Energy-saving power supply method and system for workshop energy consumption analysis

Abstract

The invention relates to an energy-saving power supply method and system for workshop energy consumption analysis, and the method comprises the steps: collecting a material image sequence and a sensing parameter sequence in a past preset time window in a workshop, and predicting the transmission material amount at a future preset moment; performing prediction error analysis according to the sensing parameter sequence to obtain an adjustment prediction error coefficient; performing fusion processing and error compensation on the predicted material quantity by adjusting a prediction error coefficient to obtain a compensated material quantity; and optimizing the operation power of the equipment according to the compensation material quantity to obtain the optimal operation power and implement energy-saving power supply. The technical problem that in the prior art, plastic crushing equipment still operates at high power under the condition of discontinuous material supply, and consequently electric power is wasted is solved, and the technical effects that by predicting the material amount and conducting error compensation, the equipment operation power is dynamically optimized, the electric power loss is reduced, and meanwhile the crushing treatment quality is guaranteed are achieved.

Description

Technical Field

[0001] The present invention relates to the field of energy-saving power supply, and particularly to an energy-saving power supply method and system for analyzing energy consumption in a workshop. Background Art

[0002] Plastic crushing equipment is widely used in the fields of industrial production and resource recycling, and is used to crush waste plastic products into small particles for reuse. In the prior art, plastic crushing equipment usually operates in a constant power mode, that is, regardless of the amount of materials on the conveyor belt, the equipment continuously operates at a preset high power. However, the material supply in the workshop is usually discontinuous, with the amount of materials varying from time to time and even there may be no materials for a short period. However, the existing control of crushing equipment lacks the ability to sense and respond to changes in the amount of materials, resulting in the equipment still maintaining a high-power operation state when the amount of materials is small or there is no material, causing a large waste of electric power resources. Summary of the Invention

[0003] The present invention aims at the technical problem that in the prior art, plastic crushing equipment still operates at a high power when the material supply is discontinuous, resulting in power waste, and provides an energy-saving power supply method and system for analyzing energy consumption in a workshop to solve this problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides an energy-saving power supply method for analyzing energy consumption in a workshop, including: in the workshop, collecting a sequence of material images and a sequence of sensing parameters within a preset past time window, predicting the transmitted material quantity at a preset future moment, and obtaining a first predicted material quantity and a second predicted material quantity; according to the sequence of sensing parameters, performing prediction error analysis to obtain a prediction error coefficient, and adjusting the prediction error coefficient according to the first predicted material quantity and the second predicted material quantity to obtain an adjusted prediction error coefficient; using the adjusted prediction error coefficient to perform fusion processing and error compensation on the first predicted material quantity and the second predicted material quantity to obtain a compensated material quantity; according to the compensated material quantity, optimizing the energy consumption power of equipment operation to obtain an optimal operating power, and performing energy-saving power supply.

[0005] Optionally, in the workshop, collecting a sequence of material images and a sequence of sensing parameters within a preset past time window includes: in the workshop, collecting material images and sensing parameters within a preset past time window through image monitoring devices and weight sensors arranged on the equipment, where the equipment is plastic crushing equipment; integrating according to the time stamps of the collected material images and sensing parameters in chronological order to obtain a sequence of material images and a sequence of sensing parameters.

[0006] Optionally, perform the prediction of the material transfer amount at a future preset moment to obtain a first predicted material amount and a second predicted material amount, including: training a first material amount prediction branch and a second material amount prediction branch to obtain a material amount predictor; inputting the material image sequence and the sensing parameter sequence into the first material amount prediction branch and the second material amount prediction branch in the material amount predictor respectively to predict the material transfer amount at a future preset moment, and outputting to obtain the first predicted material amount and the second predicted material amount.

[0007] Optionally, training a first material amount prediction branch and a second material amount prediction branch to obtain a material amount predictor includes: according to the data records of the equipment for material transfer processing within a historical time, collecting a set of sample material image sequences and a set of sample sensing parameter sequences, and collecting the material transfer amount at a preset moment after each sample material image sequence and sample sensing parameter sequence, and labeling it as a set of sample material amounts; using a convolutional neural network and a feedforward neural network to construct a first material amount prediction branch and a second material amount prediction branch; respectively using the set of sample material image sequences and the set of sample sensing parameter sequences as input features, and using the set of sample material amounts as output, training and testing the first material amount prediction branch and the second material amount prediction branch respectively until qualified; combining the first material amount prediction branch and the second material amount prediction branch to obtain a material amount predictor.

[0008] Optionally, perform prediction error analysis according to the sensing parameter sequence to obtain a prediction error coefficient, including: obtaining multiple sensing parameters in the sensing parameter sequence, and converting and processing them to obtain multiple historical material amounts; using the multiple historical material amounts to retrieve in the set of historical material amounts recorded during the operation of the equipment to obtain multiple material amount occurrence rates; obtaining the average material amount occurrence rate of different material amounts in the set of historical material amounts, calculating the mean of the ratio of the average material amount occurrence rate to the multiple material amount occurrence rates to obtain an occurrence rate coefficient; obtaining a basic prediction error coefficient for the prediction of the material transfer amount, and using the occurrence rate coefficient to correct and calculate the basic prediction error coefficient to obtain a prediction error coefficient.

[0009] Optionally, adjust the prediction error coefficient according to the first predicted material amount and the second predicted material amount to obtain an adjusted prediction error coefficient, including: calculating the mean value according to the first predicted material amount and the second predicted material amount to obtain a predicted material amount; obtaining the historical average material amount during the operation of the equipment; calculating the ratio of the predicted material amount to the historical average material amount, and adjusting and calculating the prediction error coefficient to obtain an adjusted prediction error coefficient.

[0010] Optionally, the adjusted prediction error coefficient is used to perform fusion processing and error compensation on the first predicted material quantity and the second predicted material quantity to obtain a compensated material quantity, including: calculating a predicted material quantity through mean fusion processing based on the first predicted material quantity and the second predicted material quantity; using the sum of the adjusted prediction error coefficient and 1 as an error compensation coefficient to perform error compensation calculation on the predicted material quantity to obtain a compensated material quantity.

[0011] Optionally, based on the compensated material quantity, the operating energy consumption power of the equipment is optimized to obtain an optimal operating power for energy-saving power supply, including: randomly configuring the operating power of the equipment; obtaining the current real-time power of the equipment, and combining the operating power to obtain a switching energy consumption parameter. Based on the operating power and the compensated material quantity, the qualified degree of the broken particle size is analyzed; according to the switching energy consumption parameter, the operating power, and the qualified degree of the broken particle size, an energy-saving fitness is calculated as follows: ; where SAf is the energy-saving fitness, 、 and are weights, 、 and The sum of is 1, is a preset switching energy consumption parameter, is the switching energy consumption parameter, P is the operating power, is the preset operating power of the equipment, K is the qualified degree of the broken particle size, is the preset qualified degree of the broken particle size; continue to randomly configure the operating power of the equipment for iterative optimization until convergence, and retain the operating power with the maximum energy-saving fitness as the optimal operating power for energy-saving power supply.

[0012] Optionally, obtaining the current real-time power of the equipment, combining the operating power to obtain a switching energy consumption parameter, and analyzing the qualified degree of the broken particle size based on the operating power and the compensated material quantity, including: retrieving the switching energy consumption parameter according to the real-time power and the operating power based on the power adjustment data record of the equipment within the historical time; collecting a sample material quantity set and a sample operating power set according to the material crushing data record of the equipment, and collecting the proportion of the particle size of the material after crushing meeting the requirements under different sample material quantities and sample operating powers, and labeling it as the sample qualified degree of the broken particle size to obtain a sample qualified degree of the broken particle size set; using the sample material quantity set, the sample operating power set, and the sample qualified degree of the broken particle size set as training data and test data, and training a crushing predictor based on a feedforward neural network; inputting the compensated material quantity and the operating power into the crushing predictor, and outputting the qualified degree of the broken particle size.

[0013] In a second aspect, the present invention provides an energy-saving power supply system for workshop energy consumption analysis, comprising: a material quantity prediction module, configured to collect a sequence of material images and a sequence of sensing parameters within a preset time window in the workshop, and perform prediction of the transported material quantity at a preset future moment to obtain a first predicted material quantity and a second predicted material quantity; an error coefficient acquisition module, configured to perform prediction error analysis based on the sequence of sensing parameters to obtain a prediction error coefficient, and adjust the prediction error coefficient according to the first predicted material quantity and the second predicted material quantity to obtain an adjusted prediction error coefficient; a compensated material quantity module, configured to perform fusion processing and error compensation on the first predicted material quantity and the second predicted material quantity by using the adjusted prediction error coefficient to obtain a compensated material quantity; and a power optimization module, configured to perform optimization of the power consumption of equipment operation according to the compensated material quantity to obtain an optimal operating power and perform energy-saving power supply.

[0014] The beneficial effects of the present invention are as follows: By collecting a sequence of material images and a sequence of sensing parameters within a preset time window in the workshop and performing prediction of the transported material quantity at a preset future moment to obtain a first predicted material quantity and a second predicted material quantity, data support is provided for subsequent power optimization. By performing prediction error analysis based on the sequence of sensing parameters to obtain a prediction error coefficient and adjusting the prediction error coefficient according to the first predicted material quantity and the second predicted material quantity to obtain an adjusted prediction error coefficient, the processing quality of important materials is ensured. By performing fusion processing and error compensation on the first predicted material quantity and the second predicted material quantity by using the adjusted prediction error coefficient to obtain a compensated material quantity, sufficient processing capacity is ensured even when the predicted material quantity may be low. By performing optimization of the power consumption of equipment operation according to the compensated material quantity to obtain an optimal operating power and performing energy-saving power supply, dynamic energy saving is achieved.

[0015] Through the above technical solution, the present application realizes accurate prediction of the material quantity of the crushing equipment, error compensation, and optimization control of the operating power, effectively solves the problem of power waste of the crushing equipment under the condition of discontinuous material supply, and at the same time ensures the crushing processing quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic flowchart of an energy-saving power supply method for workshop energy consumption analysis provided by the present invention; Figure 2 is a schematic structural diagram of an energy-saving power supply system for workshop energy consumption analysis provided by the present invention.

[0017] In the drawings, the components represented by the reference numerals are as follows: a material quantity prediction module 11, an error coefficient acquisition module 12, a compensated material quantity module 13, and a power optimization module 14. Detailed implementation mode

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work belong to the protection scope of the present invention.

[0019] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0020] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. In order for any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present invention.

[0021] Embodiment 1, as Figure 1 shown, the embodiment of the present invention provides an energy-saving power supply method for workshop energy consumption analysis, including: S100: In the workshop, collect the material image sequence and sensing parameter sequence within a past preset time window, and perform prediction of the transported material quantity at a future preset moment to obtain a first predicted material quantity and a second predicted material quantity.

[0022] Specifically, in the operating environment of a plastic crushing workshop, first, through the image monitoring device and weight sensor installed on the crushing equipment, the material conveyor belt of the crushing equipment is monitored in real time. For example, within a preset time window (such as 10 seconds), continuously collect the material image data and corresponding weight sensing parameter data on the conveyor belt, and integrate them in chronological order to form a material image sequence and a sensing parameter sequence.

[0023] After the acquisition is completed, the material image sequence and the sensing parameter sequence are respectively input into a pre-trained conveyor material quantity predictor, which includes a first material quantity prediction branch and a second material quantity prediction branch. Among them, the first material quantity prediction branch analyzes based on the material image sequence, and the second material quantity prediction branch analyzes based on the sensing parameter sequence. The material quantity predictor processes these two input data to predict the material transmission quantity on the conveyor belt at a preset future moment (for example, 2 seconds later), and outputs a first predicted material quantity and a second predicted material quantity respectively.

[0024] Through the dual-path prediction mechanism, visual information and sensor information can be comprehensively utilized to provide basic data support for subsequent error analysis and operating power optimization, so as to achieve precise control and energy consumption optimization of the crushing equipment.

[0025] S200: According to the sensing parameter sequence, conduct prediction error analysis to obtain a prediction error coefficient, and adjust the prediction error coefficient according to the first predicted material quantity and the second predicted material quantity to obtain an adjusted prediction error coefficient.

[0026] Specifically, first, convert the sensing parameters in the sensing parameter sequence into corresponding historical material quantities, then retrieve and match them in the pre-stored set of historical material quantities of equipment operation, and calculate the occurrence rate index of each material quantity. By comparing the ratio of the current material quantity occurrence rate to the historical average material quantity occurrence rate, an occurrence rate coefficient is obtained. This coefficient reflects the representativeness of the current material state in historical data - the smaller the occurrence rate, the rarer the current state, and the greater the possible prediction error. Subsequently, the occurrence rate coefficient and the basic prediction error coefficient are corrected and calculated to obtain a preliminary prediction error coefficient.

[0027] Then, calculate the average value of the first predicted material quantity and the second predicted material quantity to obtain a predicted material quantity, and compare it with the historical average material quantity. The larger the material quantity, the more important the current crushing task is, and a greater processing redundancy is required to ensure the crushing quality. Therefore, according to the ratio of the predicted material quantity to the historical average material quantity, the prediction error coefficient is further adjusted to obtain an adjusted prediction error coefficient.

[0028] Through the dual adjustment mechanism based on historical data analysis and current material characteristics, the prediction error can be more accurately evaluated, providing reliable parameter support for subsequent error compensation and power optimization.

[0029] S300: Use the adjusted prediction error coefficient to perform fusion processing and error compensation on the first predicted material quantity and the second predicted material quantity to obtain a compensated material quantity.

[0030] Specifically, after obtaining the adjusted prediction error coefficient, the first predicted material quantity and the second predicted material quantity are subjected to fusion processing and error compensation to obtain an accurate compensated material quantity.

[0031] First, an arithmetic mean calculation is performed on the first predicted material quantity and the second predicted material quantity to obtain the fused predicted material quantity, thereby comprehensively utilizing the advantages of image analysis and sensor data and reducing the deviation that may be brought by a single data source. Subsequently, based on the obtained adjusted prediction error coefficient, an error compensation coefficient is constructed. Specifically, the adjusted prediction error coefficient is added to 1 to form the final error compensation coefficient. This error compensation coefficient reflects the additional processing redundancy that needs to be considered under the current material conditions to ensure that the crushing quality is not affected by the material prediction error. Then, the error compensation coefficient is multiplied by the fused predicted material quantity to calculate the compensated material quantity. The compensated material quantity fully considers the prediction error and the importance of material processing, providing a more reliable decision-making basis for subsequent equipment power optimization.

[0032] Through error compensation, the uncertainty in material quantity prediction can be effectively addressed, improving stability and reliability.

[0033] S400: According to the compensated material quantity, optimize the energy consumption power of equipment operation to obtain the optimal operating power and perform energy-saving power supply.

[0034] Specifically, after obtaining the compensated material quantity, determine the optimal equipment operating power according to the compensated material quantity to achieve energy-saving power supply while ensuring the crushing treatment quality.

[0035] First, randomly configure a series of possible operating power values as the initial operating power scheme. For each configured operating power scheme, obtain the current real-time power data of the equipment and calculate the energy consumption parameters required for power switching. At the same time, use a pre-trained crushing predictor to predict the crushing particle size qualification rate when processing the compensated material quantity at this operating power, which reflects the quality level of the crushing treatment. Subsequently, construct an energy-saving fitness evaluation index, comprehensively considering the influence of three factors: switching energy consumption parameters, operating power, and crushing particle size qualification rate, and comprehensively evaluate the performance of each power configuration scheme. This index balances the relationship between energy consumption and crushing quality through a weighted calculation method. Then, through an iterative optimization method, continuously try new operating power schemes and calculate their energy-saving fitness until the algorithm converges. Finally, select the operating power scheme with the highest energy-saving fitness as the optimal operating power and perform energy-saving power supply control on the crushing equipment accordingly.

[0036] Through the optimization mechanism, it is possible to minimize the equipment energy consumption while ensuring the crushing treatment quality, achieve the goal of intelligent energy saving, and avoid power waste caused by the equipment still operating at high power when the material quantity is small or there is no material.

[0037] Further, in the workshop, by collecting the material image sequence and sensing parameter sequence within a preset time window in the past, including: S110: In the workshop, through the image monitoring device and weight sensor arranged on the equipment, collect the material images and sensing parameters within a preset time window in the past, where the equipment is a plastic crushing equipment; S120: According to the timestamps of the collected material images and sensing parameters, integrate them in chronological order to obtain the material image sequence and sensing parameter sequence.

[0038] In an alternative embodiment, first, in the environment of the plastic crushing workshop, through the image monitoring device and weight sensor arranged on the crushing equipment, collect the material images and sensing parameters within a preset time window (such as 10 seconds) in the past in real time. Among them, the image monitoring device can be a high-speed industrial camera, which can clearly capture the shape, density and distribution of the materials on the conveyor belt; the weight sensor measures the weight change of the materials on the conveyor belt in real time and provides a direct numerical index of the material quantity.

[0039] Then, perform time-series integration processing on the obtained discrete material images and sensing parameters. Specifically, read the timestamp information of each frame of material image and each group of sensing parameters, and arrange and integrate these data in strict chronological order to form the material image sequence and sensing parameter sequence. This sequence integration method based on timestamps ensures the consistency and synchronization of the two heterogeneous data in the time dimension and provides high-quality input data for the subsequent prediction of the material quantity.

[0040] Through the above steps, the key monitoring data during the operation of the plastic crushing equipment can be efficiently obtained, and a comprehensive perception ability of the material transmission state can be established, laying a data foundation for realizing accurate material quantity prediction and energy-saving control.

[0041] Further, predict the transmitted material quantity at a preset future moment to obtain the first predicted material quantity and the second predicted material quantity, including: S130: Train the first material quantity prediction branch and the second material quantity prediction branch to obtain a material quantity predictor; S140: Input the material image sequence and the sensing parameter sequence into the first material quantity prediction branch and the second material quantity prediction branch in the material quantity predictor respectively, predict the transmitted material quantity at a preset future moment, and output to obtain the first predicted material quantity and the second predicted material quantity.

[0042] In a preferred embodiment, first, a material quantity predictor is constructed through offline training. The material quantity predictor consists of two parallel prediction branches: the first material quantity prediction branch is dedicated to processing image information and can extract implicit information related to the transfer quantity from the visual features of the material; the second material quantity prediction branch is dedicated to processing sensing parameter information and can infer the transfer quantity trend from the measurement data of the physical properties of the material. This dual-branch design makes full use of the complementary advantages of multi-modal data and can improve the robustness and accuracy of prediction. Then, the real-time collected and integrated material image sequence and sensing parameter sequence are respectively input into the corresponding prediction branches of the pre-trained material quantity predictor. Specifically, the material image sequence is input into the first material quantity prediction branch, and after feature extraction and time series modeling, the first predicted material quantity is output; at the same time, the sensing parameter sequence is input into the second material quantity prediction branch, and after parameter analysis and pattern recognition, the second predicted material quantity is output. These two prediction branches work independently and respectively predict the transfer material quantity at a preset future moment (for example, 2 seconds later) based on different data modalities.

[0043] Through the dual-channel parallel prediction mechanism, it is possible to maintain a high prediction accuracy in the actual production environment where the material transfer state is complex and changeable, providing a reliable decision-making basis for subsequent error analysis and power optimization.

[0044] Furthermore, training the first material quantity prediction branch and the second material quantity prediction branch to obtain a material quantity predictor includes: S131: According to the data records of the equipment for material transfer processing within the historical time, collect a set of sample material image sequences and a set of sample sensing parameter sequences, and collect the transfer material quantity at a preset moment after each sample material image sequence and sample sensing parameter sequence, and label it as a set of sample material quantities; S132: Use a convolutional neural network and a feedforward neural network to construct the first material quantity prediction branch and the second material quantity prediction branch; S133: Respectively use the set of sample material image sequences and the set of sample sensing parameter sequences as input features, and use the set of sample material quantities as the output, and respectively train and test the first material quantity prediction branch and the second material quantity prediction branch until they are qualified; S134: Combine the first material quantity prediction branch and the second material quantity prediction branch to obtain a material quantity predictor.

[0045] In a preferred embodiment, to train the material quantity predictor, first, training data is collected from the historical operation records of the plastic crushing equipment. Specifically, from the database of the equipment's material transfer processing within the historical time, a sample material image sequence set and a sample sensing parameter sequence set are extracted as the input features of the material quantity predictor. At the same time, for each set of input data, the actual transferred material quantity after a preset time (such as 2 seconds later) is also collected and labeled as the sample material quantity set as the output label of the material quantity predictor. This labeling method based on historical data ensures the authenticity and representativeness of the training data. Then, according to the characteristics of different data modalities, corresponding deep learning architectures are used to construct the prediction branches. Specifically, for the first material quantity prediction branch that processes the material image sequence, a convolutional neural network is used as the basic architecture, which can effectively extract the spatial features and material form information in the image; for the second material quantity prediction branch that processes the sensing parameter sequence, a feedforward neural network is used as the basic architecture, which can efficiently analyze the complex relationships between numerical parameters. Through targeted network design, the information value of different data modalities can be maximally utilized.

[0046] Next, the two prediction branches are independently trained and performance tested. Specifically, the first material quantity prediction branch is trained with the sample material image sequence set as the input and the sample material quantity set as the output label; the second material quantity prediction branch is trained with the sample sensing parameter sequence set as the input and also with the sample material quantity set as the output label. During the training process, the backpropagation algorithm is used to optimize the network parameters, and the cross-validation method is used to evaluate the performance of the material quantity predictor, and the iteration is repeated until the performance of the material quantity predictor reaches the preset qualified standard. After that, the trained first material quantity prediction branch and the second material quantity prediction branch are combined and integrated to form a complete material quantity predictor. This material quantity predictor can process the two data modalities in parallel and output the prediction results based on different information sources respectively, providing a multi-dimensional decision basis for subsequent fusion processing and error compensation.

[0047] Through the above steps, a dual-channel material quantity predictor based on deep learning is constructed, which can fully exploit the information value of multi-modal data, significantly improve the accuracy and reliability of prediction, and lay a foundation for achieving precise energy-saving control.

[0048] Furthermore, according to the sensing parameter sequence, a prediction error analysis is carried out to obtain a prediction error coefficient, including: S210: Obtain a plurality of sensing parameters within the sensing parameter sequence, and convert and process them to obtain a plurality of historical material quantities; S220: Use the plurality of historical material quantities to retrieve within the historical material quantity set recorded during the operation of the equipment to obtain a plurality of material quantity occurrence rates; S230: Obtain the average material quantity appearance rate of different material quantities in the historical material quantity set, calculate the mean value of the ratio of the average material quantity appearance rate to the multiple material quantity appearance rates, and obtain the appearance rate coefficient; S240: Obtain the basic prediction error coefficient for the predicted transported material quantity, and perform a correction calculation on the basic prediction error coefficient using the appearance rate coefficient to obtain the prediction error coefficient.

[0049] In a preferred implementation manner, first, obtain multiple sensing parameter data points in the real-time collected sensing parameter sequence, and convert these sensing parameters into corresponding historical material quantities. For example, based on the calibration curve of the sensor, accurately reflect the material weight at different times on the conveyor belt, and provide an accurate numerical representation of the material transport state. Then, retrieve and match the multiple historical material quantity values obtained by conversion in the pre-stored device historical material quantity set. Through the retrieval operation, the occurrence frequency of these material quantity values in the historical operation data can be determined, and the appearance rate index of each material quantity value can be calculated to obtain multiple material quantity appearance rates. These material quantity appearance rates directly reflect the typical degree and representativeness of the current material state in the historical operation.

[0050] Subsequently, obtain the average material quantity appearance rate of all different material quantity values in the historical material quantity set as the reference value. Then, calculate the ratio of this average material quantity appearance rate to the multiple material quantity appearance rates obtained, and obtain the arithmetic mean of these ratios to obtain the appearance rate coefficient. This coefficient is an index to measure the specificity degree of the current material state in the statistical distribution. After that, obtain the pre-set basic prediction error coefficient for the predicted transported material quantity, which represents the inherent error level in the prediction under standard conditions. Then, perform a correction calculation on the basic prediction error coefficient using the obtained appearance rate coefficient to generate a prediction error coefficient adapted to the characteristics of the current material state. Specifically, when the appearance rate coefficient is small, the prediction error coefficient is correspondingly increased to compensate for the prediction uncertainty that may be brought by rare material states; otherwise, the prediction error coefficient is decreased.

[0051] Through the above steps, an adaptive error evaluation mechanism based on historical data analysis is established, which can dynamically adjust the prediction error evaluation standard according to the statistical characteristics of the current material state, improve the pertinence and effectiveness of error compensation, and provide a more reliable decision-making basis for subsequent energy-saving control.

[0052] Furthermore, according to the first predicted material quantity and the second predicted material quantity, adjust the prediction error coefficient to obtain an adjusted prediction error coefficient, including: S250: Calculate the mean value according to the first predicted material quantity and the second predicted material quantity to obtain the predicted material quantity; S260: Obtain the historical average material quantity during the operation of the device; S270: Calculate the ratio of the predicted material quantity to the historical average material quantity, and perform an adjustment calculation on the prediction error coefficient to obtain an adjusted prediction error coefficient.

[0053] In a feasible implementation, first, perform a fusion process on the first predicted material quantity and the second predicted material quantity respectively output by the first material quantity prediction branch and the second material quantity prediction branch. Specifically, calculate the arithmetic mean of these two prediction results to obtain a comprehensive predicted material quantity, thereby balancing the respective advantages and disadvantages of the two prediction branches and improving the overall reliability of the prediction results. Then, obtain the historical material quantity data recorded during the long-term operation of the equipment from the historical database, and calculate the average value of these historical data to obtain the historical average material quantity. This historical average material quantity reflects the material load level of the plastic crushing equipment under normal operating conditions and is a reference value for evaluating the relative importance of the current material state.

[0054] After that, calculate the ratio of the obtained predicted material quantity to the obtained historical average material quantity, and perform an adjustment calculation on the prediction error coefficient based on this ratio to finally obtain the adjusted prediction error coefficient. For example, when the predicted material quantity is greater than the historical average material quantity, it indicates that the material load of the current crushing task is heavier and the processing importance is higher, and the prediction error coefficient is correspondingly increased to provide a greater processing redundancy to ensure the crushing quality; on the contrary, when the predicted material quantity is less than the historical average material quantity, the prediction error coefficient is correspondingly decreased to optimize the energy consumption efficiency.

[0055] Through the adaptive error adjustment mechanism based on the material load level, it is possible to dynamically adjust the prediction error evaluation standard according to the relative importance of the current material processing task, balance the relationship between processing quality and energy efficiency, and provide more scientific parameter support for realizing precise energy-saving control.

[0056] Furthermore, using the adjusted prediction error coefficient, perform a fusion process and error compensation on the first predicted material quantity and the second predicted material quantity to obtain a compensated material quantity, including: S310: Calculate the predicted material quantity obtained by mean fusion processing according to the first predicted material quantity and the second predicted material quantity; S320: Use the sum of the adjusted prediction error coefficient and 1 as the error compensation coefficient to perform an error compensation calculation on the predicted material quantity to obtain the compensated material quantity.

[0057] In an alternative embodiment, first, the first predicted material quantity and the second predicted material quantity output by two different prediction branches are fused. Specifically, the arithmetic mean method is used to calculate the mean of these two predicted values to obtain the fused predicted material quantity. This mean fusion strategy can comprehensively utilize the two prediction results based on image analysis and sensing parameter analysis, reduce the random error and systematic error that may be brought by a single prediction method, and improve the stability and reliability of the prediction result. Then, an error compensation mechanism is constructed based on the obtained adjusted prediction error coefficient. Specifically, the adjusted prediction error coefficient is added to 1 to form the final error compensation coefficient, ensuring that the error compensation coefficient is always greater than 1, enabling positive error compensation and providing a necessary redundancy for material processing. Subsequently, the error compensation coefficient is multiplied by the obtained predicted material quantity to perform error compensation calculation and obtain the compensated material quantity.

[0058] Through positive error compensation, it is possible to appropriately increase the processing redundancy based on the predicted material quantity, effectively coping with the uncertainties brought by prediction errors and material fluctuations. Especially in the case of a large material quantity, since the adjusted prediction error coefficient increases correspondingly, a greater processing redundancy will be provided to ensure the processing quality of important crushing tasks; while in the case of a small material quantity, the provided processing redundancy is relatively small, which is beneficial to improving energy utilization efficiency. Through the adaptive error compensation strategy, it is possible to dynamically adjust the compensation strategy according to the material state characteristics and processing importance, achieving the best balance between ensuring processing quality and energy-saving efficiency, and providing a decision basis for subsequent equipment power optimization.

[0059] Furthermore, based on the compensated material quantity, equipment operation energy consumption power optimization is performed to obtain the optimal operation power for energy-saving power supply, including: S410: Randomly configure the operation power of the equipment; S420: Obtain the current real-time power of the equipment, combine it with the operation power to obtain the switching energy consumption parameter, and analyze the qualified degree of the crushing particle size based on the operation power and the compensated material quantity; S430: Calculate the energy-saving fitness according to the switching energy consumption parameter, operation power, and qualified degree of the crushing particle size, as follows: ; where SAf is the energy-saving fitness, , and are weights, , and The sum of is 1, is the preset switching energy consumption parameter, is the switching energy consumption parameter, P is the operation power, $P_0$ is the preset operating power of the device, and $K$ is the qualified degree of crushing particle size, which is the preset qualified degree of crushing particle size; S440: Continuously randomly configure the operating power of the device for iterative optimization until convergence, retain the operating power with the maximum energy-saving fitness as the optimal operating power, and perform energy-saving power supply.

[0060] In a preferred embodiment, first, the operating power configuration of the device is initialized using a random search strategy. Specifically, a set of operating powers is randomly generated within the power range allowed by the device as the initial solution space of the optimization algorithm. This random initialization method helps to avoid the optimization process falling into local optimal solutions and improves the global search ability. Then, the current real-time power of the device is obtained and compared with the randomly configured operating power for analysis to calculate the energy consumption parameters required for power switching. This parameter reflects the additional energy required for the device to switch from the current power state to the candidate operating power state. At the same time, the randomly configured operating power and the obtained compensation material quantity are used as input parameters and analyzed through a pre-trained crushing predictor to predict the qualified degree of crushing particle size when processing this compensation material quantity at this operating power. This qualified degree of crushing particle size reflects the crushing quality of the device under the current parameter configuration.

[0061] Then, according to the switching energy consumption parameter, operating power, and qualified degree of crushing particle size, the energy-saving fitness is calculated to comprehensively evaluate the performance of the randomly configured operating power. The specific formula for calculating the energy-saving fitness is as follows: ; where the energy-saving fitness is obtained by weighted calculation of three key factors, namely the ratio of switching energy consumption parameters , the ratio of operating power , and the ratio of qualified degree of crushing particle size . Among them, , , and are the corresponding weight coefficients and their sum is 1, is the preset switching energy consumption parameter, is the switching energy consumption parameter, $P$ is the operating power, $P_0$ is the preset operating power of the device, and $K$ is the qualified degree of crushing particle size, which is the preset qualified degree of crushing particle size. This multi-objective weighted evaluation method can simultaneously consider energy consumption efficiency and processing quality to achieve balanced optimization between the two.

[0062] After that, an iterative optimization strategy is adopted to continuously improve the power configuration plan. Specifically, new operating power configurations are randomly generated, and the evaluation processes in steps S420 and S430 are repeatedly executed. The energy-saving fitness of the operating power of the new configuration is calculated and compared with the current optimal operating power configuration. If the energy-saving fitness of the operating power of the new configuration is higher, the optimal operating power is updated. This iterative process continues until the algorithm converges to the stopping condition. Finally, the operating power configuration with the maximum energy-saving fitness is selected as the optimal operating power, and the energy-saving power supply control of the crushing equipment is carried out accordingly.

[0063] Through the random search optimization mechanism, it is possible to minimize the equipment energy consumption and achieve intelligent energy saving while ensuring the crushing quality. Especially in the plastic crushing application scenario with large fluctuations in the material quantity, this method can dynamically adjust the equipment power according to the real-time material state, avoiding power waste caused by the equipment still running at high power when the material quantity is small or there is no material, and significantly improving the energy utilization efficiency.

[0064] Furthermore, the current real-time power of the equipment is obtained, and the switching energy consumption parameter is obtained by combining with the processing of the operating power. According to the operating power and the compensated material quantity, the qualified degree of the crushing particle size is analyzed, including: S421: According to the power adjustment data record within the historical time of the equipment, the switching energy consumption parameter is retrieved according to the real-time power and the operating power; S422: According to the material crushing data record of the equipment, the sample material quantity set and the sample operating power set are collected, and the proportion of the particle size of the material after crushing meeting the requirements under different sample material quantities and sample operating powers is collected and labeled as the sample crushing particle size qualified degree, and the sample crushing particle size qualified degree set is obtained; S423: Using the sample material quantity set, the sample operating power set and the sample crushing particle size qualified degree set as training data and test data, a crushing predictor is trained based on the feedforward neural network; S424: The compensated material quantity and the operating power are input into the crushing predictor, and the qualified degree of the crushing particle size is output.

[0065] In a preferred embodiment, first, the energy consumption characteristics of power switching are analyzed based on the historical operation data of the device. Specifically, from the power adjustment data records within the historical time, using the current real-time power and the candidate operating power as retrieval conditions, the energy consumption data in similar power switching scenarios is queried to obtain the corresponding switching energy consumption parameters. The retrieval method based on historical records can accurately reflect the actual energy consumption level of the device under different power switching states, providing a reliable parameter basis for the calculation of energy-saving fitness. Then, a training dataset for the crushing predictor is constructed. Specifically, from the material crushing data records of the device, a set of sample material quantities and a set of sample operating powers are collected as input features, and the proportion of the particle size of the material meeting the specification requirements after crushing under different combinations of sample material quantities and sample operating powers is collected and labeled as the sample crushing particle size qualification degree, forming a set of sample crushing particle size qualification degrees as the output label. This multi-dimensional data collection method comprehensively covers the combined influence of material quantity and operating power on crushing quality, providing rich learning samples for the training of the crushing predictor.

[0066] After that, a crushing predictor is constructed and trained based on the collected training data. Specifically, the set of sample material quantities and the set of sample operating powers are used as input features, and the set of sample crushing particle size qualification degrees is used as the output label. A crushing predictor architecture is constructed based on the feedforward neural network architecture, and parameter optimization training is performed through a supervised learning method. During the training process, the dataset is divided into a training set and a test set to ensure that the model has good generalization ability. The prediction method based on the neural network can effectively capture the complex non-linear relationship between material quantity, operating power, and crushing quality, realizing high-precision prediction of crushing effects. After that, the trained crushing predictor is applied for real-time prediction. Specifically, the obtained compensated material quantity and the currently evaluated operating power are used as input parameters and input into the crushing predictor, and the crushing particle size qualification degree is obtained after calculation. This prediction result directly reflects the expected quality level of plastic crushing under the current material state and power configuration.

[0067] Through the crushing quality prediction mechanism based on historical data analysis and deep learning, the crushing treatment effect can be accurately evaluated under different material loads and power configurations, providing a scientific basis for power optimization decisions and achieving the best balance between treatment quality and energy efficiency.

[0068] Embodiment 2, as Figure 2 shown, based on the same inventive concept as the energy-saving power supply method for workshop energy consumption analysis provided in Embodiment 1, the present invention embodiment also provides an energy-saving power supply system for workshop energy consumption analysis, including: The material quantity prediction module 11 is used to collect a sequence of material images and a sequence of sensing parameters within a preset time window in the workshop, and predict the transmitted material quantity at a preset future moment to obtain a first predicted material quantity and a second predicted material quantity; The prediction error coefficient acquisition module 12 is used to perform prediction error analysis based on the sequence of sensing parameters to obtain a prediction error coefficient, and adjust the prediction error coefficient according to the first predicted material quantity and the second predicted material quantity to obtain an adjusted prediction error coefficient; The compensated material quantity module 13 is used to perform fusion processing and error compensation on the first predicted material quantity and the second predicted material quantity by using the adjusted prediction error coefficient to obtain a compensated material quantity; The power optimization module 14 is used to optimize the power consumption of equipment operation according to the compensated material quantity to obtain an optimal operating power and perform energy-saving power supply.

[0069] Furthermore, the execution steps of the material quantity prediction module 11 include: In the workshop, collect material images and sensing parameters within a preset time window in the past through image monitoring devices and weight sensors arranged on the equipment, where the equipment is a plastic crushing equipment; Integrate the collected material images and sensing parameters according to the timestamps in chronological order to obtain a sequence of material images and a sequence of sensing parameters.

[0070] Furthermore, the execution steps of the material quantity prediction module 11 further include: Train the first material quantity prediction branch and the second material quantity prediction branch to obtain a material quantity predictor; Input the sequence of material images and the sequence of sensing parameters into the first material quantity prediction branch and the second material quantity prediction branch in the material quantity predictor respectively to predict the transmitted material quantity at a preset future moment, and output to obtain a first predicted material quantity and a second predicted material quantity.

[0071] Furthermore, the execution steps of the material quantity prediction module 11 further include: According to the data records of the equipment for material transmission processing within the historical time, collect a set of sample material image sequences and a set of sample sensing parameter sequences, and collect the transmitted material quantity at a preset moment after each sample material image sequence and sample sensing parameter sequence, and label it as a set of sample material quantities; Construct the first material quantity prediction branch and the second material quantity prediction branch by using a convolutional neural network and a feedforward neural network; Respectively use the set of sample material image sequences and the set of sample sensing parameter sequences as input features, and use the set of sample material quantities as output, and train and test the first material quantity prediction branch and the second material quantity prediction branch respectively until they are qualified; Combine the first material quantity prediction branch and the second material quantity prediction branch to obtain a material quantity predictor.

[0072] Furthermore, the execution steps of the error coefficient acquisition module 12 include: Obtain multiple sensing parameters within the sensing parameter sequence, and through conversion processing, obtain multiple historical material quantities; Use the multiple historical material quantities to retrieve within the set of historical material quantities recorded during the operation of the device, and obtain multiple material quantity occurrence rates; Obtain the average material quantity occurrence rate of different material quantities within the set of historical material quantities, calculate the mean value of the ratio of the average material quantity occurrence rate to the multiple material quantity occurrence rates, and obtain an occurrence rate coefficient; Obtain the basic prediction error coefficient for predicting the transported material quantity, and use the occurrence rate coefficient to perform correction calculation on the basic prediction error coefficient to obtain a prediction error coefficient.

[0073] Furthermore, the execution steps of the error coefficient acquisition module 12 also include: Calculate the mean value based on the first predicted material quantity and the second predicted material quantity to obtain a predicted material quantity; Obtain the historical average material quantity during the operation of the device; Calculate the ratio of the predicted material quantity to the historical average material quantity, and perform adjustment calculation on the prediction error coefficient to obtain an adjusted prediction error coefficient.

[0074] Furthermore, the execution steps of the compensated material quantity module 13 include: Calculate the mean value through fusion processing based on the first predicted material quantity and the second predicted material quantity to obtain a predicted material quantity; Use the sum of the adjusted prediction error coefficient and 1 as an error compensation coefficient to perform error compensation calculation on the predicted material quantity to obtain a compensated material quantity.

[0075] Furthermore, the execution steps of the power optimization module 14 include: Randomly configure the operating power of the device; Obtain the current real-time power of the device, combine with the operating power to process and obtain a switching energy consumption parameter, and analyze based on the operating power and the compensated material quantity to obtain the qualified degree of the broken particle size; Calculate the energy-saving fitness based on the switching energy consumption parameter, the operating power, and the qualified degree of the broken particle size, as follows: ; where SAf is the energy-saving fitness, , and are weights, , and The sum of and is 1, is the preset switching energy consumption parameter, is the switching energy consumption parameter, P is the operating power, is the preset operating power of the device, K is the qualified degree of the crushing particle size, is the preset qualified degree of the crushing particle size; Continue to randomly configure the operating power of the device for iterative optimization until convergence, retain the operating power with the largest energy-saving fitness as the optimal operating power, and perform energy-saving power supply.

[0076] Furthermore, the execution steps of the power optimization module 14 further include: According to the power adjustment data record of the device within the historical time, retrieve the switching energy consumption parameter according to the real-time power and the operating power; According to the material crushing data record of the device, collect the sample material quantity set and the sample operating power set, and collect the proportion of the particle size of the material after crushing meeting the requirements under different sample material quantities and sample operating powers, and label it as the sample crushing particle size qualified degree to obtain the sample crushing particle size qualified degree set; Use the sample material quantity set, the sample operating power set and the sample crushing particle size qualified degree set as training data and test data, and train the crushing predictor based on the feedforward neural network; Input the compensation material quantity and the operating power into the crushing predictor, and output to obtain the qualified degree of the crushing particle size.

[0077] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0078] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded computers, or other programmable data processing devices to produce a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0080] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0082] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concepts.

[0083] Obviously, those skilled in the art can make various changes and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An energy-saving power supply method for energy consumption analysis in a workshop, characterized in that, The method includes: In the workshop, collect the material image sequence and sensing parameter sequence within a preset past time window, and perform prediction of the transported material quantity at a preset future moment to obtain a first predicted material quantity and a second predicted material quantity; According to the sensing parameter sequence, perform prediction error analysis to obtain a prediction error coefficient, and adjust the prediction error coefficient according to the first predicted material quantity and the second predicted material quantity to obtain an adjusted prediction error coefficient; Use the adjusted prediction error coefficient to perform fusion processing and error compensation on the first predicted material quantity and the second predicted material quantity to obtain a compensated material quantity; According to the compensated material quantity, optimize the energy consumption power of the equipment operation to obtain the optimal operation power and perform energy-saving power supply.

2. The energy-saving power supply method for workshop energy consumption analysis according to claim 1, characterized in that In the workshop, by collecting the material image sequence and sensing parameter sequence within a preset past time window, it includes: In the workshop, through the image monitoring equipment and weight sensors arranged on the equipment, collect the material images and sensing parameters within a preset past time window, where the equipment is a plastic crushing equipment; According to the timestamps of the collected material images and sensing parameters, integrate them in chronological order to obtain a material image sequence and a sensing parameter sequence.

3. The energy-saving power supply method for workshop energy consumption analysis according to claim 1, characterized in that, Perform prediction of the transported material quantity at a preset future moment to obtain a first predicted material quantity and a second predicted material quantity, including: Train a first material quantity prediction branch and a second material quantity prediction branch to obtain a material quantity predictor; Input the material image sequence and the sensing parameter sequence into the first material quantity prediction branch and the second material quantity prediction branch in the material quantity predictor respectively to predict the transported material quantity at a preset future moment, and output to obtain a first predicted material quantity and a second predicted material quantity.

4. The energy-saving power supply method for workshop energy consumption analysis according to claim 3, characterized in that, Train a first material quantity prediction branch and a second material quantity prediction branch to obtain a material quantity predictor, including: According to the data records of the equipment for material transportation processing within the historical time, collect a sample material image sequence set and a sample sensing parameter sequence set, and collect the transported material quantity at a preset moment after each sample material image sequence and sample sensing parameter sequence, and label it as a sample material quantity set; Use a convolutional neural network and a feedforward neural network to construct a first material quantity prediction branch and a second material quantity prediction branch; Respectively use the sample material image sequence set and the sample sensing parameter sequence set as input features, and use the sample material quantity set as the output, and respectively train and test the first material quantity prediction branch and the second material quantity prediction branch until they are qualified; Combine the first material quantity prediction branch and the second material quantity prediction branch to obtain a material quantity predictor.

5. The energy-saving power supply method for workshop energy consumption analysis according to claim 1, wherein, According to the sensing parameter sequence, perform prediction error analysis to obtain a prediction error coefficient, including: Obtain multiple sensing parameters within the sensing parameter sequence, and perform conversion processing to obtain multiple historical material quantities; Use the multiple historical material quantities to retrieve within the historical material quantity set recorded during the equipment operation to obtain multiple material quantity occurrence rates; Obtain the average material quantity occurrence rate of different material quantities within the historical material quantity set, calculate the mean of the ratio of the average material quantity occurrence rate to the multiple material quantity occurrence rates to obtain an occurrence rate coefficient; Obtain the basic prediction error coefficient for predicting the transported material quantity, and use the appearance rate coefficient to perform correction calculation on the basic prediction error coefficient to obtain the prediction error coefficient.

6. The energy-saving power supply method for workshop energy consumption analysis according to claim 1, characterized in that Adjust the prediction error coefficient according to the first predicted material quantity and the second predicted material quantity to obtain an adjusted prediction error coefficient, including: Calculate the mean value according to the first predicted material quantity and the second predicted material quantity to obtain the predicted material quantity; Obtain the historical average material quantity during the operation of the equipment; Calculate the ratio of the predicted material quantity to the historical average material quantity, and perform adjustment calculation on the prediction error coefficient to obtain the adjusted prediction error coefficient.

7. The energy-saving power supply method for workshop energy consumption analysis according to claim 1, characterized in that, Use the adjusted prediction error coefficient to perform fusion processing and error compensation on the first predicted material quantity and the second predicted material quantity to obtain the compensated material quantity, including: Calculate the mean value for fusion processing according to the first predicted material quantity and the second predicted material quantity to obtain the predicted material quantity; Use the sum of the adjusted prediction error coefficient and 1 as the error compensation coefficient to perform error compensation calculation on the predicted material quantity to obtain the compensated material quantity.

8. The energy-saving power supply method for workshop energy consumption analysis according to claim 1, characterized in that, Optimize the energy consumption power of the equipment operation according to the compensated material quantity to obtain the optimal operating power, and perform energy-saving power supply, including: Randomly configure the operating power of the equipment; Obtain the current real-time power of the equipment, combine it with the operating power to obtain the switching energy consumption parameter, and analyze the qualified degree of the broken particle size according to the operating power and the compensated material quantity; Calculate the energy-saving fitness according to the switching energy consumption parameter, the operating power and the qualified degree of the broken particle size, as shown in the following formula: ； Among them, SAf is the energy-saving fitness degree, , and are weights, , and The sum of them is 1, is the preset switching energy consumption parameter, is the switching energy consumption parameter, P is the operating power, is the preset operating power of the device, K is the qualified degree of crushing particle size, is the preset qualified degree of crushing particle size; Continue to randomly configure the operating power of the equipment for iterative optimization until convergence, and retain the operating power with the largest energy-saving fitness as the optimal operating power for energy-saving power supply.

9. The energy-saving power supply method for workshop energy consumption analysis according to claim 8, characterized in that, Obtain the current real-time power of the equipment, combine it with the operating power to obtain the switching energy consumption parameter, and analyze the qualified degree of the broken particle size according to the operating power and the compensated material quantity, including: According to the power adjustment data record within the historical time of the equipment, retrieve the switching energy consumption parameter according to the real-time power and the operating power; According to the material crushing data record of the equipment, collect the sample material quantity set and the sample operating power set, and collect the proportion of the particle size of the material after crushing meeting the requirements under different sample material quantities and sample operating powers, and label it as the sample qualified degree of the broken particle size to obtain the sample qualified degree set of the broken particle size; Use the sample material quantity set, the sample operating power set and the sample qualified degree set of the broken particle size as training data and test data, and train the crushing predictor based on the feedforward neural network; Input the compensated material quantity and the operating power into the crushing predictor, and output to obtain the qualified degree of the broken particle size.

10. An energy-saving power supply system for workshop energy consumption analysis, characterized in that, For implementing the energy-saving power supply method for the workshop energy consumption analysis according to any one of claims 1 to 9, the system includes: A material quantity prediction module, which is used to collect the material image sequence and the sensing parameter sequence within the past preset time window in the workshop, and perform the prediction of the transported material quantity at the future preset moment to obtain the first predicted material quantity and the second predicted material quantity; An error coefficient acquisition module, configured to perform prediction error analysis based on the sensing parameter sequence to obtain a prediction error coefficient, and adjust the prediction error coefficient according to the first predicted material quantity and the second predicted material quantity to obtain an adjusted prediction error coefficient; A compensated material quantity module, configured to perform fusion processing and error compensation on the first predicted material quantity and the second predicted material quantity by using the adjusted prediction error coefficient to obtain a compensated material quantity; A power optimization module, configured to perform optimization on the power consumption of equipment operation according to the compensated material quantity to obtain an optimal operating power and perform energy-saving power supply.

Images