Method and equipment for predicting energy consumption of rubber production factory and medium

Abstract

The embodiment of the invention discloses a rubber production factory energy consumption prediction method, equipment and a medium, belongs to the technical field of energy consumption prediction, and solves the problem that the energy consumption monitoring of a rubber production factory lags behind. Performing fusion processing on the thermal imaging data of the to-be-tested rubber production factory to obtain spatial thermal data corresponding to the to-be-tested rubber production factory; dividing and comparing the historical energy consumption data set, screening abnormal historical data, and determining reference energy consumption prediction data based on the screened historical data; according to the building distribution data in the to-be-tested rubber production factory, the equipment distribution data in the to-be-tested rubber production factory and the space heat data, constructing an energy consumption influence relation graph; determining a final energy consumption influence factor based on a preset energy consumption influence factor database and the energy consumption influence relation graph; and adjusting the reference energy consumption prediction data based on the final energy consumption influence factor to obtain final energy consumption prediction data.

Description

Technical Field

[0001] This application relates to the technical field of energy consumption prediction, and in particular, to a method, device, and medium for predicting energy consumption in a rubber production factory. Background Art

[0002] With the acceleration of the industrialization process and the continuous expansion of production scale, the energy consumption of rubber production factories has been increasing year by year. This not only poses significant pressure on the environment but also greatly increases the operating costs. The energy consumption prediction of rubber production factories covers various types of energy used in the production process, and the use and consumption of these energies are directly related to the operating efficiency and environmental impact of the factories. With the continuous progress of modern information technology, Internet of Things technology, and artificial intelligence technology, factory automation control systems and energy consumption monitoring systems have been widely applied in the rubber production field.

[0003] Although factory automation control systems and energy consumption monitoring systems have achieved remarkable energy-saving effects in rubber production factories, some challenges still occur in the actual application process. On the one hand, the complexity and diversity of energy data make it difficult to ensure the accuracy and reliability of the data. On the other hand, since the energy consumption of rubber production factories is affected by multiple factors, the energy consumption situation is often adjusted only when the energy consumption reaches the warning threshold in the factory. This may cause some production equipment in the factory to operate near or at the limit state, or affect the health of the equipment due to frequent shutdowns for maintenance, thereby having an adverse impact on the stable operation of rubber production equipment. Summary of the Invention

[0004] Embodiments of this application provide a method, device, and medium for predicting energy consumption in a rubber production factory to solve the following technical problems: The energy consumption situation of a rubber production factory is adjusted only when the energy consumption of the rubber production factory is in an alarm state, which affects the health of the equipment and further affects the stable operation of the energy consumption equipment in the rubber production factory.

[0005] Embodiments of this application adopt the following technical solutions:

[0006] An embodiment of the present application provides a method for predicting energy consumption in a rubber production factory. The method includes: obtaining thermal imaging data of the rubber production factory to be measured, and performing fusion processing on the thermal imaging data of the rubber production factory to be measured to obtain spatial thermal data corresponding to the rubber production factory to be measured; obtaining a historical energy consumption data set corresponding to the rubber production factory to be measured, and based on the data distribution of the historical energy consumption data set, dividing and comparing the historical energy consumption data set, and screening out abnormal historical data, so as to determine reference energy consumption prediction data based on the screened historical data; constructing an energy consumption influence relationship diagram according to the building distribution data and equipment distribution data in the rubber production factory to be measured and the spatial thermal data; determining energy consumption influence factors between different factors based on a preset energy consumption influence factor database and the energy consumption influence relationship diagram; performing influence degree processing on the energy consumption influence factors based on the energy consumption influence relationship diagram and the energy consumption influence factors between different factors to determine the final energy consumption influence factors; and adjusting the reference energy consumption prediction data based on the final energy consumption influence factors to obtain the final energy consumption prediction data.

[0007] In the embodiment of the present application, by integrating thermal imaging data through fusion processing into a comprehensive data set, the quality and reliability of the data are improved. Using the screened and sorted historical data to determine the reference energy consumption prediction data can more accurately reflect the energy consumption characteristics and laws of the rubber production factory. By constructing an energy consumption influence relationship diagram, the correlation between factors such as building distribution, equipment distribution, and heat transfer in the rubber production factory and energy consumption can be clearly shown. By determining the energy consumption influence factors between different factors, processing such as superimposing the data of the rubber production factory obtained can be performed, so that the correlation between different influence factors is more accurate. By adjusting the reference energy consumption prediction data and taking into account the influence of different factors, a more accurate and practical final energy consumption prediction data can be obtained, improving the accuracy of energy consumption prediction in the rubber production factory.

[0008] In one implementation manner of the present application, obtaining thermal imaging data of the rubber production factory to be measured, and performing fusion processing on the thermal imaging data of the rubber production factory to be measured to obtain spatial thermal data corresponding to the rubber production factory to be measured specifically includes: obtaining a BIM model corresponding to the rubber production factory to be measured, and obtaining a thermal imaging image corresponding to the rubber production factory to be measured; determining a fusion mode, and when the fusion mode is direct fusion, determining geometric features of the rubber production factory to be measured in the BIM model and determining temperature change features in the thermal imaging image; matching the geometric features with the temperature change features to determine the spatial correspondence between the BIM model and the thermal imaging image; and based on the spatial correspondence, fusing the BIM model and the thermal imaging image into the same coordinate system.

[0009] In an implementation manner of the present application, after determining the fusion mode, the method further includes: when the fusion mode is indirect fusion, determining an indirect model in the BIM model, and based on the geometric features of the indirect model, performing a first interval intercept on the thermal imaging image to obtain a first indirect image; matching the indirect model with the first indirect image, and based on the matching relationship, performing a second interval intercept on the first indirect image to obtain a second indirect image; fusing the indirect model and the second indirect image into the same coordinate system.

[0010] In an implementation manner of the present application, a historical energy consumption data set corresponding to a rubber production factory to be measured is obtained, and based on the data distribution of the historical energy consumption data set, the historical energy consumption data set is divided and compared, and abnormal historical data is screened out. Specifically, it includes: dividing the historical energy consumption data set to obtain a plurality of energy consumption sub-data sets and a plurality of composite class sub-data sets; determining a normal energy consumption sub-data set and an abnormal energy consumption sub-data set in the energy consumption sub-data sets, and calculating the similarity between the plurality of composite class sub-data sets and the energy consumption sub-data sets respectively, so as to divide the composite class sub-data sets that meet the similarity threshold into the normal energy consumption sub-data set or the abnormal energy consumption sub-data set; determining the remaining data sets in the composite class sub-data sets, and based on the remaining data sets and the abnormal energy consumption sub-data sets, determining the abnormal data in the historical energy consumption data set, and screening out the abnormal historical data.

[0011] In an implementation manner of the present application, based on the screened historical data, reference energy consumption prediction data is determined. Specifically, it includes: based on the screened historical data, obtaining the personnel data and equipment data corresponding to the rubber production factory to be measured; determining the historical personnel distribution data in the rubber production factory to be measured based on the personnel data, and determining the equipment distribution data in the rubber production factory to be measured based on the equipment data; determining the energy consumption prediction data to be adjusted based on the spatial thermal data, historical personnel distribution data, equipment distribution data, and a preset energy consumption prediction model; based on the production equipment operation period information, obtaining the current personnel distribution data corresponding to the rubber production factory to be measured, and predicting the personnel distribution change rate in a future specific time period based on the difference between the current personnel distribution data and the historical personnel distribution data; determining the energy consumption change rate of the rubber production factory equipment corresponding to different equipment distribution points based on a preset energy consumption change prediction model and the personnel distribution change rate; adjusting the energy consumption prediction data to be adjusted corresponding to different equipment distribution points in a future specific time period based on the energy consumption change rate to obtain the reference energy consumption prediction data; wherein the reference energy consumption prediction data includes electric energy consumption data and water consumption data.

[0012] In an implementation manner of the present application, an energy consumption impact relationship diagram is constructed according to the building distribution data, equipment distribution data, and spatial heat data in the rubber production factory to be measured, which specifically includes: based on the building distribution data, determining the building position data in the rubber production factory to be measured, and determining the first node according to the building position data; determining the second node based on the equipment distribution data in the rubber production factory to be measured; and determining the heat transfer data of the rubber production factory to be measured based on the equipment distribution data and spatial heat data in the rubber production factory to be measured; constructing an energy consumption impact relationship diagram based on the impact relationship between the first node and the second node, and the impact relationship between the heat transfer data of the rubber production factory to be measured and the second node.

[0013] In an implementation manner of the present application, based on the energy consumption impact relationship diagram and the energy consumption impact factors between different factors, the impact degree of the energy consumption impact factors is processed to determine the final energy consumption impact factors, which specifically includes: based on the energy consumption impact relationship diagram, determining the connection line direction, and determining the first energy consumption impact factor in the preset energy consumption impact factor database based on the node data corresponding to both ends of the connection line; obtaining the first node corresponding to each second node, and determining the node impact degree based on the corresponding first node, and determining the second energy consumption impact factor based on the node impact degree; where the node impact degree includes the superposition impact degree and the repulsion impact degree; determining the final energy consumption impact factor based on the preset energy consumption impact factor function, the first energy consumption impact factor, and the second energy consumption impact factor.

[0014] In an implementation manner of the present application, based on the preset energy consumption impact factor function, it specifically includes:

[0015]

[0016] Among them, F is the final energy consumption impact factor corresponding to the current second node; i is the label of the first energy consumption impact factor corresponding to the current second node; p is the total number of the first energy consumption impact factors corresponding to the current second node; W is the weight corresponding to the first energy consumption impact factor; Q is the first energy consumption impact factor; n is the current first node; m is the total number of the first nodes that have an impact degree with the current second node; Z is the second energy consumption impact factor corresponding to the current first node; T is the weight corresponding to the second energy consumption impact factor.

[0017] An embodiment of the present application provides an energy consumption prediction device for a rubber production factory, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: obtain thermal imaging data of the rubber production factory to be measured, and perform fusion processing on the thermal imaging data of the rubber production factory to be measured to obtain spatial thermal data corresponding to the rubber production factory to be measured; obtain a historical energy consumption data set corresponding to the rubber production factory to be measured, and based on the data distribution of the historical energy consumption data set, perform division comparison on the historical energy consumption data set, and screen out abnormal historical data, so as to determine reference energy consumption prediction data based on the screened historical data; construct an energy consumption impact relationship diagram according to the building distribution data in the rubber production factory to be measured, the equipment distribution data in the rubber production factory to be measured, and the spatial thermal data; determine the energy consumption impact factors between different factors based on the preset energy consumption impact factor database and the energy consumption impact relationship diagram; perform impact degree processing on the energy consumption impact factors based on the energy consumption impact relationship diagram and the energy consumption impact factors between different factors to determine the final energy consumption impact factors; adjust the reference energy consumption prediction data based on the final energy consumption impact factors to obtain the final energy consumption prediction data.

[0018] A non-volatile computer storage medium provided by an embodiment of the present application stores computer-executable instructions, and the computer-executable instructions are set to: obtain thermal imaging data of the rubber production factory to be measured, and perform fusion processing on the thermal imaging data of the rubber production factory to be measured to obtain spatial thermal data corresponding to the rubber production factory to be measured; obtain a historical energy consumption data set corresponding to the rubber production factory to be measured, and based on the data distribution of the historical energy consumption data set, perform division comparison on the historical energy consumption data set, and screen out abnormal historical data, so as to determine reference energy consumption prediction data based on the screened historical data; construct an energy consumption impact relationship diagram according to the building distribution data in the rubber production factory to be measured, the equipment distribution data in the rubber production factory to be measured, and the spatial thermal data; determine the energy consumption impact factors between different factors based on the preset energy consumption impact factor database and the energy consumption impact relationship diagram; perform impact degree processing on the energy consumption impact factors based on the energy consumption impact relationship diagram and the energy consumption impact factors between different factors to determine the final energy consumption impact factors; adjust the reference energy consumption prediction data based on the final energy consumption impact factors to obtain the final energy consumption prediction data.

[0019] The above at least one technical solution adopted in the embodiments of the present application can achieve the following beneficial effects: By integrating and processing thermal imaging data into a comprehensive data set, the quality and reliability of the data are improved. Using the screened and sorted historical data to determine the reference energy consumption prediction data can more accurately reflect the energy consumption characteristics and laws of the rubber production plant. By constructing an energy consumption influence relationship diagram, the correlation between factors such as personnel distribution, equipment distribution, and heat transfer in the rubber production plant and energy consumption can be clearly displayed. By determining the energy consumption influence factors between different factors, the data obtained from the rubber production plant can be processed such as superposition, so that the correlation between different influencing factors is more accurate. By adjusting the reference energy consumption prediction data and taking into account the influence of different factors, a more accurate and practical final energy consumption prediction data can be obtained, improving the accuracy of energy consumption prediction in the rubber production plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0021] Figure 1 It is a flowchart of a method for predicting energy consumption in a rubber production plant provided by an embodiment of the present application;

[0022] Figure 2 It is a schematic structural diagram of a device for predicting energy consumption in a rubber production plant provided by an embodiment of the present application.

[0023] Reference numerals:

[0024] 200: Device for predicting energy consumption in a rubber production plant, 201: Processor, 202: Memory. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] The embodiments of the present application provide a method, device and medium for predicting energy consumption in a rubber production plant.

[0026] In order to enable those skilled in the art to better understand the technical solutions in the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0027] The technical solutions proposed in the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0028] Figure 1 The following is a flowchart of an energy consumption prediction method for a rubber production factory provided in an embodiment of the present application. As Figure 1 shown, the energy consumption prediction method for a rubber production factory includes the following steps:

[0029] Step 101: Obtain the thermal imaging data of the rubber production factory to be measured, and perform fusion processing on the thermal imaging data of the rubber production factory to be measured to obtain the spatial thermal data corresponding to the rubber production factory to be measured.

[0030] In an embodiment of the present application, obtain the BIM model corresponding to the rubber production factory to be measured, and obtain the thermal imaging image corresponding to the rubber production factory to be measured. Determine the fusion mode. In the case where the fusion mode is direct fusion, determine the geometric features of the rubber production factory to be measured in the BIM model, and determine the temperature change features in the thermal imaging image. Match the geometric features with the temperature change features to determine the spatial correspondence between the BIM model and the thermal imaging image. Based on the spatial correspondence, fuse the BIM model and the thermal imaging image into the same coordinate system.

[0031] Specifically, first obtain the BIM model (Building Information Modeling) corresponding to the rubber production factory to be measured. At the same time, capture the thermal imaging image corresponding to the rubber production factory to be measured through an infrared thermal imager. The BIM model contains the geometric, physical, and functional characteristics of the rubber production factory, and the thermal imaging image can display the temperature distribution on the surface of the rubber production factory. In the case where the fusion mode is direct fusion, in the BIM model, the geometric features of the rubber production factory, such as walls, windows, doors, roofs, etc., can be identified. These features have clear size and position information. In the thermal imaging image, the temperature change features are manifested as color changes in different regions. The regions with high temperature appear as brighter colors in the image, while the regions with low temperature appear as darker colors. By identifying the temperature change features, determine their corresponding positions and ranges.

[0032] Furthermore, extract key geometric features from the BIM model, such as the positions of doors and windows, corners, etc., and extract temperature change features from the thermal imaging image. Considering factors such as the position, shape, and size of the features, match the geometric features in the BIM model with the temperature change features in the thermal imaging image. Through feature matching, determine the spatial correspondence between the BIM model and the thermal imaging image. If the coordinate systems of the BIM model and the thermal imaging image are different, coordinate system conversion is required to make them have the same coordinate system.

[0033] Specifically, based on information such as the position, shape, and size of features, initial matching is performed using image registration or feature point matching algorithms. According to the initial matching results, an optimization algorithm, such as the least squares method, is used to optimize the matching results, eliminate incorrect matching points, and improve the accuracy of the matching. According to the optimized matching results, each element in the BIM model, such as rooms, doors and windows, equipment, etc., is associated with the corresponding temperature region in the thermal imaging image.

[0034] In an embodiment of the present application, in the case where the fusion mode is indirect fusion, an indirect model is determined in the BIM model. Based on the geometric features of the indirect model, the thermal imaging image is intercepted in a first interval to obtain a first indirect image. The indirect model is matched with the first indirect image, and based on the matching relationship, the first indirect image is intercepted in a second interval to obtain a second indirect image. The indirect model and the second indirect image are fused into the same coordinate system.

[0035] Specifically, according to specific requirements or analysis objectives, one or more indirect models are determined. These indirect models can be a certain part, a certain functional area, or a certain specific geometric feature in the BIM model. In the case where the fusion mode is indirect fusion, the area in the thermal imaging image corresponding to the geometric features of the indirect model is identified, and the thermal imaging image is cropped or masked according to the boundary or feature points of the indirect model to obtain a first indirect image. For example, the indirect model is a certain workshop in a rubber production factory to be measured. According to the geometric dimensions and position information of the workshop, the corresponding area is found in the thermal imaging image and intercepted as the first indirect image.

[0036] Furthermore, image registration or feature point matching algorithms are used to correspond the geometric features of the indirect model with the features in the first indirect image. According to the matching results, necessary adjustments are made to the first indirect image, such as rotation, scaling, or translation, to ensure complete matching with the indirect model. Further, image processing techniques are used to intercept the area that meets the conditions in the first indirect image to obtain a second indirect image. For example, if only a specific area (such as near the window) in the workshop is of interest, the boundary of this area can be defined and intercepted in the first indirect image to obtain a second indirect image. Further, the indirect model and the second indirect image are fused into the same coordinate system and displayed on the map.

[0037] Step 102: Obtain the historical energy consumption dataset corresponding to the rubber production factory to be measured. Based on the data distribution of the historical energy consumption dataset, the historical energy consumption dataset is divided and compared, and abnormal historical data is screened out to determine the reference energy consumption prediction data based on the screened historical data.

[0038] In one embodiment of the present application, the historical energy consumption dataset is partitioned to obtain a plurality of energy consumption sub-datasets and a plurality of composite class sub-datasets. The normal energy consumption sub-dataset and the abnormal energy consumption sub-dataset in the energy consumption sub-datasets are determined. The plurality of composite class sub-datasets are respectively calculated for similarity with the energy consumption sub-datasets, so as to partition the composite class sub-datasets that meet the similarity threshold into the normal energy consumption sub-dataset or the abnormal energy consumption sub-dataset. The remaining datasets in the composite class sub-datasets are determined, and based on the remaining datasets and the abnormal energy consumption sub-datasets, the abnormal data in the historical energy consumption dataset is determined, and the abnormal historical data is screened out.

[0039] Specifically, the historical energy consumption dataset is logically partitioned into a plurality of energy consumption sub-datasets according to time, equipment type, geographical location, etc. At the same time, based on other factors related to energy consumption in the historical energy consumption dataset, such as environmental parameters, equipment status, etc. The composite class sub-datasets are determined. For example, the energy consumption sub-dataset can be the energy consumption data subset divided according to months from January to December, and the composite class sub-dataset can be the dataset containing composite class information such as temperature, humidity, equipment running time, etc.

[0040] Further, through statistical methods, such as mean, standard deviation, median, etc., normal energy consumption and abnormal energy consumption are identified from the energy consumption sub-datasets. For example, for the energy consumption sub-dataset of each month, its mean and standard deviation are calculated. If the value of a certain data point exceeds the mean plus twice the standard deviation, it is regarded as abnormal. The similarity between the composite class sub-datasets and the energy consumption sub-datasets is calculated, and the similarity calculation can be performed through cosine similarity, etc. Based on the similarity calculation results, the composite class sub-datasets are partitioned into the normal or abnormal energy consumption sub-datasets. For example, for each composite class sub-dataset, its similarity with the normal energy consumption sub-dataset is calculated. If the similarity is higher than the preset threshold, the composite class sub-dataset is partitioned into the normal class; otherwise, it is partitioned into the abnormal class.

[0041] Further, after classifying the composite class sub-datasets, the remaining composite class sub-datasets are obtained, and the abnormal data in the historical energy consumption dataset is determined based on the association between these remaining datasets and the abnormal energy consumption sub-datasets. If a certain remaining dataset is highly correlated with multiple abnormal energy consumption sub-datasets, it is regarded as abnormal data, thereby screening out the abnormal data in the historical energy consumption dataset.

[0042] In an embodiment of the present application, based on the screened historical data, the personnel data and equipment data corresponding to the rubber production factory to be tested are obtained. Based on the personnel data, the historical personnel distribution data within the rubber production factory to be tested is determined, and based on the equipment data, the equipment distribution data within the rubber production factory to be tested is determined. Based on the space thermal data, historical personnel distribution data, equipment distribution data, and a preset energy consumption prediction model, the energy consumption prediction data to be adjusted is determined. Based on the production equipment operation time period information, the current personnel distribution data corresponding to the rubber production factory to be tested is obtained, and based on the difference between the current personnel distribution data and the historical personnel distribution data, the personnel distribution change rate within a specific future time period is predicted. Based on the preset energy consumption change prediction model and the personnel distribution change rate, the energy consumption change rate of the rubber production factory equipment corresponding to different equipment distribution points is determined. Based on the energy consumption change rate, the energy consumption prediction data to be adjusted corresponding to different equipment distribution points within a specific future time period is adjusted to obtain the reference energy consumption prediction data; wherein, the reference energy consumption prediction data includes power energy consumption data and water consumption energy data.

[0043] Specifically, effective and relevant personnel data and equipment data are screened from the historical database of the rubber production factory to be tested. For example, detailed data such as the number of employees, job distribution, operation time, and power of the equipment every day in the past year are obtained. Based on the screened personnel data, the personnel flow patterns and distribution within the factory during different time periods (such as weekdays, weekends, and holidays) are analyzed to form the historical personnel distribution data. At the same time, according to the equipment data, the spatial distribution and operation status of the equipment are determined. For example, during weekdays, from 8 am to 10 am, employees are mainly concentrated in production line A and the office area, while the equipment is mainly distributed in production line A and the warehouse. Combining the space thermal data, such as environmental parameters like temperature and humidity, historical personnel distribution data, equipment distribution data, and the established energy consumption prediction model, the energy consumption situation of the factory during different time periods is predicted, and the energy consumption prediction data that needs to be adjusted is determined.

[0044] Furthermore, an energy consumption prediction model is set in the embodiment of the present application. The training process of this model is as follows: Using the space thermal data sample, historical personnel distribution data sample, and equipment distribution sample as inputs, and the factory energy consumption data corresponding to the input samples as outputs, the preset neural network model is trained to obtain this energy consumption prediction model. The space thermal data, personnel distribution data, and equipment data corresponding to the current rubber production factory to be tested are input into this energy consumption prediction model to determine the energy consumption prediction data to be adjusted. For example, using the preset energy consumption prediction model, it can be predicted that during weekdays from 8 am to 10 am, due to the concentration of employees and equipment, the power and water consumption energy of the factory will increase significantly.

[0045] Furthermore, based on the production equipment operation period information and the current personnel distribution data, compare with the historical personnel distribution data to predict the personnel distribution change rate within a specific future time period. For example, from the production equipment operation period information, it can be known that production line A needs to stop for repair in the current time period, and production line B starts to be put into use. Then the current data shows that employees start to transfer from production line A to production line B. A machine learning model can be used to predict that the number of personnel on production line B will increase within the next week, while that on production line A will decrease accordingly. By using the pre-set energy consumption change prediction model and combining it with the predicted personnel distribution change rate, calculate the energy consumption change rate corresponding to different equipment distribution points, that is, the energy consumption corresponding to production line A will decrease, and the energy consumption corresponding to production line B will increase.

[0046] Among them, the training process of the pre-set energy consumption change prediction model is as follows: Use the equipment information samples at different distribution points and the personnel distribution change rate samples as inputs, and use the energy consumption change rate samples corresponding to each distribution point of the input samples as outputs to train the pre-set neural network model to obtain the pre-set energy consumption change prediction model. Input the current personnel distribution change rate and the equipment information of the distribution point into the pre-set energy consumption change prediction model, and the energy consumption change rate of the rubber production factory equipment corresponding to different distribution points can be obtained.

[0047] Furthermore, adjust the to-be-adjusted energy consumption prediction data obtained according to the energy consumption change rate to obtain more accurate reference energy consumption prediction data, including electricity and water consumption energy. Specifically, multiply the predicted energy consumption change rate by the current energy consumption value to obtain the reference energy consumption prediction values corresponding to each equipment distribution point within the future time period. For example, if the personnel density at a certain equipment distribution point decreases, the energy consumption at that equipment distribution point will decrease, and the more the personnel density decreases, the more its energy consumption will decrease.

[0048] Step 103: Construct an energy consumption impact relationship diagram based on the building distribution data, equipment distribution data, and space heat data within the rubber production factory to be measured.

[0049] In an embodiment of the present application, based on the building distribution data, determine the building location data within the rubber production factory to be measured, and determine the first node according to the building location data. Based on the equipment distribution data within the rubber production factory to be measured, determine the second node. And, based on the equipment distribution data and space heat data within the rubber production factory to be measured, determine the heat transfer data of the rubber production factory to be measured. Construct an energy consumption impact relationship diagram based on the impact relationship between the first node and the second node, and the impact relationship between the heat transfer data of the rubber production factory to be measured and the second node.

[0050] Specifically, based on the spatial thermal data of the rubber production factory to be measured, the specific locations of each building in the factory and the thermal data corresponding to different locations can be determined. These location data usually include information such as the coordinates, area, and height of the building. Based on the collected data, the specific locations of each building in the factory and their spatial relationships with each other are determined. Multiple first nodes are determined according to the locations of the buildings. Suppose there are three main production workshops, Workshop A, Workshop B, and Workshop C, and an office in the rubber production factory to be measured. Through the building distribution data, the specific locations of these buildings can be determined, and each workshop and the office are used as the first nodes.

[0051] Furthermore, based on the equipment distribution data of the rubber production factory, the specific locations of each equipment and its energy consumption characteristics are determined. Then, according to factors such as the energy consumption level of the equipment and its contribution to the overall energy consumption, multiple key equipments are selected as the second nodes. For example, in Workshop A, there are multiple injection molding machines and vulcanizing machines. Through the equipment distribution data, the locations of these equipments can be determined, and each injection molding machine and vulcanizing machine are used as the second nodes.

[0052] Furthermore, based on the equipment distribution data and spatial thermal data within the rubber production factory to be measured, the heat transfer situation inside the factory is analyzed. This includes the heat generated by the equipment, the conduction and blocking of heat by the building structure, etc. Specifically, the equipment types and equipment data corresponding to different workshops are obtained, the heat generated by each workshop is obtained, and according to the building structure of each workshop, such as the wall height and the type of wall building materials, the heat transfer coefficient is determined. Thus, through calculation and analysis, the heat transfer data of the rubber production factory can be obtained. For example, in Workshop A, a large amount of heat is generated when the injection molding machine is working. At the same time, the building structures such as the walls and roofs of the workshop have a certain impact on the conduction of heat. Through calculation and analysis, the heat transfer data of Workshop A can be obtained, such as the heat transfer rate and temperature distribution.

[0053] Furthermore, based on the influence relationship between the first nodes and the second nodes, that is, there is an energy consumption influence relationship between different building areas and equipments, and the influence relationship between the heat transfer data of the rubber production factory and the second nodes, that is, the heat generated by the equipment heats the surrounding environment, an energy consumption influence relationship diagram is constructed to show the energy consumption transfer and influence paths between each node. For example, Workshop A (the first node) and the injection molding machine (the second node) can be connected by an arrow to indicate that the energy consumption of the injection molding machine has a direct impact on the energy consumption of Workshop A. At the same time, the heat generated by the injection molding machine and the heat transfer data of Workshop A can also be connected by an arrow to indicate that the heat generated by the injection molding machine has a direct impact on the temperature distribution of Workshop A.

[0054] Step 104: Based on the preset energy consumption influence factor database and the energy consumption influence relationship diagram, determine the energy consumption influence factors between different factors.

[0055] In an embodiment of the present application, a preset energy consumption impact factor database is provided in the embodiment of the present application. Different energy consumption impact factors are included in the database, and the energy consumption impact factors corresponding to different energy consumption impact factors are also included. According to the energy consumption impact relationship diagram in the embodiment of the present application, different factors with an impact relationship are determined, so as to determine the energy consumption impact factors between different factors in the preset energy consumption impact factor database.

[0056] Step 105: Perform an impact degree process on the energy consumption impact factors based on the energy consumption impact relationship diagram and the energy consumption impact factors between different factors, so as to determine the final energy consumption impact factor.

[0057] In an embodiment of the present application, based on the energy consumption impact relationship diagram, the connection line direction is determined, and based on the node data corresponding to both ends of the connection line, the first energy consumption impact factor is determined in the preset energy consumption impact factor database. The first node corresponding to each second node is obtained, and the node impact degree is determined based on the corresponding first node. The second energy consumption impact factor is determined based on the node impact degree; wherein, the node impact degree includes a superposition impact degree and a repulsion impact degree. The final energy consumption impact factor is determined based on the preset energy consumption impact factor function, the first energy consumption impact factor, and the second energy consumption impact factor.

[0058] Specifically, based on the energy consumption impact relationship diagram, the connection line direction between each node is determined. Based on the node data corresponding to both ends of the connection line, the first energy consumption impact factor is searched for and determined in the database. The first node corresponding to each second node is obtained, and the node impact degree is determined based on the corresponding first node. The node impact degree includes a superposition impact degree and a repulsion impact degree. The superposition impact degree means that an increase in the energy consumption of one node will cause an increase in the energy consumption of another node, and the repulsion impact degree means that an increase in the energy consumption of one node will cause a decrease in the energy consumption of another node. The multiple first nodes corresponding to each second node are determined, and the energy consumption impact factors of the determined first nodes on the energy consumption of the first node are obtained. If it is a superposition impact degree, the energy consumption impact factors corresponding to the first node are superimposed, and if there is a repulsion impact degree, the energy consumption impact factor corresponding to the repulsion impact degree is subtracted.

[0059] In an embodiment of the present application, the preset energy consumption impact factor function specifically includes:

[0060]

[0061] Wherein, F is the final energy consumption impact factor corresponding to the current second node; i is the label of the first energy consumption impact factor corresponding to the current second node; p is the total number of the first energy consumption impact factors corresponding to the current second node; W is the weight corresponding to the first energy consumption impact factor; Q is the first energy consumption impact factor; n is the current first node; m is the total number of the first nodes having an influence degree on the current second node; Z is the second energy consumption impact factor corresponding to the current first node; T is the weight corresponding to the second energy consumption impact factor.

[0062] Further, based on a preset energy consumption impact factor function, the first energy consumption impact factor, and the second energy consumption impact factor, the final energy consumption impact factor is determined.

[0063] Step 106: Adjust the reference energy consumption prediction data based on the final energy consumption impact factor to obtain the final energy consumption prediction data.

[0064] Specifically, based on the obtained final energy consumption impact factor, the energy consumption of multiple second nodes in the rubber production factory to be measured is recalculated. For example, the product of the reference energy consumption prediction data corresponding to each second node and the corresponding final energy consumption impact factor can be calculated, so as to adjust the reference energy consumption prediction data to obtain the final energy consumption prediction data.

[0065] Figure 2 It is a schematic structural diagram of an energy consumption prediction device for a rubber production factory provided by an embodiment of the present application. As Figure 2 shown, the energy consumption prediction device 200 for a rubber production factory includes: at least one processor 201; and a memory 202 communicatively connected to the at least one processor 201; wherein, the memory 202 stores instructions executable by the at least one processor 201, and when the instructions are executed by the at least one processor 201, the at least one processor 201 is capable of: obtaining thermal imaging data of the rubber production factory to be measured, and performing fusion processing on the thermal imaging data of the rubber production factory to be measured to obtain spatial thermal data corresponding to the rubber production factory to be measured; obtaining a historical energy consumption data set corresponding to the rubber production factory to be measured, based on the data distribution of the historical energy consumption data set, performing division and comparison on the historical energy consumption data set, and screening out abnormal historical data, so as to determine reference energy consumption prediction data based on the screened historical data; constructing an energy consumption impact relationship diagram according to the building distribution data and equipment distribution data in the rubber production factory to be measured and the spatial thermal data; determining energy consumption impact factors between different factors based on a preset energy consumption impact factor database and the energy consumption impact relationship diagram; performing an influence degree process on the energy consumption impact factors based on the energy consumption impact relationship diagram and the energy consumption impact factors between different factors to determine the final energy consumption impact factor; and adjusting the reference energy consumption prediction data based on the final energy consumption impact factor to obtain the final energy consumption prediction data.

[0066] A non-volatile computer storage medium provided by an embodiment of the present application stores computer-executable instructions, and the computer-executable instructions are configured to: obtain thermal imaging data of a rubber production factory to be measured, and perform fusion processing on the thermal imaging data of the rubber production factory to be measured to obtain spatial thermal data corresponding to the rubber production factory to be measured; obtain a historical energy consumption data set corresponding to the rubber production factory to be measured, perform division and comparison on the historical energy consumption data set based on the data distribution of the historical energy consumption data set, and screen out abnormal historical data, so as to determine reference energy consumption prediction data based on the screened historical data; construct an energy consumption influence relationship diagram according to the building distribution data in the rubber production factory to be measured, the equipment distribution data in the rubber production factory to be measured, and the spatial thermal data; determine the energy consumption influence factors between different factors based on the preset energy consumption influence factor database and the energy consumption influence relationship diagram; perform influence degree processing on the energy consumption influence factors based on the energy consumption influence relationship diagram and the energy consumption influence factors between different factors to determine the final energy consumption influence factors; and adjust the reference energy consumption prediction data based on the final energy consumption influence factors to obtain the final energy consumption prediction data.

[0067] The embodiments in the present application are all described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, equipment, and non-volatile computer storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0068] The above are only the embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the embodiments of the present application. These modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for predicting energy consumption of a rubber production plant, characterized in that: The method comprises: Acquire thermal imaging data of the rubber production plant to be tested, and perform fusion processing on the thermal imaging data of the rubber production plant to be tested to obtain spatial thermal data corresponding to the rubber production plant to be tested; Acquire a historical energy consumption data set corresponding to the rubber production plant to be tested, divide and compare the historical energy consumption data set based on data distribution of the historical energy consumption data set, screen out abnormal historical data, and determine reference energy consumption forecast data based on the screened historical data; Constructing an energy consumption impact relationship diagram according to the building distribution data in the rubber production factory to be tested, the equipment distribution data in the rubber production factory to be tested and the space thermal data; Based on the preset energy consumption influencing factor database and the energy consumption influencing relationship diagram, determining the energy consumption influencing factors between different factors; Based on the energy consumption impact relationship diagram and the energy consumption impact factors between the different factors, the energy consumption impact factors are processed for impact to determine a final energy consumption impact factor; The reference energy consumption prediction data is adjusted based on the final energy consumption influencing factor to obtain final energy consumption prediction data.

2. A method for predicting energy consumption of a rubber production plant according to claim 1, characterized in that: The step of acquiring thermal imaging data of the rubber production plant to be tested and fusing the thermal imaging data of the rubber production plant to be tested to obtain spatial thermal data corresponding to the rubber production plant to be tested specifically includes: Obtaining a BIM model corresponding to the rubber production factory to be tested, and obtaining a thermal imaging image corresponding to the rubber production factory to be tested; Determine a fusion mode, and when the fusion mode is direct fusion, determine the geometric features of the rubber production plant to be tested in the BIM model, and determine the temperature change features in the thermal imaging image; Matching the geometric features with the temperature change features to determine a spatial correspondence between the BIM model and the thermal imaging image; Based on the spatial correspondence, the BIM model and the thermal imaging image are fused into the same coordinate system.

3. A method for predicting energy consumption of a rubber production plant according to claim 2, characterized in that: After the fusion mode is determined, the method further includes: When the fusion mode is indirect fusion, an indirect model is determined in the BIM model, and based on geometric features of the indirect model, a first interval is intercepted on the thermal imaging image to obtain a first indirect image; Matching the indirect model with the first indirect image, and performing a second interval interception on the first indirect image based on the matching relationship to obtain a second indirect image; The indirect model and the second indirect image are fused into the same coordinate system.

4. The method for predicting energy consumption of a rubber production plant according to claim 1, characterized in that: The obtaining of a historical energy consumption data set corresponding to the rubber production plant to be tested, dividing and comparing the historical energy consumption data set based on data distribution of the historical energy consumption data set, and filtering out abnormal historical data specifically includes: Dividing the historical energy consumption data set to obtain a plurality of energy consumption sub-data sets and a plurality of composite sub-data sets; Determine a normal energy consumption sub-dataset and an abnormal energy consumption sub-dataset in the energy consumption sub-dataset, and perform similarity calculations on a plurality of the composite sub-datasets and the energy consumption sub-dataset respectively, so as to classify the composite sub-datasets that meet the similarity threshold into the normal energy consumption sub-dataset or the abnormal energy consumption sub-dataset; The remaining data sets in the composite sub-data set are determined, and based on the remaining data sets and the abnormal energy consumption sub-data set, the abnormal data in the historical energy consumption data set are determined, and the abnormal data are screened out.

5. The method for predicting energy consumption of a rubber production plant according to claim 1, characterized in that: Determining reference energy consumption forecast data based on the filtered historical data specifically includes: Based on the screened historical data, obtaining the personnel data and equipment data corresponding to the rubber production factory to be tested; Determining historical personnel distribution data in the rubber production factory to be tested based on the personnel data, and determining equipment distribution data in the rubber production factory to be tested based on the equipment data; Determining energy consumption forecast data to be adjusted based on the space thermal data, the historical personnel distribution data, the equipment distribution data, and a preset energy consumption forecast model; Based on the production equipment operation time period information, current personnel distribution data corresponding to the rubber production plant to be tested is obtained, and based on the difference between the current personnel distribution data and the historical personnel distribution data, the personnel distribution change rate within a specific time period in the future is predicted; Based on the preset energy consumption change prediction model and the personnel distribution change rate, determining the energy consumption change rate of the rubber production plant equipment corresponding to different equipment distribution points; Based on the energy consumption change rate, adjusting the energy consumption forecast data to be adjusted corresponding to different equipment distribution points in the future specific time period to obtain the reference energy consumption forecast data; The reference energy consumption forecast data includes electricity energy consumption data and water energy consumption data.

6. The method for predicting energy consumption of a rubber production plant according to claim 1, characterized in that: The energy consumption impact relationship diagram is constructed according to the building distribution data in the rubber production factory to be tested, the equipment distribution data in the rubber production factory to be tested and the space thermal data, specifically including: Based on the building distribution data, determining the building location data in the rubber production plant to be tested, and determining the first node according to the building location data; Determining a second node based on equipment distribution data in the rubber production plant to be tested; and, determining heat transfer data of the rubber production plant to be tested based on the equipment distribution data in the rubber production plant to be tested and the space thermal data; The energy consumption influence relationship diagram is constructed based on the influence relationship between the first node and the second node, and the influence relationship between the heat transfer data of the rubber production plant to be tested and the second node.

7. A method for predicting energy consumption of a rubber production plant according to claim 6, characterized in that: The energy consumption impact factor based on the energy consumption impact relationship diagram and the energy consumption impact factor between the different factors, performing impact processing on the energy consumption impact factor to determine the final energy consumption impact factor, specifically includes: Based on the energy consumption impact relationship diagram, determine the direction of the connection line, and based on the node data corresponding to both ends of the connection line, determine the first energy consumption impact factor in the preset energy consumption impact factor database; Acquire the first nodes corresponding to each of the second nodes, and determine the node influence based on the corresponding first nodes, and determine the second energy consumption influence factor based on the node influence; wherein the node influence includes superposition influence and exclusion influence; A final energy consumption impact factor is determined based on a preset energy consumption impact factor function, the first energy consumption impact factor, and the second energy consumption impact factor.

8. A method for predicting energy consumption of a rubber production plant according to claim 7, characterized in that: The preset energy consumption influencing factor function specifically includes: Among them, F is the final energy consumption impact factor corresponding to the current second node; i is the label of the first energy consumption impact factor corresponding to the current second node; p is the total number of first energy consumption impact factors corresponding to the current second node; W is the weight corresponding to the first energy consumption impact factor; Q is the first energy consumption impact factor; n is the current first node; m is the total number of first nodes that have an influence on the current second node; Z is the second energy consumption impact factor corresponding to the current first node; T is the weight corresponding to the second energy consumption impact factor.

9. A rubber production plant energy consumption prediction device, characterized in that: The device comprises a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the device is triggered to execute the method according to any one of claims 1 to 8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions can execute the method according to any one of claims 1 to 8.

Images