Device energy consumption detection method and apparatus, computer device and computer program product

Abstract

The application discloses a kind of equipment energy consumption detection method, device, computer equipment and computer program product.Therein, the method comprises: obtaining the running data and energy consumption data of target equipment in target operation period;Determine target working condition intervention contrast energy consumption model based on running data;Standard production condition parameters are input into target working condition intervention contrast energy consumption model, and standard energy consumption data is obtained;Based on running data, the target operation period is divided into multiple energy consumption responsibility slices;Based on standard energy consumption data, the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices is determined;Based on energy consumption data and baseline energy consumption data, energy consumption deviation is calculated;Based on energy consumption deviation, energy consumption detection result is obtained.The present application solves the technical problem that the current evaluation of potash fertilizer production equipment energy consumption is usually directly compared with energy consumption or unit energy consumption under actual operating conditions, lacks a systematic method for converting energy consumption to standard production conditions, resulting in inaccurate energy consumption detection results.

Description

Technical Field

[0001] This invention relates to the field of energy consumption management technology in potash fertilizer production, and more specifically, to a method, apparatus, computer equipment, and computer program product for detecting equipment energy consumption. Background Technology

[0002] In the field of energy consumption management in potash fertilizer production, existing technical solutions mostly rely on direct energy consumption metering and simple statistical analysis. Specifically, potash fertilizer companies typically deploy energy metering and monitoring systems during production. These systems collect operational and energy consumption data from key stages such as evaporation, drying, grinding, and conveying processes at metering points, and combine this data with production information to generate energy consumption statistical reports. However, these reports and analytical methods have significant limitations when dealing with the allocation of energy consumption responsibility under complex operating conditions.

[0003] Currently, energy consumption summaries at the process and equipment levels fail to adequately account for the impact of production condition fluctuations on energy consumption. In potash fertilizer production, operating conditions such as material composition, solution concentration, material moisture content, and equipment load continuously change, and these changes directly affect energy consumption fluctuations. Traditional methods often directly compare energy consumption or unit energy consumption under actual operating conditions, without establishing a unified standard energy consumption model under standard production conditions. Therefore, it is difficult to accurately isolate the impact of operating condition changes on energy consumption, resulting in a lack of objectivity and comparability in energy consumption comparisons between different processes, equipment, or operating methods.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, computer equipment, and computer program product for detecting equipment energy consumption, in order to at least solve the technical problem that current assessments of energy consumption in potash fertilizer production equipment typically involve directly comparing energy consumption or unit energy consumption under actual operating conditions, lacking a systematic method to uniformly convert energy consumption to standard production conditions, which leads to inaccurate energy consumption detection results.

[0006] According to one aspect of the present invention, a method for detecting equipment energy consumption is provided, comprising: acquiring operating data and energy consumption data of a target equipment during a target operating period; determining a target operating condition intervention control energy consumption model based on the operating data, wherein the target operating condition intervention control energy consumption model characterizes the influence model of operating conditions on the standard energy consumption data of the target equipment; inputting preset standard production condition parameters into the target operating condition intervention control energy consumption model to obtain standard energy consumption data; dividing the target operating period into multiple energy consumption responsibility slices based on the operating data, wherein the energy consumption responsibility slice characterizes a time segment in which the operating data of the target equipment remains unchanged; determining baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on the standard energy consumption data; calculating the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices based on the energy consumption data and the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices; and obtaining the energy consumption detection result of the target equipment based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices.

[0007] Optionally, based on operational data, a target operating condition intervention control energy consumption model is determined, including: calculating and generating feature data based on process solution concentration data, material moisture data, and equipment load data in the operational data, wherein the feature data includes: solution state feature data, heat exchange state feature data, and equipment load state feature data; discretizing and encoding the process parameters in the operational data to obtain operation codes; generating an operating condition sample sequence based on the operation codes and feature data; and training the preset initial operating condition intervention control energy consumption model using the operating condition sample sequence to obtain the target operating condition intervention control energy consumption model.

[0008] Optionally, preset standard production condition parameters are input into the target operating condition intervention control energy consumption model to obtain standard energy consumption data, including: acquiring historical operating data of the target equipment; selecting time segments from the historical operating data that meet preset stability thresholds and output thresholds as candidate standard production segments; calculating the statistical characteristics of solution concentration, material moisture content, and equipment load based on the candidate standard production segments to obtain a set of candidate standard production condition parameters; filtering from the set of candidate standard production condition parameters based on preset energy consumption level thresholds to determine standard production condition parameters; adjusting the operating condition sample sequence using the standard production condition parameters to obtain a standard production condition operating condition sample sequence; and inputting the standard production condition operating condition sample sequence into the target operating condition intervention control energy consumption model to obtain standard energy consumption data.

[0009] Optionally, based on standard energy consumption data, baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices is determined, including: determining standard energy consumption data between the start and end times of each of the multiple energy consumption responsibility slices based on standard energy consumption data; determining steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment corresponding to each of the multiple energy consumption responsibility slices based on the standard energy consumption data between the start and end times of each of the multiple energy consumption responsibility slices; adding the energy consumption increments hourly in chronological order based on the steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment corresponding to each of the multiple energy consumption responsibility slices to obtain the steam energy consumption baseline value, hot air energy consumption baseline value, and electricity consumption baseline value corresponding to each of the multiple energy consumption responsibility slices; and determining the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on the steam energy consumption baseline value, hot air energy consumption baseline value, and electricity consumption baseline value corresponding to each of the multiple energy consumption responsibility slices.

[0010] Optionally, the energy consumption detection result of the target equipment is obtained based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices, including: dividing the multiple energy consumption responsibility slices into multiple slice sets based on the section information in the operation data; determining the sum of energy consumption deviations corresponding to each of the multiple slice sets based on the energy consumption deviations corresponding to each of the multiple energy consumption responsibility slices; and determining the energy consumption detection result based on the sum of energy consumption deviations corresponding to each of the multiple slice sets.

[0011] Optionally, when multiple devices and the target device are both of the same type, the method further includes: obtaining the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices corresponding to the multiple devices; determining the average energy consumption deviation based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices corresponding to the multiple devices; and determining the energy consumption evaluation result corresponding to the target device type based on the average energy consumption deviation.

[0012] According to another aspect of the present invention, an energy consumption detection device for equipment is also provided, comprising: an acquisition module for acquiring operating data and energy consumption data of a target equipment during a target operating period; a construction module for determining a target operating condition intervention control energy consumption model based on the operating data, wherein the target operating condition intervention control energy consumption model characterizes the influence model of operating conditions on the standard energy consumption data of the target equipment; an input module for inputting preset standard production condition parameters into the target operating condition intervention control energy consumption model to obtain standard energy consumption data; a division module for dividing the target operating period into multiple energy consumption responsibility slices based on the operating data, wherein the energy consumption responsibility slice characterizes a time segment in which the operating data of the target equipment remains unchanged; a first determination module for determining baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on the standard energy consumption data; a calculation module for calculating the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices based on the energy consumption data and the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices; and a second determination module for obtaining the energy consumption detection result of the target equipment based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices.

[0013] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is running, it controls the device where the non-volatile storage medium is located to execute any of the above-described device power consumption detection methods.

[0014] According to another aspect of the present invention, a computer device is also provided, the computer device including a processor, the processor being configured to run a program, wherein the program executes any of the above-described device power consumption detection methods during runtime.

[0015] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements any of the above-described device energy consumption detection methods.

[0016] In this embodiment of the invention, an equipment energy consumption detection method is employed. This involves acquiring the operating data and energy consumption data of the target equipment during a target operating period. Based on the operating data, a target operating condition intervention control energy consumption model is determined, whereby the target operating condition intervention control energy consumption model characterizes the influence model of operating conditions on the standard energy consumption data of the target equipment. Preset standard production condition parameters are input into the target operating condition intervention control energy consumption model to obtain standard energy consumption data. Based on the operating data, the target operating period is divided into multiple energy consumption responsibility slices, whereby an energy consumption responsibility slice characterizes a time segment in which the operating data of the target equipment remains unchanged. Based on the standard energy consumption data, multiple energy consumption responsibility slices are determined. The system calculates the baseline energy consumption data corresponding to each energy consumption responsibility slice; based on the energy consumption data and the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices, it calculates the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices; based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices, it obtains the energy consumption detection results of the target equipment, thereby achieving the goal of converting energy consumption to standard production conditions, thus realizing the technical effect of improving the accuracy of energy consumption detection results. This solves the technical problem that the current assessment of energy consumption of potash fertilizer production equipment usually involves directly comparing energy consumption or unit energy consumption under actual operating conditions, lacking a systematic method to uniformly convert energy consumption to standard production conditions, which leads to inaccurate energy consumption detection results. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a computer terminal for implementing a device energy consumption detection method is shown.

[0019] Figure 2 This is a schematic flowchart of the device energy consumption detection method provided according to an embodiment of the present invention;

[0020] Figure 3 This is a schematic flowchart of an equipment energy consumption detection method provided by an optional embodiment of the present invention;

[0021] Figure 4 This is a flowchart of standard production condition parameters provided by an optional embodiment of the present invention;

[0022] Figure 5 This is a flowchart of the energy consumption data of the intervention control model and standard production conditions provided by an optional embodiment of the present invention.

[0023] Figure 6 This is a flowchart of the slice baseline energy consumption data calculation provided by an optional embodiment of the present invention;

[0024] Figure 7 This is a structural block diagram of the equipment energy consumption detection device provided in an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] According to an embodiment of the present invention, a method embodiment for detecting device energy consumption is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0028] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a device energy consumption detection method is shown. Figure 1 As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0029] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0030] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the device energy consumption detection method in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the device energy consumption detection method of the aforementioned application. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0031] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0032] Figure 2 This is a flowchart illustrating the device energy consumption detection method provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the method includes the following steps:

[0033] Step S202: Obtain the operating data and energy consumption data of the target device during the target runtime.

[0034] In this step, various sensors, including but not limited to temperature sensors, pressure sensors, flow meters, electricity meters, and hygrometers, can be installed on key parts of the target equipment to monitor its operating parameters and energy consumption in real time. Based on the target operating period, operating data and energy consumption data for the corresponding time points are selected from the data repository. The data can be cleaned, and missing values ​​can be removed to ensure accuracy and reliability.

[0035] The system can analyze operational data to extract various process parameters related to the target equipment, such as solution concentration, material moisture content, and equipment load. These parameters are then aligned with timestamps to form time-series data, facilitating subsequent analysis and modeling.

[0036] It can also analyze energy consumption data to determine the amount of steam, hot air, and electricity consumed by the equipment during the target operating period. This ensures that the timestamps of energy consumption data correspond to those of operating data, thereby accurately linking equipment operating status and energy consumption performance.

[0037] Operational data and energy consumption data can be integrated into a single dataset, forming a complete record that includes timestamps, process parameters, and energy consumption measurements. This integrated data can then be used to build energy consumption models and analyze the energy consumption characteristics of equipment under different operating conditions.

[0038] Optionally, the metering points of the high-energy-consuming potash fertilizer equipment can be used as input to obtain the operating data and energy consumption data of the evaporation section, drying section, grinding and conveying section, and the operating data and energy consumption data can be matched according to the timestamp to form a continuous operating raw data sequence.

[0039] Through the above steps, industrial enterprises such as potash fertilizer producers can obtain comprehensive and accurate equipment operation data and energy consumption data, providing a solid data foundation for further energy consumption analysis, model building, and responsibility assessment.

[0040] Step S204: Based on the operating data, determine the target operating condition intervention control energy consumption model, wherein the target operating condition intervention control energy consumption model characterizes the impact model of operating conditions on the standard energy consumption data of the target equipment.

[0041] In this step, the operating condition intervention control energy consumption model is an energy consumption prediction and analysis model based on artificial intelligence (especially deep learning technology) used in potash fertilizer production. The model aims to quantify and analyze the energy consumption changes of high-energy-consuming equipment in potash fertilizer production under different operating conditions, thereby achieving accountability and refined management of energy consumption. Energy-related state features, such as process solution concentration, material moisture content, and equipment load, can be extracted from operational data. These features are converted into numerical vector forms compatible with the model input. Then, based on the section parameters in the operational data, the configuration parameters of the evaporation section, the parameters of the drying section, and the grinding and conveying load parameters are converted into operation codes. These codes are used to characterize different operating modes and equipment states. A multi-input, multi-output operating condition intervention control energy consumption model can be designed, capable of simultaneously processing solution state feature data, heat exchange state feature data, equipment load state feature data, and operation codes. Internally, the model includes a solution feature sub-network, a heat exchange feature sub-network, an equipment load feature sub-network, and an operating mode sub-network, as well as at least one fully connected network layer for feature fusion and energy consumption prediction. All network layer parameters in the model are initialized, including weights and biases. Then you can set the loss function and optimizer to prepare for model training.

[0042] Construct a training dataset where the input consists of state feature data and operation codes, and the output is the standard energy consumption data (steam energy consumption, hot air energy consumption, and electricity consumption increment) of the target equipment under the specified operating condition. The dataset should include historical operating data and energy consumption data, along with their corresponding values ​​under standard production conditions. Train the target operating condition intervention control energy consumption model using the training dataset, adjusting network layer parameters through backpropagation to minimize the difference between predicted and actual energy consumption. Monitor the training process, adjusting hyperparameters (such as learning rate and batch size) to ensure model convergence and good generalization ability. Evaluate the model performance on the validation dataset to check for overfitting or underfitting. Based on the evaluation results, adjust the model architecture or parameters until the model has satisfactory predictive ability on the validation set, thus obtaining the target operating condition intervention control energy consumption model.

[0043] Step S206: Input the preset standard production condition parameters into the target working condition intervention control energy consumption model to obtain standard energy consumption data.

[0044] In this step, the standard production condition parameters should reflect the operating conditions in best practices for potash fertilizer production, including but not limited to the optimal concentration of the process solution, the optimal moisture content of the material, the ideal load conditions of the equipment, and recommended operating methods. These parameters are typically determined based on historical performance data, industry standards, equipment manufacturer guidelines, or expert knowledge. The determined standard production condition parameters can be converted into a model-readable format, such as converting solution concentration, material moisture content, and equipment load into numerical vectors. Operating methods should be coded and represented as discrete numerical codes for easy model input.

[0045] The solution state characteristics, heat exchange state characteristics, equipment load state characteristics, and operation codes in the standard production condition parameters are mapped to timestamps, even if these parameters are constant, and prepared according to the time series format required by the model. The operating condition intervention control energy consumption model is invoked, using the prepared standard production condition parameters as input. After the model execution is complete, the steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment output by the model are read. These data represent the theoretical energy consumption level of equipment operation under standard production conditions. The energy consumption increment data output by the model can be sorted by timestamp to form an energy consumption time series under standard production conditions. The standard energy consumption data is saved for subsequent energy consumption responsibility segmentation and energy consumption deviation calculation.

[0046] Through the steps described above, a comparative energy consumption model based on operational condition intervention can be used to transform preset standard production condition parameters into standard energy consumption data. This provides a unified energy consumption benchmark for comparison, regardless of changes in actual operating conditions, enabling a more objective and accurate evaluation of energy consumption responsibility in the production process and the identification of potential energy-saving opportunities.

[0047] Step S208: Based on the operating data, the target operating period is divided into multiple energy consumption responsibility slices, wherein the energy consumption responsibility slice represents a time segment in which the operating data of the target device remains unchanged.

[0048] In this step, the operational data can be preprocessed to ensure that all energy-related state characteristic data (such as solution state, heat exchange state, and equipment load) and operation records have a unified timestamp, forming continuous time-series data. By monitoring the time series of section information, equipment information, and operation mode information, the moments when these information changes are identified. These changes may be due to adjustments in the production process, equipment switching, or changes in operating modes. Once the moments of information change are identified, these moments are used as boundary points to divide the target operating period into multiple sub-periods, each constituting an energy consumption responsibility slice. Within each slice, the section information, equipment information, and operation mode information remain unchanged, meaning that the equipment operates under the same conditions within that slice. For each identified sub-period (i.e., energy consumption responsibility slice), its start and end times, as well as the constant section information, equipment information, and operation mode information during this period, are extracted. These attributes are then bound to the corresponding energy consumption data to form an energy consumption responsibility slice record, which contains the energy consumption baseline and measured energy consumption of a specific device under specific conditions.

[0049] For example, suppose that in a continuous stretch of operational data, device A operates using parameter P1 between 10:00 AM and 11:00 AM, and switches to parameter P2 from 11:00 AM to 1:00 PM. This means that 10:00 AM to 11:00 AM can be considered one energy consumption responsibility slice, while 11:00 AM to 1:00 PM is another slice.

[0050] Step S210: Based on standard energy consumption data, determine the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices.

[0051] In this step, we can first ensure that the standard energy consumption data (i.e., the incremental data of steam energy consumption, hot air energy consumption and electricity consumption under standard production conditions) are aligned with the timestamps in the operating data to form a time series.

[0052] Standard energy consumption data is linked to the section information, equipment information, and operation mode information in the operational data to ensure that the energy consumption data at each time point corresponds to the corresponding operational condition information. For each energy consumption responsibility slice, the steam, hot air, and electricity consumption increment sequences are extracted from the standard energy consumption data within its time range. These sequences are ensured to be consistent with the time range of the slice and the fixed operational condition information within the slice. The energy consumption increment sequences within each slice can be added hourly using a time step consistent with the operational data acquisition cycle. The steam energy consumption baseline value, hot air energy consumption baseline value, and electricity consumption baseline value for each energy consumption responsibility slice are calculated. These values ​​reflect the theoretical energy consumption of the equipment within the slice under standard production conditions.

[0053] The calculated baseline energy consumption value for each slice is bound to the section information, equipment information, and operation mode information of that slice. This creates a record containing slice attributes and baseline energy consumption data, which constitutes the slice baseline energy consumption data set.

[0054] By following the steps above, the baseline energy consumption data for each energy consumption responsibility slice can be accurately calculated based on energy consumption data under standard production conditions.

[0055] Step S212: Based on the energy consumption data and the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices, calculate the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices.

[0056] In this step, energy consumption data is mapped to the time range of each energy consumption responsibility slice to ensure that the timestamps of the energy consumption data accurately reflect the energy consumption measurements of each slice. For each energy consumption responsibility slice, the difference between its actual energy consumption and the baseline energy consumption is calculated, i.e., the energy consumption deviation. Here, energy consumption deviation = actual energy consumption - baseline energy consumption. Steam energy consumption deviation, hot air energy consumption deviation, and electricity consumption deviation can be calculated separately. If the actual energy consumption is higher than the baseline energy consumption, it indicates that there is excessive energy consumption within that slice, which may require optimization of equipment operation or operating methods. If the actual energy consumption is lower than the baseline energy consumption, it may mean that there are energy-saving operations or equipment efficiency improvements. The calculated energy consumption deviation data can be bound to the corresponding energy consumption responsibility slice information, including the slice's start and end times, section information, equipment information, and operating method information. This forms a complete energy consumption deviation dataset, facilitating subsequent responsibility evaluation and energy consumption management.

[0057] Step S214: Based on the energy consumption deviations corresponding to each of the multiple energy consumption responsibility slices, the energy consumption detection results of the target device are obtained.

[0058] In this step, the energy consumption deviations (steam, hot air, and electricity consumption deviations) of each energy consumption responsibility segment can be categorized based on section information, equipment information, and shift information. Within each category, the corresponding energy consumption deviations of all segments are summed to obtain a total energy consumption deviation summary value by section, equipment, and shift dimension. Based on section information, the cumulative energy consumption deviation for each section is calculated. This helps to understand which sections in the entire process flow require improvement in energy consumption control. For a specific piece of equipment, the energy consumption deviations of all relevant segments are summed using equipment information to obtain the total energy consumption deviation for that equipment. This can identify which equipment performs poorly in terms of energy consumption. Based on shift information, the energy consumption deviations of all segments operating under that shift are summed to form a shift-level energy consumption deviation result. This helps to evaluate the operational efficiency and energy consumption control capabilities of different shifts. By analyzing the summary results of energy consumption deviations, it can be determined which section, which piece of equipment, or which shift bears significant responsibility for exceeding energy consumption limits. Furthermore, it can identify which operating methods or equipment states lead to higher energy consumption, providing guidance for optimizing production processes and equipment operation.

[0059] Through the above steps, potash fertilizer producers can gain a comprehensive understanding of the energy consumption status of target equipment from multiple dimensions, identify energy-saving potential, and take corresponding measures to reduce energy consumption and improve production efficiency. This detection method based on energy consumption responsibility segments and energy consumption deviations provides strong support for enterprises' production optimization and energy cost control.

[0060] As an optional embodiment, the target operating condition intervention control energy consumption model is determined based on operational data, including: calculating and generating feature data based on process solution concentration data, material moisture data, and equipment load data in the operational data, wherein the feature data includes: solution state feature data, heat exchange state feature data, and equipment load state feature data; discretizing and encoding the process parameters in the operational data to obtain operation codes; generating an operating condition sample sequence based on the operation codes and feature data; and training a preset initial operating condition intervention control energy consumption model using the operating condition sample sequence to obtain the target operating condition intervention control energy consumption model.

[0061] Optionally, the process solution concentration data, material moisture data, and equipment load data in the operational data can be transformed into feature data with physical meaning, including solution state feature data, heat exchange state feature data, and equipment load state feature data. These data can accurately characterize the key operating conditions in the potash fertilizer production process. Next, section parameters, such as evaporation section configuration parameters, drying section parameters, and grinding and conveying load parameters, are discretized and encoded into operation codes. This encoding process simplifies complex operating methods into a computer-processable form. Subsequently, the operation codes are combined with the feature data to generate an operating condition sample sequence. This step ensures the comprehensiveness and representativeness of the model input. Finally, based on the operating condition sample sequence, a preset initial operating condition intervention control energy consumption model is trained. By adjusting the model parameters, the model can accurately predict the increase in steam energy consumption, hot air energy consumption, and electricity consumption under given operation codes and feature data.

[0062] Specifically, the concentration data of the process solution is extracted from the operational data. The concentrations of effective components, impurities, and the overall concentration are combined and arranged into a fixed-length numerical vector according to a predetermined order. Using material moisture data and temperature information from the evaporation and drying sections, inlet and outlet temperature differences, heat transfer temperature differences, and heat exchange capacity indicators are calculated, and these indicators are then combined into a fixed-length numerical vector. Equipment load data, such as ball mill power, pump flow rate, and fan speed, are normalized and segmented, and then combined into a fixed-length numerical vector to reflect the real-time load status of the equipment. The configuration parameters of the evaporation section, the drying section, and the load parameters of the grinding and conveying sections are discretized, and the parameters are converted into fixed-length numerical vectors using a preset mapping rule to form operation codes. Solution state characteristic data, heat exchange state characteristic data, equipment load state characteristic data, and operation codes are matched by timestamps, combined with section information and equipment information, to form a sequence of operating condition samples with operation mode labels. This provides structured, multi-dimensional input data for model training. The operating condition sample sequence is used to train a preset initial operating condition intervention control energy consumption model. During model training, input feature data (solution state, heat exchange state, equipment load state, and operation code) are matched with measured energy consumption increments (steam, hot air, and electricity consumption) to optimize model parameters, enabling the model to accurately predict energy consumption increments. Training continues until the model's prediction error on the validation set reaches an acceptable range or converges. At this point, the resulting target operating condition intervention control energy consumption model can accurately predict energy consumption increments under a given operating mode based on the input feature data.

[0063] This process utilized a large amount of historical operational and energy consumption data, employing deep learning technology to capture the dynamic changes in energy consumption under complex operating conditions. This enabled refined modeling of energy consumption in high-energy-consuming equipment during potash fertilizer production, providing technical support for subsequent energy consumption responsibility evaluations by work section, equipment, and shift. After training, the target operating condition intervention control energy consumption model can output three types of energy consumption increments under unified standard operating conditions, thus supporting the quantitative assessment and management optimization of energy consumption responsibility. This comprehensive solution not only considers the impact of material state, heat exchange efficiency, and equipment load on energy consumption but also incorporates the intervention effect of operating methods, forming a comprehensive and accurate energy consumption model. This helps potash fertilizer companies achieve refined energy consumption management and energy conservation goals.

[0064] As an optional embodiment, preset standard production condition parameters are input into the target operating condition intervention control energy consumption model to obtain standard energy consumption data. This includes: acquiring historical operating data of the target equipment; selecting time segments from the historical operating data that meet preset stability thresholds and output thresholds as candidate standard production segments; calculating the statistical characteristics of solution concentration, material moisture content, and equipment load based on the candidate standard production segments to obtain a set of candidate standard production condition parameters; filtering from the set of candidate standard production condition parameters based on preset energy consumption level thresholds to determine standard production condition parameters; adjusting the operating condition sample sequence using the standard production condition parameters to obtain a standard production condition operating condition sample sequence; and inputting the standard production condition operating condition sample sequence into the target operating condition intervention control energy consumption model to obtain standard energy consumption data.

[0065] Optionally, to establish an energy consumption model based on unified standard conditions, time segments that meet preset stability and output thresholds are first selected from the historical operating data of the target equipment as candidate standard production segments. Here, the stability and output thresholds ensure the comparability and representativeness of the operating conditions. Based on these candidate segments, the statistical characteristics of solution concentration, material moisture content, and equipment load are calculated, forming a set of candidate standard production condition parameters. Subsequently, the parameters in the set are screened using preset energy consumption level thresholds to determine a set of standard parameters that reflect standard production conditions. This set of parameters ensures the consistency of model input and the rationality of energy consumption assessment. Next, the determined standard parameters are used to adjust the operating condition sample sequence, generating a standard production condition operating condition sample sequence. This sequence ensures the consistency between the model input and the standard conditions. Finally, the standard production condition operating condition sample sequence is fed into the target operating condition intervention control energy consumption model to obtain energy consumption data under standard production conditions, i.e., standard energy consumption data.

[0066] Specifically, historical operating data of the target equipment is collected from the operation records, including process solution concentration, material moisture content, equipment load, and output data, ensuring that the data covers all stages and conditions of equipment operation. Based on preset stability thresholds (such as the fluctuation range of solution concentration, material moisture content, and equipment load) and output thresholds, time segments that meet the criteria are selected from the historical operating data. These segments should reflect the equipment's operation under stable conditions. For each candidate segment, statistical characteristics of solution concentration, material moisture content, and equipment load are calculated, such as average, standard deviation, maximum, and minimum values, forming a set of candidate standard production condition parameters. Using preset energy consumption level thresholds, such as comprehensive energy consumption indicators, state parameters that represent high efficiency and low energy consumption of the equipment under normal operating conditions are selected from the set of candidate standard production condition parameters as standard production condition parameters. Using the determined standard production condition parameters, the solution concentration, material moisture content, and equipment load status in the historical operating data are adjusted to map them to standard production conditions, forming a sequence of operating condition samples under standard production conditions. The standard production condition sample sequence is input into the pre-trained target condition intervention control energy consumption model to predict the energy consumption increment of each sample under standard production conditions, including the increments of steam energy consumption, hot air energy consumption, and electricity energy consumption. The predicted energy consumption increment data are integrated to form a standard energy consumption dataset, which accurately reflects the theoretical energy consumption level of the target equipment under standard production conditions.

[0067] The entire process not only improves the applicability and accuracy of the energy consumption model, but also provides a reliable foundation for subsequent energy consumption responsibility assessment. It helps to accurately evaluate the energy consumption performance of different work sections, equipment and operating methods under standard conditions, thereby achieving refined energy consumption management and responsibility division.

[0068] As an optional embodiment, based on standard energy consumption data, baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices is determined, including: determining standard energy consumption data between the start and end times of each of the multiple energy consumption responsibility slices based on the standard energy consumption data between the start and end times of each of the multiple energy consumption responsibility slices; determining the steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment corresponding to each of the multiple energy consumption responsibility slices based on the standard energy consumption data between the start and end times of each of the multiple energy consumption responsibility slices; adding the energy consumption increments hourly in chronological order based on the steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment corresponding to each of the multiple energy consumption responsibility slices to obtain the steam energy consumption baseline value, hot air energy consumption baseline value, and electricity consumption baseline value corresponding to each of the multiple energy consumption responsibility slices; and determining the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on the steam energy consumption baseline value, hot air energy consumption baseline value, and electricity consumption baseline value corresponding to each of the multiple energy consumption responsibility slices.

[0069] Optionally, based on the start and end times of each energy consumption responsibility segment, corresponding data segments are selected from the overall energy consumption data. Based on these data segments, specific steam energy consumption increments, hot air energy consumption increments, and electricity consumption increments within the responsibility segment can be calculated. This step essentially provides a quantitative description of the energy consumption characteristics of the responsibility segment. Subsequently, these energy consumption increments are integrated into the baseline energy consumption value for each responsibility segment by adding them hourly. This method ensures that the baseline energy consumption data is closely related to the operating conditions of the responsibility segment, reflecting the expected energy consumption level under standard operating conditions. Finally, by associating the baseline energy consumption values ​​with the section, equipment, and operating mode information of each responsibility segment, detailed baseline energy consumption data for each responsibility segment is formed.

[0070] Specifically, each energy consumption responsibility segment can be checked to determine its specific start and end times. Ensure that the section information, equipment information, and operation mode information remain consistent within this time frame. Based on the start and end times of each segment, extract corresponding data segments from the standard energy consumption data. These data segments should include the steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment within the specified time frame. For each extracted segment's standard energy consumption data, the steam energy consumption increment is added hourly in chronological order to obtain the steam energy consumption baseline value for that segment. Similarly, the hot air energy consumption increment and electricity consumption increment are accumulated separately to obtain the hot air energy consumption baseline value and electricity consumption baseline value. The calculated steam energy consumption baseline value, hot air energy consumption baseline value, and electricity consumption baseline value are then bound to the section information, equipment information, and operation mode information for each segment. This forms the baseline energy consumption data for each segment, containing the expected energy consumption of that segment under standard production conditions.

[0071] The baseline energy consumption data of all slices are organized in chronological order or by work section / equipment / operation mode to form a baseline energy consumption data set. This set provides a unified energy consumption benchmark for subsequent energy consumption deviation analysis, facilitating the comparison of energy consumption responsibility between different slices.

[0072] This series of operations not only quantifies the energy consumption performance of the responsibility slice, but also provides a key benchmark for subsequent energy consumption responsibility evaluation. It helps to accurately measure the deviation between actual energy consumption and expected baseline, thereby achieving refined energy consumption management and clear responsibility attribution.

[0073] As an optional embodiment, the energy consumption detection result of the target equipment is obtained based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices, including: dividing the multiple energy consumption responsibility slices into multiple slice sets based on the section information in the operation data; determining the sum of energy consumption deviations corresponding to each of the multiple slice sets based on the energy consumption deviations corresponding to each of the multiple energy consumption responsibility slices; and determining the energy consumption detection result based on the sum of energy consumption deviations corresponding to each of the multiple slice sets.

[0074] Optionally, based on the section information in the operational data, multiple energy consumption responsibility segments are divided into multiple segment sets, each set covering all segments of the same section. Then, based on the energy consumption deviations corresponding to each of the multiple energy consumption responsibility segments, the sum of energy consumption deviations corresponding to each of the multiple segment sets is determined. By summing the energy consumption deviations of all segments within the same set, the total energy consumption deviation for that section is obtained, thus providing data support for the energy consumption assessment of that section. Finally, based on the sum of energy consumption deviations corresponding to each of the multiple segment sets, the energy consumption detection result is determined. This result not only reflects the energy consumption level of the target equipment under standard production conditions but also reveals the contribution of each section, equipment, and operating method to the energy consumption deviation, providing a quantitative basis for the refined management and responsibility evaluation of high-energy-consuming equipment in potash fertilizer production.

[0075] Specifically, based on the section information in the operational data, all sections associated with the target equipment are identified. All energy consumption responsibility slices related to the same section are grouped together to form multiple slice sets, each representing the energy consumption responsibility of a specific section at different time points. For each slice set, the steam energy consumption deviation, hot air energy consumption deviation, and electricity consumption deviation of all member slices are summed. The summed result is the total energy consumption deviation value for that section, reflecting the overall energy consumption deviation of that section. Based on the total energy consumption deviation value of all slice sets, a comprehensive analysis is performed to identify which sections bear primary responsibility for the overall energy consumption exceeding the standard. An evaluation system can be considered to assign a score or rating to each section based on the magnitude of the energy consumption deviation, facilitating intuitive understanding and comparison.

[0076] As an optional embodiment, when multiple devices and the target device are both of the target device type, the method further includes: obtaining the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices corresponding to the multiple devices; determining the average energy consumption deviation based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices corresponding to the multiple devices; and determining the energy consumption evaluation result corresponding to the target device type based on the average energy consumption deviation.

[0077] Optionally, when multiple devices of the same type exist, the method further includes acquiring the energy consumption deviations of these devices under each energy consumption responsibility slice, calculating the average value based on these deviations, and thus determining the overall energy consumption evaluation result for that device type. This process first collects energy consumption deviation data for all devices in their relevant slices, and then uses statistical analysis to derive the average energy consumption deviation, aiming to assess the average energy consumption level and deviation of the device type under standard production conditions. Analysis based on the average energy consumption deviation helps identify the energy consumption characteristics of specific device types in production, providing precise data support for equipment upgrades, process optimization, and personnel training, thereby promoting the improvement of overall production efficiency and energy utilization efficiency.

[0078] An optional embodiment is provided below. Figure 3 This is a schematic flowchart of a device energy consumption detection method provided by an optional embodiment of the present invention, as shown below. Figure 3 As shown, where:

[0079] S1. Obtain the operating data and energy consumption data of high-energy-consuming potash fertilizer equipment, and determine the standard potash fertilizer production condition parameters according to the potash fertilizer production process.

[0080] S2. Based on the operating data, calculate the process solution concentration data, material moisture data, and equipment load data to generate solution state characteristic data, heat exchange state characteristic data, and equipment load state characteristic data;

[0081] S3. Based on solution state characteristic data, heat exchange state characteristic data, equipment load state characteristic data, and operation records in the operation data, construct an operating condition intervention control energy consumption model. Represent the configuration parameters of the evaporation section, the parameters of the drying section, and the grinding and conveying load parameters as operation codes. When the operating condition intervention control energy consumption model is input with state characteristic data and operation codes, it outputs the steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment. Based on the standard potash fertilizer production condition parameters, convert the operation records into standard production condition state sequence data. Calculate the standard production condition energy consumption data using the operating condition intervention control energy consumption model.

[0082] S4. Based on the standard production condition energy consumption data and the section information, equipment information and operation mode information in the operation data, the continuous operation process is divided into several energy consumption responsibility slices. Each energy consumption responsibility slice corresponds to a time segment of a combination of a section, equipment and operation mode. Within the time range of each energy consumption responsibility slice, the steam energy consumption increment, hot air energy consumption increment and electricity consumption increment in the standard production condition energy consumption data are summarized to obtain the slice baseline energy consumption data.

[0083] S5. Based on the energy consumption data of the slice baseline and the energy consumption data, calculate the actual energy consumption and energy consumption deviation of each energy consumption responsibility slice to obtain the energy consumption deviation data.

[0084] S6. Aggregate energy consumption deviation data by work section, equipment and team, and output energy consumption responsibility evaluation results for energy consumption responsibility evaluation of high energy-consuming potash fertilizer equipment.

[0085] Figure 4 This is a flowchart of standard production condition parameters provided by an optional embodiment of the present invention, such as... Figure 4 As shown, the metering points of the high-energy-consuming potash fertilizer equipment are used as input, and the data is collected according to the timestamps of the data acquisition system. The operating data and energy consumption data of the evaporation section, drying section, grinding and conveying section are correlated to obtain a continuous operating raw data sequence, and the operating data is denoted as... This includes process solution concentration data. Material moisture data Equipment load data Production data , This represents the numerical combination of the effective ingredient concentration and impurity content at each moment. This represents the moisture content of the material at any given moment. This represents the numerical combination of ball mill power, pump flow rate, and fan speed at any given moment. This represents the output value at each moment, and the energy consumption data is recorded as... This includes a series of steam energy consumption measurements. Hot air energy consumption measurement value sequence With power consumption measurement value sequence Embedding section information and equipment information and The index maintains the correspondence between the time series;

[0086] Based on the section information and equipment information in the continuous operation original data sequence, and The data is categorized at the section and equipment levels, and section-level operation sequence data is constructed. Using the equipment status of each time period as input, the configuration parameters of the evaporation section are identified. Drying section parameters With grinding and conveying load parameters ,Will , and Bind to the corresponding work section-level operation sequence data to form a sequence marked with operation mode information, and maintain... , , and The original values ​​and time sequence are used to support the subsequent generation of solution state characteristic data, heat exchange state characteristic data and equipment load state characteristic data based on the section-level operation sequence data;

[0087] Based on the potash fertilizer production process, time segments that meet preset stability and yield thresholds are selected from the process-level operational sequence data as candidate standard production segments. The stability threshold is denoted as... Based on time collection cycle For any time segment, the time step is defined as follows: , and Calculate the fluctuation range separately, and denote the fluctuation range as follows: , and ,in Within this segment The difference between the maximum and minimum values, for The difference between the maximum and minimum values, for The weighted sum of the differences between the hourly maximum and minimum values ​​of each component, when , and Not exceeding When the time is considered stable, the output threshold is recorded as... , in the same period of cumulative addition The total output is obtained by summing the results within this segment. ,when Not less than At that time, it was determined that the production capacity requirements were met, and for those that met the requirements... and For each candidate standard production segment, the statistical feature vector of the process solution concentration data is calculated. Statistical feature vector of material moisture data Statistical feature vector of equipment load data The statistical feature vector consists of the mean, standard deviation, maximum, and minimum values ​​arranged in a fixed order, forming candidate standard potash fertilizer production condition parameters. The set of parameters for all segments is denoted as... And maintain the binding relationship with section information, equipment information and operation method information;

[0088] by As input, preset production capacity requirements and comprehensive energy consumption level thresholds are used to... The screening process was conducted, and the production capacity requirements were recorded as follows: In terms of total output As a basis for judgment, when Not less than The corresponding parameters are retained, and the comprehensive energy consumption level threshold is recorded as follows: Within this segment , and By accumulating the values ​​over the same period, a comprehensive energy consumption index can be obtained. ,when No more than The corresponding parameters are retained at the same time, for those that simultaneously satisfy and Candidate parameters, calculate , and Difference between different candidate fragments Difference The sum of the absolute differences of each component is used to calculate the degree of difference. The smallest candidate parameter is used as the standard potash fertilizer production condition parameter, denoted as . ,Will Bind to section-level operation sequence data, to To constrain the generation of standard production condition state sequence data in subsequent processes, , and The solution state characteristic data, heat transfer state characteristic data, and equipment load state characteristic data are mapped to the four input branches of the input layer of the energy consumption model for intervention under operating conditions, and are used as follows: , and The generated operation code enables the working condition intervention control energy consumption model to output steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment under unified standard potash fertilizer production condition parameters, providing direct support for the calculation of subsequent slice baseline energy consumption data and energy consumption deviation data.

[0089] Figure 5 This is a flowchart of the energy consumption data of the intervention control model and standard production conditions provided by an optional embodiment of the present invention, such as... Figure 5 As shown, the timestamp of the data acquisition system is used. As an index, the operational data is correlated with the monitoring data of the equipment in the process section, forming a time-series operational data that includes process solution concentration data, material moisture data, and equipment load data. This time-series operational data is denoted as... The process solution concentration data is denoted as Material moisture data is recorded as Equipment load data is recorded as The time step is recorded as The inlet temperature of the evaporation section is denoted as... The outlet temperature of the evaporation section is recorded as The inlet temperature of the drying section is recorded as The outlet temperature of the drying section is recorded as The hot air temperature of the hot air furnace is recorded as Meanwhile, the power of the ball mill is recorded as Pump flow rate is recorded as The fan speed is recorded as ,according to This ensures that the subsequently generated solution state characteristic data, heat exchange state characteristic data, and equipment load state characteristic data have a unified time reference.

[0090] by and As input, calculate the solution state characteristic data, and record the concentration of the effective component as... The impurity content is recorded as The total concentration is denoted as With preset weights , and right , and Perform a linear combination, specifically, at each time step, ... Multiply ,Will Multiply ,Will Multiply Then, add the products of the three terms together to obtain the solution component strength, which is denoted as . The weights are determined by the potash fertilizer production process configuration and remain unchanged during operation. , , and Arranged in a preset order, they form a fixed-length numerical vector, denoted as . Numerical vectors are denoted as , Used as input to the solution feature sub-network, enabling the solution feature sub-network to receive solution state feature data with consistent dimensions and physical meaning at each time step, providing a basis for generating solution feature vectors in the subsequent working condition intervention comparison energy consumption model;

[0091] by , , , , and As input, calculate the heat transfer state characteristic data, and record the temperature difference between the inlet and outlet of the evaporator as... ,Depend on minus The temperature difference between the inlet and outlet of the drying equipment is recorded as follows: ,Depend on minus The temperature difference between the material and the hot air is recorded as follows: ,Depend on minus The heat exchange capacity of the evaporation equipment is thus determined. At every moment and Multiplying them together, the heat exchange capacity of the drying equipment is indicated as... At every moment and Multiplying them together, we get... Adjacent timestamps and The numerical difference divided by The change rate of material moisture content is obtained and denoted as . Used to characterize the dehydration intensity per unit time, , , , , and Arranged in a preset order as a fixed-length numerical vector, the fixed length is denoted as . Numerical vectors are denoted as , Used as input for the heat exchange feature sub-network, enabling the heat exchange feature sub-network to receive heat exchange state feature data directly related to steam use and hot air use at each time moment, providing input for the generation of heat exchange feature vectors in the working condition intervention comparison energy consumption model;

[0092] by As input, calculate the equipment load state characteristic data, and Represented by components The minimum allowable value of each component is denoted as The maximum allowable value of each component is denoted as , and Obtained from the equipment nameplate parameters and operating settings, for each moment , and Component-wise linear normalization is performed. Linear normalization involves first subtracting the corresponding minimum allowable value from the component, then dividing the difference by the difference between the maximum and minimum allowable values ​​to obtain the normalized result, ensuring the normalized result falls within the interval. The lower limit of the normalization threshold is denoted as The upper limit of the normalization threshold is denoted as The normalized components are pruned using an interval pruning method. When a certain component is less than Update it to When a certain component is greater than Update it to The cut equipment load component values ​​are obtained, and the cut components are arranged into a fixed-length numerical vector according to a preset order. The fixed length is denoted as . Numerical vectors are denoted as , Used as input for the equipment load characteristic sub-network, enabling the equipment load characteristic sub-network to receive equipment load status characteristic data directly corresponding to the load status of the ball mill, pump, and fan at each moment;

[0093] Will , and Keeping it in sync with the timeline The data are fed into the solution feature subnetwork, heat exchange feature subnetwork, and equipment load feature subnetwork in a consistent order, ensuring that the three types of state feature data dimensions in the four input branches of the input layer of the operating condition intervention control energy consumption model are consistent with those of the input subnetwork. , and Consistently, the aforementioned feature data form solution feature vectors, heat exchange feature vectors, and equipment load feature vectors in the intermediate layer of the operating condition intervention control energy consumption model. These feature vectors, together with the operation code, are spliced ​​together to form operating condition fusion features. This drives the steam energy consumption output channel, hot air energy consumption output channel, and electricity consumption output channel to output the steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment at each moment. This provides calculable feature inputs for the slice baseline energy consumption data and energy consumption deviation data of the subsequent energy consumption responsibility slice.

[0094] The solution state characteristic data, heat exchange state characteristic data, and equipment load state characteristic data are mapped to the operation records in the operation data according to timestamps, and the discrete time index is denoted as... The solution state characteristic data are denoted as The heat transfer state characteristic data are denoted as The equipment load status characteristic data is recorded as The aforementioned feature vectors are all generated in step S2, and the configuration parameters of the evaporation section in the operating data are denoted as... The parameters of the drying section are recorded as follows: The grinding and conveying load parameters are denoted as And read the corresponding section information and equipment information from the operation data, in order to For indexing, , , and , , Combine them to form a working condition sample with operation record markers. Arrange the working condition samples at all times in chronological order to obtain a working condition sample sequence.

[0095] For the working condition sample sequence , and Discretization coding is performed, dividing the evaporation section configuration, such as evaporation efficiency and the number of evaporators in operation, into a finite number of states. Each state is mapped to a one-dimensional or multi-dimensional discrete number. Similarly, drying section parameters, such as drying medium temperature setting and dryer speed setting, are divided into a finite number of states, each mapped to a discrete number. Grinding and conveying load parameters, such as ball mill feed rate range and conveying capacity range, are also divided into a finite number of states, each mapped to a discrete number. These discrete numbers are then numerically processed according to a preset mapping rule, encoding each category of parameters into a fixed-length numerical segment. Finally, the evaporation section configuration code, drying section parameter code, and grinding and conveying load parameter code are concatenated in a fixed order to form a fixed-length numerical vector, denoted as . , For operation coding, It maintains a corresponding relationship with the relevant work section information and equipment information, and is used to distinguish the operation mode of different work sections and different equipment in the work condition intervention comparison energy consumption model;

[0096] In the energy consumption model for intervention under operating conditions, a multi-input branch structure is set up. Solution state characteristic data, heat transfer state characteristic data, equipment load state characteristic data, and operation codes are respectively sent to different sub-networks. The input solution feature subnetwork consists of at least two fully connected neuron layers, each containing no fewer than thirty-two neurons. After performing linear transformation and nonlinear activation, the output solution feature vector is denoted as . ,Will Input the heat transfer feature network, whose structure is consistent with the solution feature network, for Perform a nonlinear transformation to output the heat transfer characteristic vector, denoted as . ,Will Input device load characteristic subnetwork, device load characteristic subnetwork to Perform a layer-by-layer nonlinear mapping to output the equipment load characteristic vector, denoted as . ,Will The input operation mode subnetwork, employing a multi-layer fully connected neuron structure, embeds and nonlinearly maps the discrete operation mode encodings, outputting an operation mode feature vector. This operation mode feature vector is denoted as... ;

[0097] A working condition fusion layer is set in the intermediate layer of the working condition intervention control energy consumption model to... , , and The components are assembled in a preset order to form a working condition fusion feature, which is denoted as [missing information]. ,Will The input consists of at least one fully connected neural layer. It performs comprehensive calculations on features derived from material state, heat exchange state, equipment load, and operating mode, and outputs energy-related features, denoted as [missing information]. ,by Based on the basic characteristics, the subsequent energy consumption increment is calculated in the steam energy consumption output channel, the hot air energy consumption output channel, and the electricity consumption output channel, respectively.

[0098] Energy consumption output channels are constructed separately for the three types of energy consumption. In the steam energy consumption output channel, and , The vector is concatenated to obtain a dedicated input vector for steam energy consumption. This vector is then input into a fully connected neural layer for steam energy consumption. The scalar output is calculated using the weights and biases of this neural layer. The scalar output is denoted as... , This represents the increase in steam energy consumption at a corresponding moment, which will be displayed in the hot air energy consumption output channel. and The input is a fully connected neuron layer with hot air energy consumption, and a scalar output is obtained by splicing the layers together. , This represents the increase in hot air energy consumption at a corresponding moment. In the power consumption output channel, it will be... and The input is concatenated into a fully connected neuron layer with high power consumption, and a scalar output is obtained. , The three output channels use independent weight parameters to represent the power consumption increment at the corresponding time, so that the working condition intervention control energy consumption model can learn the dependence of steam energy consumption increment, hot air energy consumption increment and power consumption increment on different feature vectors respectively.

[0099] A sample set was constructed to train the energy consumption model for intervention control under operating conditions. This set included solution state characteristic data, heat exchange state characteristic data, and equipment load state characteristic data from historical operating data, along with operation codes. The input samples are combined with the measured values ​​of steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment from the historical energy consumption data at the corresponding time point to form the target output, thus creating a sample set. This sample set is denoted as . ,by Each sample is taken as input, and... , , and Input the operating condition intervention control energy consumption model to obtain the predicted steam energy consumption increment. Predicting the increase in hot air energy consumption Compared with the predicted increase in electricity consumption To simultaneously constrain the prediction errors of the three types of energy consumption increments, the loss function is... Defined as:

[0100] ;

[0101] in, The loss function of the energy consumption model under the intervention condition is given. For sample set The number of samples included. For sample index, For the control energy consumption model under working conditions intervention Predicted steam energy consumption increments at all times for Measurement of steam energy consumption increment at any given time. For the control energy consumption model under working conditions intervention Real-time prediction of hot air energy consumption increments for Measurement of hot air energy consumption increment at any given time. For the control energy consumption model under working conditions intervention Predicted power consumption increments at all times for Measurement of the increase in power consumption at any given time. The weighting coefficient for the incremental error term of steam energy consumption. This is the weighting coefficient for the incremental error term of hot air energy consumption. The weighting coefficient for the incremental error term of power consumption. , and All are dimensionless parameters not less than zero, used to weight the error contribution according to the importance of the three energy sources in potash fertilizer production;

[0102] loss function To optimize the objective, a gradient descent-like parameter update algorithm is used to iteratively update the weights and biases in the solution feature subnetwork, heat transfer feature subnetwork, equipment load feature subnetwork, operation mode subnetwork, and the three energy consumption output channels. In each iteration, the algorithm is updated based on the loss function. The gradients of each parameter are used to adjust the parameters until the loss function is reached. Once the values ​​on the validation samples stabilize below the preset convergence threshold, the converged working condition intervention control energy consumption model is obtained.

[0103] Based on the standard potash fertilizer production condition parameters, the solution state characteristic data, heat transfer state characteristic data, and equipment load state characteristic data at each moment in the operating condition sample sequence are adjusted and calculated. The standard potash fertilizer production condition parameters are denoted as follows: , It includes statistical characteristics of standard solution concentration, statistical characteristics of standard material moisture content, and statistical characteristics of standard equipment load. As input, the current time... By comparing the statistical characteristics of the concentration of the current characteristic component with those of the standard solution, the ratio or difference between the current characteristic component and the standard component is calculated, and the analysis is performed accordingly. The relevant components in the standard solution are linearly scaled or translated to obtain the state characteristic data of the standard solution. The state characteristic data of the standard solution is denoted as . Using the same method, By comparing the statistical characteristics of moisture content and the correlation with temperature difference of standard materials, and adjusting the moisture and temperature difference components, standard heat transfer state characteristic data are obtained. These standard heat transfer state characteristic data are denoted as... ,Will By comparing the load statistics with those of standard equipment, and scaling each load component proportionally, standard equipment load state characteristic data is obtained. This standard equipment load state characteristic data is denoted as... ,Will , and according to Permutations and combinations are used to form standard production condition state sequence data, and the standard production condition state sequence data is then matched with the corresponding operation codes. Input the converged operating condition intervention control energy consumption model to obtain the steam energy consumption increment under standard potash fertilizer production conditions. Increase in hot air energy consumption With the increase in power consumption The above three types of increments are combined in chronological order to form standard production condition energy consumption data, so that the standard production condition energy consumption data can simultaneously provide steam energy consumption increment, hot air energy consumption increment and electricity consumption increment at each moment, providing a unified working condition energy consumption baseline for subsequent calculation of slice baseline energy consumption data and energy consumption deviation data based on energy consumption responsibility slices.

[0104] Figure 6 This is a flowchart of the slice baseline energy consumption data calculation provided by an optional embodiment of the present invention, such as... Figure 6 As shown, standard production condition energy consumption data is mapped to operational data according to timestamps, and the discrete time index is denoted as... The increase in steam energy consumption in the standard production condition energy consumption data is recorded as The increase in hot air energy consumption is recorded as The increase in power consumption is recorded as Record the section information in the operation data as Record the device information as Record the operation method information as Using timestamp alignment, , , and , , In each The above correspondence is used to form a standard production condition energy consumption sequence that simultaneously contains three types of energy consumption increments and three types of identification information at each moment, providing a time series basis with physical meaning for dividing energy consumption responsibility slices;

[0105] Using the energy consumption sequence under standard production conditions as input, the detection , and The value change will be recorded as the energy consumption responsibility slice number. , will the The start time index of each energy consumption responsibility slice is denoted as... The end time index is denoted as Starting from the first time index, scan sequentially. When adjacent time points and any of the following , or When the value of changes, The corresponding index is used as the new ,Will The corresponding index serves as the current energy consumption responsibility slice. Therefore, a continuous index interval in which the section information, equipment information and operation mode information remain unchanged throughout the entire time axis is defined as an energy consumption responsibility slice, resulting in multiple energy consumption responsibility slices with unique combinations of section, equipment and operation mode.

[0106] For each energy consumption responsibility slice, extract standard production condition energy consumption data within the corresponding time range, and then... The number of time points included in each energy consumption responsibility slice is denoted as . , equal and Add one to the difference, to arrive All between For indexing, Arranged in chronological order, we get the [number]. The steam energy consumption increment sequence of each energy consumption responsibility slice is processed in the same way. Arranged as a sequence of hot air energy consumption increments, Arranged as an incremental sequence of power consumption, this sequence extraction method, which divides the energy consumption responsibility slices, ensures that the incremental sequence of energy consumption within each energy consumption responsibility slice corresponds to the section information, equipment information, and operation mode information of that energy consumption responsibility slice.

[0107] Using the steam energy consumption increment sequence as input, calculate the steam energy consumption baseline value for each energy consumption responsibility slice, and denot the collection period as... , To standardize the sampling interval for energy consumption data and operational data under standard production conditions, the first... A slice of energy consumption responsibility, from arrive Read by index Accumulate the results in chronological order and record the result as follows: ,because Indicates the collection period The increase in steam energy consumption within a given time period can be summed up item by item according to the time index to obtain the baseline value of steam energy consumption for that energy consumption responsibility slice under standard potash fertilizer production conditions. The baseline value corresponds to the start and end times of the energy consumption responsibility slice, as well as the section information and equipment information;

[0108] Using the incremental sequence of hot air energy consumption as input, calculate the baseline value of hot air energy consumption for each energy consumption responsibility slice. A slice of energy consumption responsibility, from arrive Read by index Accumulate the results in chronological order and record the result as follows: Similarly, Indicates the collection period The increase in internal hot air energy consumption is calculated by adding it hourly within the energy consumption responsibility slice. Accurately reflect the baseline value of hot air energy consumption caused by the combination of corresponding work sections, equipment and operating methods under standard potash fertilizer production conditions and parameters for this energy consumption responsibility slice;

[0109] Using the incremental power consumption sequence as input, calculate the baseline power consumption value for each energy consumption responsibility slice. A slice of energy consumption responsibility, from arrive Read by index Accumulate the results in chronological order and record the result as follows: ,because Corresponding collection period The incremental electricity consumption within a given time period can be summed up according to the time index to obtain the baseline electricity consumption value of that energy consumption responsibility slice under standard potash fertilizer production conditions. To describe the three energy consumption baseline values ​​within the same framework, the first... The energy consumption vector of the slice baseline of each energy consumption responsibility slice is denoted as... And use the following formula for unified calculation:

[0110] ;

[0111] in, For the first The slice baseline energy consumption vector of each energy consumption responsibility slice For the first The baseline value of steam energy consumption for each energy consumption responsibility slice. For the first Baseline value of hot air energy consumption for each energy consumption responsibility segment For the first The baseline value of electricity consumption for each energy consumption responsibility slice. Assign energy consumption responsibility slice numbering, For the first The start time index of each energy consumption responsibility slice. For the first The termination time index of each energy consumption responsibility slice. Under standard potash fertilizer production conditions, The increase in steam energy consumption at any given moment Under standard potash fertilizer production conditions, The increase in hot air energy consumption at any time Under standard potash fertilizer production conditions, The power consumption increment at any given time, and all three types of power consumption increments mentioned above occur within a single data collection cycle. The energy consumption within is all in energy units, so that the summation of the vectors on the right side is consistent with the three energy consumption baseline values ​​on the left side in terms of dimension.

[0112] Using the unified vector form described above, it is possible to... Based on this, the baseline values ​​of steam energy consumption, hot air energy consumption, and electricity consumption are managed uniformly at the slice level and are consistent with the multi-channel output structure of the working condition intervention comparison energy consumption model, providing structured numerical input for subsequent energy consumption responsibility evaluation at the section level, equipment level, and operation mode level.

[0113] The three energy consumption baseline values ​​corresponding to each energy consumption responsibility segment are bound to the section information, equipment information, and operation mode information of that energy consumption responsibility segment. Each energy consumption responsibility slice will , and With this energy consumption responsibility slice in , and The unique combination of values ​​corresponds to the above information, which is organized into slice baseline energy consumption records according to a preset field order. The record set constitutes slice baseline energy consumption data, which is then processed at the work section level. Indexed to specific work sections, at the equipment level via Indexed to specific devices, at the operation mode level via The index leads to specific operational methods, and within each energy consumption responsibility slice, it compares the energy consumption model output with the operational condition intervention. , and Maintaining the correspondence provides fine-grained baseline energy consumption support for subsequent calculation of energy consumption deviation data based on actual energy consumption data and for conducting energy consumption responsibility assessments.

[0114] The energy consumption data is mapped to the start and end times of the energy consumption responsibility slices, and the discrete time index is denoted as... The steam energy consumption measurement value in the energy consumption data is recorded as The measured value of hot air energy consumption is recorded as Record the measured power consumption value as According to the start time index of the aforementioned energy consumption responsibility slice and termination time index Constrained by the time range of each energy consumption responsibility slice, for Filtering will satisfy of , and Arranged chronologically, the actual energy consumption sequence of the energy consumption responsibility slice is formed, and the first slice is... Energy consumption responsibility slice in The combination of the three energy consumption measurements at time is denoted as , Depend on , and The composition is used to accumulate the three energy sources separately in subsequent steps;

[0115] Using the actual energy consumption sequence of the slice as input, the measured values ​​of steam energy consumption, hot air energy consumption, and electricity consumption within the same energy consumption responsibility slice time range are accumulated respectively. A slice of energy consumption responsibility, from arrive Read by index Add the items one by one in chronological order, and record the result as follows: , This indicates the total actual energy consumption of steam within the energy consumption responsibility slice. Similarly, for... Add the items together and record the total actual energy consumption of the hot air as follows: ,right Add each item together and record the total actual energy consumption as follows: By using this accumulation method with the energy consumption responsibility slice time range as the boundary, it enables... , and Each energy consumption responsibility slice is kept consistent with its physical boundary.

[0116] Based on the slice baseline energy consumption data, the actual energy consumption of each energy consumption responsibility slice is compared and calculated with the baseline energy consumption. The steam energy consumption baseline value in the slice baseline energy consumption data is recorded as follows: The baseline value of hot air energy consumption is recorded as Record the baseline power consumption value as The above three types of baseline values ​​are obtained by accumulating standard production condition energy consumption data within the corresponding energy consumption responsibility slice time range. Each energy consumption responsibility segment will determine the actual energy consumption of steam. Subtract the baseline value of steam energy consumption The steam energy consumption deviation is obtained and denoted as . The actual energy consumption of hot air Subtract the baseline value of hot air energy consumption The hot air energy consumption deviation is obtained and denoted as . The actual energy consumption of electricity Subtract the baseline power consumption value The power consumption deviation is obtained and denoted as . The above three types of energy consumption deviations are all expressed in terms of energy consumption, and directly reflect the energy consumption deviation of the energy consumption responsibility slice under the standard potash fertilizer production conditions.

[0117] The steam energy consumption deviation, hot air energy consumption deviation, and electricity consumption deviation corresponding to each energy consumption responsibility segment are combined with the section information, equipment information, and operation mode information of that energy consumption responsibility segment to form energy consumption deviation data. Each energy consumption responsibility slice will be recorded as the section information determined during the slice division phase. Record the device information as Record the operation method information as ,Will , , and , , Binding is performed according to a preset field order to form a single energy consumption deviation information record. The energy consumption deviation information records of all energy consumption responsibility slices are organized in chronological order or by work section / equipment index order to form an energy consumption deviation data set. This energy consumption deviation data set is then processed at the work section level... Aggregation, at the device level In subsequent steps, when aggregating at the team level by combining team operation and scheduling information, the time range of the energy consumption responsibility slice is used as the basis for determining team affiliation. This enables energy consumption responsibility evaluation by work section, equipment, and work team, allowing energy consumption responsibility to be traced back to the work section, equipment, and operation mode combination corresponding to the specific energy consumption responsibility slice.

[0118] In this embodiment, step S6 specifically includes:

[0119] Using energy consumption deviation data as input, the section information and equipment information corresponding to each energy consumption responsibility slice are extracted, and the energy consumption responsibility slice number is recorded as follows. , will the The work section information corresponding to each energy consumption responsibility slice is denoted as follows: Record the device information as The steam energy consumption deviation is denoted as The hot air energy consumption deviation is recorded as The power consumption deviation is recorded as Firstly, according to All energy consumption responsibility slices are grouped into work sections. Energy consumption responsibility slices with the same work section information are grouped into the same work section group. Within each work section group, further adjustments are made based on... Equipment is grouped, and energy consumption responsibility slices with the same equipment information are assigned to the same equipment group. Through the above two-level grouping, the energy consumption deviation data is organized into a set of energy consumption deviation groups divided by work section and equipment. In this set, each group corresponds to a unique combination of work section information and equipment information.

[0120] Using the energy consumption deviation group set as input, the steam energy consumption deviation, hot air energy consumption deviation, and electricity consumption deviation are accumulated within each work section and equipment group, and the work section and equipment group index is denoted as... ,in For section group identification, Assign device group identifiers, in Within the group, collect all that meet the requirements. and Energy consumption responsibility slice number For the corresponding By adding up each item, the total steam energy consumption deviation for this section and equipment combination is obtained. This total steam energy consumption deviation is denoted as... Using the same method, for Add them together to get the total value of hot air energy consumption deviation. Record the total value of hot air energy consumption deviation as follows: ,right Add them together to get the total power consumption deviation value, and record the total power consumption deviation value as . By performing the above-mentioned cumulative operation within each work section and equipment group, , and These represent the total deviations in steam, hot air, and electricity consumption for the work section and equipment within the entire energy consumption responsibility slice.

[0121] Based on the time range and work group of the energy consumption responsibility segments, the energy consumption responsibility segments are divided according to work groups, and the work group scheduling information recorded in the production management system is recorded as follows: , At each timestamp The corresponding work group identifier is given above, and the first one will be... The start time index of each energy consumption responsibility slice is denoted as... The end time index is denoted as ,by to The covered time range is the time range of this energy consumption responsibility slice. When dividing into work groups, the work group corresponding to the start time of the energy consumption responsibility slice can be selected. As the team identifier for this energy consumption responsibility segment, the team identifier is recorded as follows: This enables the mapping of energy consumption responsibility segments to work teams, thereby achieving the following: Using the work group as the key, all energy consumption responsibility segments are categorized according to work group identifiers, resulting in a set of energy consumption responsibility segments divided by work group. Then, using... , and Based on this, and according to the energy consumption responsibility slice set and work group identifier contained within each work section and equipment group, The correspondence between them is used to aggregate the energy consumption deviation values ​​at the work group level, and the work group identifier is recorded as follows. For all those in the work group The following appears Grouping corresponding The values ​​are accumulated to obtain the steam energy consumption deviation value for each shift. This steam energy consumption deviation value for each shift is recorded as follows: Using the same method, for The values ​​are accumulated to obtain the hot air energy consumption deviation value for each work group. This hot air energy consumption deviation value for each work group is recorded as follows: ,right The values ​​are accumulated to obtain the electricity consumption deviation value for each work group. This value is then recorded as follows: Through the above aggregation, the deviations in steam, hot air, and electricity consumption at the team level can be correlated with the specific operational behavior of the team.

[0122] The summarized values ​​of steam energy consumption deviation, hot air energy consumption deviation, and electricity consumption deviation, categorized by work section and equipment, are combined with the team-specific values ​​of steam energy consumption deviation, hot air energy consumption deviation, and electricity consumption deviation. This combination is then applied to each work section and equipment. Construct corresponding energy consumption responsibility assessment records, and and As the section field and equipment field in the record, , , As a field recording the energy consumption deviation at the equipment level for the work section, and based on the set of work teams involved in the work section and equipment combination, the work team identifier is also included. and , , As a field for energy consumption deviation at the work group level, it is added to the same evaluation result. All records are arranged according to the preset sorting of work section, equipment and work group to form a complete energy consumption responsibility evaluation result. The energy consumption responsibility evaluation result uses work section as the first index, equipment as the second index and work group as the third index to quantitatively express the distribution of steam energy consumption deviation, hot air energy consumption deviation and electricity consumption deviation at the work section level, equipment level and work group level. It is used for energy consumption responsibility evaluation and management of potash fertilizer high energy consumption equipment.

[0123] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0124] Through the above description of the embodiments, those skilled in the art can clearly understand that the device energy consumption detection method according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0125] According to embodiments of the present invention, an equipment energy consumption detection device for implementing the above-described equipment energy consumption detection method is also provided. Figure 7 This is a structural block diagram of the equipment energy consumption detection device provided according to an embodiment of the present invention, such as... Figure 7 As shown, the energy consumption detection device includes: an acquisition module 702, a construction module 704, an input module 706, a division module 708, a first determination module 710, a calculation module 712, and a second determination module 714. The energy consumption detection device will be described below.

[0126] The acquisition module 702 is used to acquire the operating data and energy consumption data of the target device during the target runtime.

[0127] The construction module 704, connected to the acquisition module 702, is used to determine the target operating condition intervention control energy consumption model based on the operating data. The target operating condition intervention control energy consumption model represents the impact model of operating conditions on the standard energy consumption data of the target equipment.

[0128] The input module 706, connected to the construction module 704, is used to input preset standard production condition parameters into the target working condition intervention control energy consumption model to obtain standard energy consumption data.

[0129] The partitioning module 708, connected to the input module 706, is used to divide the target runtime into multiple energy consumption responsibility slices based on the runtime data. The energy consumption responsibility slice represents a time segment in which the runtime data of the target device remains unchanged.

[0130] The first determination module 710, connected to the division module 708, is used to determine the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on standard energy consumption data.

[0131] The calculation module 712, connected to the first determination module 710, is used to calculate the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices based on the energy consumption data and the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices.

[0132] The second determining module 714, connected to the calculation module 712, is used to obtain the energy consumption detection result of the target device based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices.

[0133] It should be noted that the aforementioned acquisition module 702, construction module 704, input module 706, partitioning module 708, first determination module 710, calculation module 712, and second determination module 714 correspond to steps S202 to S214 in the embodiments. Multiple modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should also be noted that the aforementioned modules, as part of the device, can run on the computer terminal 10 provided in the embodiments.

[0134] Embodiments of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0135] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the device energy consumption detection method and apparatus in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned device energy consumption detection method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0136] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: acquiring the target device's operating data and energy consumption data during the target operating period; determining a target operating condition intervention control energy consumption model based on the operating data, wherein the target operating condition intervention control energy consumption model characterizes the influence model of operating conditions on the target device's standard energy consumption data; inputting preset standard production condition parameters into the target operating condition intervention control energy consumption model to obtain standard energy consumption data; dividing the target operating period into multiple energy consumption responsibility slices based on the operating data, wherein the energy consumption responsibility slice characterizes a time segment in which the target device's operating data remains unchanged; determining the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on the standard energy consumption data; calculating the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices based on the energy consumption data and the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices; and obtaining the energy consumption detection result of the target device based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices.

[0137] Optionally, the processor may also execute program code for the following steps: determining a target operating condition intervention control energy consumption model based on operating data, including: calculating and generating feature data based on process solution concentration data, material moisture data, and equipment load data in the operating data, wherein the feature data includes: solution state feature data, heat exchange state feature data, and equipment load state feature data; discretizing and encoding the process parameters in the operating data to obtain operation codes; generating an operating condition sample sequence based on the operation codes and feature data; and training a preset initial operating condition intervention control energy consumption model using the operating condition sample sequence to obtain a target operating condition intervention control energy consumption model.

[0138] Optionally, the processor may also execute program code for the following steps: inputting preset standard production condition parameters into the target operating condition intervention control energy consumption model to obtain standard energy consumption data, including: acquiring historical operating data of the target equipment; selecting time segments from the historical operating data that meet preset stability thresholds and output thresholds as candidate standard production segments; calculating the statistical characteristics of solution concentration, material moisture, and equipment load based on the candidate standard production segments to obtain a set of candidate standard production condition parameters; filtering from the set of candidate standard production condition parameters based on preset energy consumption level thresholds to determine standard production condition parameters; adjusting the operating condition sample sequence using the standard production condition parameters to obtain a standard production condition operating condition sample sequence; and inputting the standard production condition operating condition sample sequence into the target operating condition intervention control energy consumption model to obtain standard energy consumption data.

[0139] Optionally, the processor may also execute program code for the following steps: determining baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on standard energy consumption data, including: determining standard energy consumption data between the start and end times of each of the multiple energy consumption responsibility slices based on standard energy consumption data; determining steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment corresponding to each of the multiple energy consumption responsibility slices based on the standard energy consumption data between the start and end times of each of the multiple energy consumption responsibility slices; adding the energy consumption increments hourly in chronological order based on the steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment corresponding to each of the multiple energy consumption responsibility slices to obtain the steam energy consumption baseline value, hot air energy consumption baseline value, and electricity consumption baseline value corresponding to each of the multiple energy consumption responsibility slices; and determining the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on the steam energy consumption baseline value, hot air energy consumption baseline value, and electricity consumption baseline value corresponding to each of the multiple energy consumption responsibility slices.

[0140] Optionally, the processor may also execute program code for the following steps: obtaining the energy consumption detection result of the target device based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices, including: dividing the multiple energy consumption responsibility slices into multiple slice sets based on the section information in the operating data; determining the sum of energy consumption deviations corresponding to each of the multiple slice sets based on the energy consumption deviations corresponding to each of the multiple energy consumption responsibility slices; and determining the energy consumption detection result based on the sum of energy consumption deviations corresponding to each of the multiple slice sets.

[0141] Optionally, the processor may also execute program code for the following steps: when multiple devices and the target device are both of the target device type, the processor may further include: obtaining the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices corresponding to the multiple devices; determining the average energy consumption deviation based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices corresponding to the multiple devices; and determining the energy consumption evaluation result corresponding to the target device type based on the average energy consumption deviation.

[0142] This invention provides a method for detecting equipment energy consumption. The method involves acquiring operational data and energy consumption data of a target device during a target operating period. Based on the operational data, a target operating condition intervention control energy consumption model is determined, whereby the target operating condition intervention control energy consumption model characterizes the influence of operating conditions on the standard energy consumption data of the target device. Preset standard production condition parameters are input into the target operating condition intervention control energy consumption model to obtain standard energy consumption data. Based on the operational data, the target operating period is divided into multiple energy consumption responsibility slices, whereby an energy consumption responsibility slice characterizes a time segment in which the operational data of the target device remains unchanged. Based on the standard energy consumption data, multiple... The baseline energy consumption data corresponding to each energy consumption responsibility segment is used; based on the energy consumption data and the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility segments, the energy consumption deviation corresponding to each of the multiple energy consumption responsibility segments is calculated; based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility segments, the energy consumption detection result of the target equipment is obtained, which achieves the purpose of converting energy consumption to standard production conditions, thereby realizing the technical effect of improving the accuracy of energy consumption detection results. This solves the technical problem that the current assessment of energy consumption of potash fertilizer production equipment usually involves directly comparing energy consumption or unit energy consumption under actual operating conditions, lacking a systematic method to uniformly convert energy consumption to standard production conditions, which leads to inaccurate energy consumption detection results.

[0143] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a non-volatile storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0144] Embodiments of the present invention also provide a non-volatile storage medium. Optionally, in this embodiment, the non-volatile storage medium can be used to store the program code executed by the device power consumption detection method provided in the above embodiments.

[0145] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0146] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: acquiring operating data and energy consumption data of the target device during the target operating period; determining a target operating condition intervention control energy consumption model based on the operating data, wherein the target operating condition intervention control energy consumption model characterizes the influence model of operating conditions on the standard energy consumption data of the target device; inputting preset standard production condition parameters into the target operating condition intervention control energy consumption model to obtain standard energy consumption data; dividing the target operating period into multiple energy consumption responsibility slices based on the operating data, wherein the energy consumption responsibility slice characterizes a time segment in which the operating data of the target device remains unchanged; determining the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on the standard energy consumption data; calculating the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices based on the energy consumption data and the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices; and obtaining the energy consumption detection result of the target device based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices.

[0147] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining a target operating condition intervention control energy consumption model based on operating data, including: calculating and generating feature data based on process solution concentration data, material moisture data, and equipment load data in the operating data, wherein the feature data includes: solution state feature data, heat exchange state feature data, and equipment load state feature data; discretizing and encoding the process parameters in the operating data to obtain operation codes; generating an operating condition sample sequence based on the operation codes and feature data; and training a preset initial operating condition intervention control energy consumption model using the operating condition sample sequence to obtain a target operating condition intervention control energy consumption model.

[0148] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: inputting preset standard production condition parameters into the target operating condition intervention control energy consumption model to obtain standard energy consumption data, including: acquiring historical operating data of the target equipment; selecting time segments from the historical operating data that meet preset stability thresholds and production thresholds as candidate standard production segments; calculating the statistical characteristics of solution concentration, material moisture, and equipment load based on the candidate standard production segments to obtain a set of candidate standard production condition parameters; filtering from the set of candidate standard production condition parameters based on preset energy consumption level thresholds to determine standard production condition parameters; adjusting the operating condition sample sequence using the standard production condition parameters to obtain a standard production condition operating condition sample sequence; and inputting the standard production condition operating condition sample sequence into the target operating condition intervention control energy consumption model to obtain standard energy consumption data.

[0149] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on standard energy consumption data, including: determining standard energy consumption data between the start and end times of each of the multiple energy consumption responsibility slices based on standard energy consumption data; determining steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment corresponding to each of the multiple energy consumption responsibility slices based on the standard energy consumption data between the start and end times of each of the multiple energy consumption responsibility slices; adding the energy consumption increments hourly in chronological order based on the steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment corresponding to each of the multiple energy consumption responsibility slices to obtain the steam energy consumption baseline value, hot air energy consumption baseline value, and electricity consumption baseline value corresponding to each of the multiple energy consumption responsibility slices; and determining the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on the steam energy consumption baseline value, hot air energy consumption baseline value, and electricity consumption baseline value corresponding to each of the multiple energy consumption responsibility slices.

[0150] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: obtaining the energy consumption detection result of the target device based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices, including: dividing the multiple energy consumption responsibility slices into multiple slice sets based on the section information in the operating data; determining the sum of energy consumption deviations corresponding to each of the multiple slice sets based on the energy consumption deviations corresponding to each of the multiple energy consumption responsibility slices; and determining the energy consumption detection result based on the sum of energy consumption deviations corresponding to each of the multiple slice sets.

[0151] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: when there are multiple devices and the target device that are both of the target device type, the method further includes: obtaining the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices corresponding to the multiple devices; determining the average energy consumption deviation based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices corresponding to the multiple devices; and determining the energy consumption evaluation result corresponding to the target device type based on the average energy consumption deviation.

[0152] Embodiments of the present invention also provide a computer program product, including a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, it can: acquire operating data and energy consumption data of a target device during a target operating period; determine a target operating condition intervention control energy consumption model based on the operating data, wherein the target operating condition intervention control energy consumption model characterizes the influence model of operating conditions on the standard energy consumption data of the target device; input preset standard production condition parameters into the target operating condition intervention control energy consumption model to obtain standard energy consumption data; divide the target operating period into multiple energy consumption responsibility slices based on the operating data, wherein the energy consumption responsibility slice characterizes a time segment in which the operating data of the target device remains unchanged; determine the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on the standard energy consumption data; calculate the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices based on the energy consumption data and the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices; and obtain the energy consumption detection result of the target device based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices.

[0153] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0154] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0155] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0156] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0157] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0158] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0159] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for detecting equipment energy consumption, characterized in that, include: Acquire the target device's operating data and energy consumption data during the target runtime period; Based on the operational data, a target operating condition intervention control energy consumption model is determined, wherein the target operating condition intervention control energy consumption model is a model characterizing the impact of operating conditions on the standard energy consumption data of the target equipment; The preset standard production condition parameters are input into the target working condition intervention control energy consumption model to obtain standard energy consumption data; Based on the operational data, the target runtime is divided into multiple energy consumption responsibility slices, wherein the energy consumption responsibility slice represents a time segment in which the operational data of the target device remains unchanged; Based on the standard energy consumption data, the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices is determined; Based on the energy consumption data and the baseline energy consumption data corresponding to each of the plurality of energy consumption responsibility slices, calculate the energy consumption deviation corresponding to each of the plurality of energy consumption responsibility slices; Based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices, the energy consumption detection result of the target device is obtained.

2. The method according to claim 1, characterized in that, The step of determining the target operating condition intervention control energy consumption model based on the operational data includes: Based on the process solution concentration data, material moisture data, and equipment load data in the operating data, characteristic data is generated, which includes: solution state characteristic data, heat exchange state characteristic data, and equipment load state characteristic data. Discrete encoding is performed on the section parameters in the operation data to obtain the operation code; Based on the operation code and the feature data, a working condition sample sequence is generated; The preset initial working condition intervention control energy consumption model is trained using the working condition sample sequence to obtain the target working condition intervention control energy consumption model.

3. The method according to claim 2, characterized in that, The step of inputting preset standard production condition parameters into the target working condition intervention control energy consumption model to obtain standard energy consumption data includes: Obtain the historical operating data of the target device; Select time segments that meet the preset stability threshold and output threshold from the historical operation data as candidate standard production segments; Based on the candidate standard production segments, the statistical characteristics of solution concentration, material moisture content, and equipment load are calculated to obtain a set of candidate standard production condition parameters. Based on a preset energy consumption level threshold, the standard production condition parameters are determined by filtering from the set of candidate standard production condition parameters. The standard production condition sample sequence is obtained by adjusting the standard production condition parameters. The standard production condition sample sequence is input into the target condition intervention control energy consumption model to obtain the standard energy consumption data.

4. The method according to claim 1, characterized in that, The step of determining the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on the standard energy consumption data includes: Based on the standard energy consumption data, determine the standard energy consumption data between the start and end times of each of the multiple energy consumption responsibility slices; Based on the standard energy consumption data between the start and end times of the multiple energy consumption responsibility slices, the steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment of each of the multiple energy consumption responsibility slices are determined. Based on the steam energy consumption increment, hot air energy consumption increment, and electricity consumption increment corresponding to each of the multiple energy consumption responsibility slices, the energy consumption increments are added hourly in time order to obtain the steam energy consumption baseline value, hot air energy consumption baseline value, and electricity consumption baseline value corresponding to each of the multiple energy consumption responsibility slices. Based on the baseline values ​​of steam energy consumption, hot air energy consumption, and electricity consumption corresponding to each of the multiple energy consumption responsibility slices, the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices is determined.

5. The method according to claim 1, characterized in that, The energy consumption detection result of the target device is obtained based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices, including: Based on the section information in the operational data, the multiple energy consumption responsibility slices are divided into multiple slice sets; Based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices, determine the summation value of the energy consumption deviation corresponding to each of the multiple slice sets; The energy consumption detection result is determined based on the summation of energy consumption deviation values ​​corresponding to each of the multiple slice sets.

6. The method according to any one of claims 1 to 5, characterized in that, In cases where multiple devices are of the same type as the target device, the following is also included: Obtain the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices for each of the multiple devices; Based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices of the multiple devices, the average energy consumption deviation is determined; Based on the average energy consumption deviation, the energy consumption evaluation result corresponding to the target equipment type is determined.

7. A device for detecting equipment energy consumption, characterized in that, include: The acquisition module is used to acquire the operating data and energy consumption data of the target device during the target runtime period; A construction module is used to determine a target operating condition intervention control energy consumption model based on the operating data, wherein the target operating condition intervention control energy consumption model characterizes the impact model of operating conditions on the standard energy consumption data of the target equipment; The input module is used to input preset standard production condition parameters into the target working condition intervention control energy consumption model to obtain standard energy consumption data; The partitioning module is used to divide the target runtime into multiple energy consumption responsibility slices based on the runtime data, wherein the energy consumption responsibility slice represents a time segment in which the runtime data of the target device remains unchanged; The first determining module is used to determine the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices based on the standard energy consumption data; The calculation module is used to calculate the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices based on the energy consumption data and the baseline energy consumption data corresponding to each of the multiple energy consumption responsibility slices. The second determining module is used to obtain the energy consumption detection result of the target device based on the energy consumption deviation corresponding to each of the multiple energy consumption responsibility slices.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the non-volatile storage medium to perform the device power consumption detection method according to any one of claims 1 to 6.

9. A computer device, characterized in that, include: Memory and processor The memory stores computer programs; The processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, the processor performs the device energy consumption detection method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the device energy consumption detection method according to any one of claims 1 to 6.

Images