognition model;
[0090] Step S807, using sample data to test the recognition model;
[0091] Step S808: analyzing the recognition results.
[0092] The object-oriented analysis process includes the establishment of demand model, basic model, auxiliary model and model specification. Fig. 9 shown.
[0093] This embodiment establishes a type recognition model by training based on the training power load data and the training power load type, thereby obtaining an accurate mapping relationship between the power load data and the power load type.
[0094] Then, step S203 is executed to set the objective function of the mixed integer nonlinear programming model to minimize the total daily electricity cost of the fully mechanized mining face.
[0095] Specifically, mixed integer nonlinear programming (MINLP) refers to optimization problems with continuous and discrete variables as well as nonlinear functions of the objective function and constraints.
[0096] The total daily electricity cost of the comprehensive mining working face is: the sum of the electricity costs of all equipment during the working hours in a single day.
[0097] In some embodiments, the total daily electricity cost of the comprehensive mining working face is: the sum of the electricity costs of all key equipment in the comprehensive mining working face during the working time period in a single day.
[0098] The electricity cost of the equipment during the working time period is the peak-valley time-of-use electricity price of the working time period × equipment power × time. Since the peak-valley time-of-use electricity prices of different working time periods are different. By selecting the appropriate working time period, the total daily electricity cost will be adjusted. Therefore, the objective function of the mixed integer nonlinear programming model is set to minimize the total daily electricity cost of the fully mechanized mining face.
[0099] The main goal of implementing peak-valley time-of-use electricity prices is to reduce load fluctuations by reducing peaks and filling valleys. In general, the peak-valley difference is used to indicate the magnitude of load fluctuations. However, for general load curves, the peak-valley difference describes the difference between the maximum and minimum values on the load curve, reflecting the local nature of the load and cannot measure the overall load fluctuation. In mathematics, variance is generally used to measure the magnitude of data fluctuations, and the variance of the load is also used as one of the objective functions. Of course, the variance does not adequately reflect the situation of large local changes in the load. Therefore, the peak-valley difference and the variance of the load are combined as the objective function of the MINLP optimization model: the lowest total daily electricity cost.
[0100] Then, step S204 is executed to solve the mixed integer nonlinear programming model to obtain the optimal daily total electricity cost.
[0101] Specifically, by solving MINLP, the peak-valley time-of-use electricity price of each device (or key equipment) is obtained when the total daily electricity cost of the fully mechanized mining face is the lowest. The time period corresponding to each peak-valley time-of-use motor is the working time period of the equipment.
[0102] This embodiment establishes the energy consumption of key electrical equipment such as coal mining machines, scraper conveyors, hydraulic supports, bridge transfer machines, retractable belt conveyors, emulsion pump stations, and control, communication and lighting systems based on the power supply line analysis of the coal mine's fully mechanized mining face and the monthly electricity consumption statistics report. In combination with the coal mining face production plan and the equipment coordination logic, an electrical power monitoring demand plan for key equipment of the fully mechanized mining face of the Qipanjing Coal Mine is established, which solves the problems of the inability to monitor equipment power consumption data in real time and the differences in electricity charges for electrical equipment in different time periods. In order to clarify the power load characteristics of key equipment in the fully mechanized mining face and find out the peak-valley optimization control measures, a power monitoring demand plan for key equipment in the fully mechanized mining face of Qipanjing Coal Mine was established; a technical plan for power monitoring of key equipment was established; a power load characteristics monitoring system for key equipment was developed; a peak-valley optimization control model for each key equipment in different electricity price periods on working days was established; an integrated power load characteristics monitoring and peak-valley optimization control system for key equipment in fully mechanized mining faces was developed; a control and dispatching system for key power equipment in fully mechanized mining faces was formed, which solved the problems of the inability to monitor equipment power consumption data in real time and the differences in electricity charges for power equipment in different time periods.
[0103] In one embodiment, solving the mixed integer nonlinear programming model to obtain the optimal daily total electricity cost includes:
[0104] The mixed integer nonlinear programming model is solved based on the constraints to obtain the optimal daily total electricity cost.
[0105] Specifically, mixed integer nonlinear programming (MINLP) refers to the optimization problem with continuous and discrete variables and nonlinear functions of the objective function and constraints. Therefore, the mixed integer nonlinear programming model is solved under the constraints to obtain the optimal daily total electricity cost.
[0106] In one embodiment, solving the mixed integer nonlinear programming model based on constraints to obtain the optimal daily total electricity cost includes:
[0107] For each device, the constraint is set as follows: after adopting the optimal value of the peak-valley time-of-use electricity price, the average value of the load during the peak period is greater than the average value of the load during the valley period;
[0108] The mixed integer nonlinear programming model is solved based on the constraints to obtain the optimal daily total electricity cost.
[0109] Specifically, the purpose of implementing peak-valley time-of-use electricity prices is to reduce peak loads and fill valleys to reduce the peak-valley difference. The nature of the peak and valley periods should not be changed after the implementation of peak-valley time-of-use electricity prices. Currently, many companies have transferred a large amount of peak loads to the valley period after implementing peak-valley time-of-use electricity prices, and even caused the phenomenon of peak-valley inversion. In order to avoid the peak-valley inversion after the implementation of peak-valley time-of-use electricity prices, the condition is that the average value of the peak period load after the implementation of peak-valley time-of-use electricity prices is greater than the average value of the valley period load.
[0110] In one embodiment, the setting of the constraint that the average value of the load during the peak period is greater than the average value of the load during the valley period after the peak-valley time-of-use electricity price is implemented includes:
[0111] For each device, set the constraint to
[0112] y+(1-b)·M≥z≥y-(1-b)·M
[0113] b·M≥y
[0114] Among them, z is the optimal value of the peak and valley time-of-use electricity price of the equipment, b is the constant corresponding to each equipment, M is the maximum electricity price, and y is the mean value of the peak and valley time-of-use electricity price.
[0115] Preferably, b is in the range of [0,1].
[0116] Peak-valley time-of-use electricity price is the most widely implemented of all economic means of power demand side management. At present, various industrial and commercial users have generally adopted peak-valley time-of-use electricity price, and residential users in some provinces have also implemented or are preparing to implement peak-valley time-of-use electricity price. Peak-valley time-of-use electricity price implements higher electricity price during peak load period and lower electricity price during low load period, which can guide users to transfer load, reduce load fluctuation of power system, and increase load rate of power system. Whether the electricity price level of peak-valley time-of-use electricity price in each period is reasonable plays a key role in the effect of peak-valley electricity price implementation. At present, the electricity price model under peak-valley time-of-use electricity price is generally established through fuzzy optimization theory.
[0117] In classical set theory, whether an element in a domain belongs to a certain set is certain and not ambiguous, that is, any element in the domain can only belong to the set or not. However, in the real world, many natural languages are ambiguous. For example, concepts such as "bright" and "young" do not have clear definitions and connotations, and are therefore unclear and ambiguous. For this reason, Professor Lazada of the University of California, USA, first proposed fuzzy set theory in 1965, using fuzzy sets to characterize fuzzy concepts.
[0118] Suppose fuzzy set A is a set on the domain U. For any element x in the domain U, fuzzy set A specifies a function in the interval [0,1] to correspond to it. This function is called the membership function of x to A. The closer the value of the membership function is to 1, the higher the degree to which x belongs to A.
[0119] The degree of membership of each element in a fuzzy set to the fuzzy set needs to be characterized by a membership function. Therefore, correctly and reasonably establishing a membership function is the key to expressing the fuzziness and ambiguity of the fuzzy set. Commonly used membership functions include Gaussian membership function, Sigmoid membership function, bell-shaped membership function, and triangle membership function.
[0120] Fuzzy inference system, also known as fuzzy system, is a system that defines input, output and state variables on fuzzy sets. This system uses the fuzziness of human brain thinking to deal with fuzzy information problems that are difficult to solve with conventional mathematical methods. The input and output of fuzzy inference system are both precise values, and complex nonlinear mapping relationships can be realized, so it has been widely used.
[0121] First, the clear input of the system is fuzzified through the membership function, and then the fuzzy input is matched with all the fuzzy rules to obtain multiple fuzzy outputs based on appropriate reasoning methods. All fuzzy outputs are then combined into a total fuzzy output set, and finally the fuzzy output is defuzzified using appropriate mathematical methods and converted into a clear number as the system output, which corresponds to the result of fuzzy reasoning.
[0122] By analyzing the coordination logic of collaborative production among key equipment in the fully mechanized mining face, analyzing the linkage sequence and duration among the equipment, and combining the power time difference price model, based on the fuzzy reasoning system, an electricity price model for key equipment in the fully mechanized mining face under the peak-valley time-sharing electricity price is established.
[0123] With the development of science and technology and the urgent need to solve complex decision-making problems in practice, the algorithm research of nonlinear integer programming problems has become one of the research hotspots in the field of operations research and optimization. The research on mixed integer nonlinear programming (MINLP) problems mainly decomposes this problem into mixed integer linear programming problems that are relatively easy to solve. The methods for solving nonlinear integer programming problems include cutting plane method, decomposition algorithm, outer approximation method, branch and bound method, etc. Since integer programming problems are NP problems, existing algorithms can only solve a special form of integer programming problems, and often have shortcomings such as large amount of calculation, slow convergence speed, and poor efficiency. So far, there is no general and effective algorithm. For the decomposable convex MINLP problem, a feasible domain convex relaxation technique and a decomposition technique of the original problem are proposed, and convex envelope and conjugate function are used. The research on convex relaxation and decomposition techniques is helpful to solve specific integer problems.
[0124] Related constraints By analyzing the production capacity and coordination logic of key equipment in the fully mechanized mining face, and combining the electricity time difference price model in the western part of Inner Mongolia, a key equipment electricity price model under peak and valley time-of-use electricity prices is established based on fuzzy optimization theory. Then, through data analysis and modeling methods, with working days as the time range and the lowest total electricity cost as the goal, a MINLP model is established, and the optimal production decision variables under multi-equipment collaborative production are planned and solved, and a peak and valley optimization control model for each key equipment in different electricity price periods on working days is established.
[0125] Among them, the optimization of peak-valley time-of-use electricity prices should guarantee the interests of electricity users. After the implementation of peak-valley time-of-use electricity prices, the interests of electricity users should not be affected. For them, the lower the average electricity price, the better. Therefore, the following constraints are set:
[0126] (1) Equipment coordination constraints. The multi-machine supporting electrical equipment in the fully mechanized mining face has corresponding coordination logic. Therefore, when considering the constraints, it is necessary to clarify the coordination sequence and time difference between the equipment. For example, the coal mining machine, scraper conveyor, and hydraulic support need to work at the same time.
[0127] (2) Constraints on peak, flat and valley electricity prices. If the peak, flat and valley electricity prices are too close, the price difference in different time periods will not provide enough incentives for users, and the effect of peak shaving and valley filling will not be achieved. If the difference between the peak, flat and valley electricity prices is too large, it will seriously affect the living and production habits of users, and will also damage the interests of the power supply company, which is not conducive to the implementation of peak and valley time-of-use electricity prices. Therefore, the ratio of the electricity price in each time period after the implementation of the peak and valley time-of-use electricity price to the electricity price before the implementation should be controlled within a certain range.
[0128] (3) Equipment total load constraint. After the implementation of peak-valley time-of-use electricity prices, for the stability of the power grid operation and the needs of the users' own production and life, the total load of the users should remain basically unchanged. In most cases, the total load of the users remains unchanged before and after the implementation of the peak-valley time-of-use electricity prices. In fact, since the average electricity price of users is slightly reduced after the implementation of the peak-valley time-of-use electricity prices, the total load of users will also increase slightly in most cases.
[0129] (4) Peak-valley inversion constraint. The purpose of implementing peak-valley time-of-use electricity prices is to reduce the peak-valley difference. The nature of the peak and valley periods should not be changed after the implementation of peak-valley time-of-use electricity prices. At present, many enterprises have transferred a large amount of peak load to the valley period after implementing peak-valley time-of-use electricity prices, which has even led to the phenomenon of peak-valley inversion. In order to avoid the occurrence of peak-valley inversion after the implementation of peak-valley time-of-use electricity prices, the condition is that the average value of the peak period load after the implementation of peak-valley time-of-use electricity prices is greater than the average value of the valley period load.
[0130] For simple nonlinear constraints containing 0-1 integers, the following formula can be used for linearization, so that the constraints are combined into:
[0131] y+(1-b)·M≥z≥y-(1-b)·M
[0132] b·M≥y
[0133] z is the optimal value of the peak-valley time-of-use electricity price of the equipment, b is a constant corresponding to each equipment, the range of b is [0,1], M is the maximum electricity price, and y is the mean of the peak-valley time-of-use electricity price.
[0134] Using this method, the optimization model established above is converted into a mixed integer linear programming problem and then solved to establish a peak-valley optimization control model for each key equipment during different electricity price periods on weekdays.
[0135] In one embodiment, the setting of the constraint that the average value of the load during the peak period is greater than the average value of the load during the valley period after the peak-valley time-of-use electricity price is implemented also includes:
[0136] The constant corresponding to each device is set to the constant corresponding to the power load type of the device.
[0137] Specifically, the power load type of each device is determined by the ELM model, and then the constant b corresponding to the power load type is obtained by, for example, looking up a table. For each device, the constraint is set as follows:
[0138] y+(1-b)·M≥z≥y-(1-b)·M
[0139] b·M≥y
[0140] The optimal value of the peak-valley time-of-use electricity price z is the optimal value of the peak-valley time-of-use electricity price for each device. Since the working day is the time range and the minimum daily total electricity cost is the goal, the MINLP model is established. The total daily electricity cost is the sum of the electricity costs of each device, and the electricity cost of each device is the peak-valley time-of-use electricity price of each device × device power × time. The constraint is the peak-valley time-of-use electricity price of each device. By adjusting the peak-valley time-of-use electricity price of each device, the total daily electricity cost is minimized while satisfying the constraints.
[0141] In this embodiment, corresponding constants are set according to the power load type of each device to meet the power load type requirements of different devices.
[0142] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0143] like Fig.10 The figure shows a hardware structure diagram of an electronic device of the present invention, including:
[0144] at least one processor 1001; and,
[0145] A memory 1002 is communicatively connected to at least one of the processors 1001; wherein,
[0146] The memory 1002 stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the method for monitoring the power load of equipment in the comprehensive mining working face as described above.
[0147] Fig.10 A processor 1001 is taken as an example.
[0148] The electronic device may further include: an input device 1003 and a display device 1004 .
[0149] The processor 1001, the memory 1002, the input device 1003 and the display device 1004 may be connected via a bus or other means, and the figure takes the connection via a bus as an example.
[0150] The memory 1002 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the power load monitoring method for fully mechanized mining working face equipment in the embodiment of the present application, for example, Figure 1 , Figure 2 , Figure 3The processor 1001 executes various functional applications and data processing by running the non-volatile software programs, instructions and modules stored in the memory 1002, that is, the power load monitoring method of the fully mechanized mining face equipment in the above embodiment is implemented.
[0151] The memory 1002 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the power load monitoring method for comprehensive mining working face equipment, etc. In addition, the memory 1002 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 1002 may optionally include a memory remotely arranged relative to the processor 1001, and these remote memories may be connected to a device for executing the power load monitoring method for comprehensive mining working face equipment via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0152] The input device 1003 can receive user clicks and generate signal inputs related to user settings and function control of the fully mechanized mining face equipment power load monitoring method. The display device 1004 can include display devices such as display screens.
[0153] The one or more modules are stored in the memory 1002, and when executed by the one or more processors 1001, the method for monitoring the power load of the comprehensive mining working face equipment in any of the above method embodiments is executed.
[0154] The present invention obtains the power load data of multiple equipment in the comprehensive mining working face, inputs the power load data of each equipment into the type recognition model, and obtains the power load type of each equipment, thereby realizing the monitoring of the power consumption data of the comprehensive mining working face equipment. At the same time, by calculating the optimal daily total electricity cost of the comprehensive mining working face, the enterprise can understand its optimal daily total electricity cost, and regulate the power consumption of the comprehensive mining working face equipment according to the optimal daily electricity cost, which is of great significance to improving the efficiency of power consumption, reducing the electricity cost of the enterprise, extending the life of the equipment, and promoting the enterprise to reduce consumption and increase efficiency.
[0155] An embodiment of the present invention provides a storage medium, which stores computer instructions. When a computer executes the computer instructions, it is used to execute all steps of the method for monitoring the power load of equipment in a comprehensive mining working face as described above.
[0156] In the context of the present disclosure, a storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. The storage medium may be a machine-readable signal medium or a machine-readable storage medium. Alternatively, the storage medium may be a non-temporary computer-readable storage medium, for example, a non-temporary computer-readable storage medium may be a ROM, a random access memory (Random Access Memory, RAM), a compact disc read-only memory (Compact Disc ROM, CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.
[0157] An embodiment of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the above-mentioned method for monitoring the power load of equipment in a fully mechanized mining face.
[0158] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
Claims
1. A method for monitoring power load of fully mechanized mining working face equipment, characterized in that: include: Obtain power load data of multiple equipment in fully mechanized mining face; Inputting the power load data of each device into a type identification model to obtain the power load type of each device; Calculate the optimal total daily electricity cost for the fully mechanized mining face.
2. The method for monitoring power load of fully mechanized mining working face equipment according to claim 1 is characterized in that: Also includes: Acquire training power load data and a training power load type corresponding to the training power load data; Training is performed based on the training power load data and the training power load type to establish a type recognition model, and the type recognition model establishes a mapping relationship between the power load data and the power load type.
3. The method for monitoring power load of fully mechanized mining working face equipment according to claim 1 is characterized in that: The calculation of the optimal daily total electricity cost of the fully mechanized mining face includes: The objective function of the mixed integer nonlinear programming model is set to minimize the total daily electricity cost of the fully mechanized mining face; The mixed integer nonlinear programming model is solved to obtain the optimal daily total electricity cost.
4. The method for monitoring power load of fully mechanized mining working face equipment according to claim 3 is characterized in that: The mixed integer nonlinear programming model is solved to obtain the optimal daily total electricity cost, including: The mixed integer nonlinear programming model is solved based on the constraints to obtain the optimal daily total electricity cost.
5. The method for monitoring power load of fully mechanized mining working face equipment according to claim 4 is characterized in that: Solving the mixed integer nonlinear programming model based on constraints to obtain the optimal daily total electricity cost includes: For each device, the constraint is set as follows: after adopting the optimal value of the peak-valley time-of-use electricity price, the average value of the load during the peak period is greater than the average value of the load during the valley period; The mixed integer nonlinear programming model is solved based on the constraints to obtain the optimal daily total electricity cost.
6. The method for monitoring power load of fully mechanized mining working face equipment according to claim 5 is characterized in that: The constraint that the average value of the load during the peak period is greater than the average value of the load during the valley period after the peak-valley time-of-use electricity price is implemented includes: For each device, set the constraint y+(1-b)·M≥z≥y-(1-b)·M b·M≥y Among them, z is the optimal value of the peak and valley time-of-use electricity price of the equipment, b is the constant corresponding to each equipment, M is the maximum electricity price, and y is the mean value of the peak and valley time-of-use electricity price.
7. The method for monitoring power load of fully mechanized mining face equipment according to claim 6 is characterized in that: The constraint that the average value of the load during the peak period is greater than the average value of the load during the valley period after the peak-valley time-of-use electricity price is implemented also includes: The constant corresponding to each device is set to the constant corresponding to the power load type of the device.
8. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to at least one of the processors; wherein, The memory stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the method for monitoring the power load of comprehensive mining working face equipment as described in any one of claims 1 to 7.
9. A storage medium, characterized in that: The storage medium stores computer instructions, which, when executed by a computer, are used to execute all steps of the method for monitoring the power load of equipment in a comprehensive mining face as described in any one of claims 1 to 7.
10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by the processor, the method for monitoring the power load of the comprehensive mining working face equipment as described in any one of claims 1 to 7 is implemented.
