Energy usage management method, system, equipment and medium based on industrial Internet of Things

Abstract

The present invention discloses an energy usage management method, system, device, and medium based on the industrial Internet of Things, which relates to the field of industrial Internet of Things data processing technology. The method comprises obtaining a to-be-managed area and to-be-managed equipment, obtaining a dynamic time window, obtaining historical status information, and obtaining energy supply information; obtaining a pre-processing energy supply time period, obtaining a processing time period threshold, and obtaining a to-be-processed energy supply time period if a pre-processing energy supply time period exceeds the processing time period threshold; obtaining load information and surface temperature information, obtaining a load variation coefficient within the to-be-processed energy supply time period based on a first indicator model and load information, obtaining a temperature variation coefficient within the to-be-processed energy supply time period based on a second indicator model and surface temperature information, and obtaining an equipment energy usage index; obtaining a regional energy usage index based on the equipment energy usage index, and obtaining an energy usage management strategy. The present invention has the advantages of dynamic monitoring, energy efficiency coupled diagnosis, and hierarchical collaborative management.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet of Things data processing, and in particular to an energy usage management method, system, device and medium based on the industrial Internet of Things. Background Art

[0002] In the field of industrial manufacturing, the optimization of energy use management has always been one of the core issues of industry development. With the widespread application of industrial Internet of Things technology, the real-time collection and analysis of device-level energy data has become the basis for achieving refined energy management.

[0003] However, existing technologies still face multiple technical bottlenecks in practical applications: the existing energy management uses a fixed time window for historical data analysis, which cannot adapt to the dynamically changing equipment conditions. For example, in typical industrial equipment groups such as injection molding machines and air compressors, the equipment often generates intermittent high-load operation due to production task adjustments. If a static time window with a preset fixed duration (such as 24 hours) is used, it will lead to delays in monitoring sudden energy consumption fluctuations, making it difficult to capture abnormal energy consumption events in a timely manner; more seriously, abnormal energy consumption caused by equipment failures is often hidden and gradual, and existing methods generally rely on a single energy consumption threshold alarm mechanism. When it is detected that the energy consumption exceeds the standard, the equipment has often entered a serious fault state, which not only causes a large amount of energy waste, but is also likely to cause chain equipment damage. In addition, the existing energy efficiency evaluation models are mostly based on simplified indicators such as total energy consumption or average load rate, and lack the coupling analysis of dynamic load fluctuations and thermodynamic characteristics. More importantly, the formulation of existing energy management strategies generally lacks a collaborative optimization mechanism for equipment groups, and often adopts a "one-size-fits-all" control method. For example, when a local energy consumption anomaly occurs in a certain area, the traditional solution may directly cut off the energy supply to the entire area, causing normal equipment to be forced to shut down, seriously affecting production continuity.

[0004] Therefore, it is urgent to develop an industrial energy management method that can achieve dynamic time window optimization, multi-dimensional energy efficiency feature extraction and intelligent strategy generation to break through the current technical bottleneck. Summary of the Invention

[0005] In response to the deficiencies in the prior art, the present invention provides an energy usage management method, system, device and medium based on the Industrial Internet of Things.

[0006] An energy use management method based on the industrial Internet of Things includes: obtaining a to-be-managed area and multiple to-be-managed devices of the same device type within the to-be-managed area according to the industrial Internet of Things, obtaining a dynamic time window with the current moment as the end, obtaining historical status information of each to-be-managed device within the dynamic time window, and obtaining energy supply information according to the historical status information; obtaining multiple continuous time periods corresponding to energy supply information exceeding a preset energy supply rate according to the energy supply information and using them as multiple pre-processing energy supply time periods, and obtaining a processing time period threshold according to the dynamic time window. If there is a pre-processing energy supply time period exceeding the processing time period threshold, obtaining the longest pre-processing energy supply time segment and use it as the energy supply time period to be processed; obtain the load information and surface temperature information within the energy supply time period to be processed based on the historical status information, and obtain the load change coefficient within the energy supply time period to be processed based on the first indicator model and the load information, and obtain the temperature change coefficient within the energy supply time period to be processed based on the second indicator model and the surface temperature information, and obtain the equipment energy usage index of each equipment to be managed according to the preset energy supply rate, load change coefficient and temperature change coefficient; obtain the regional energy usage index of the area to be managed according to multiple equipment energy usage indicators that are less than the preset usage threshold, and obtain the energy usage management strategy according to the regional energy usage index and the equipment energy usage index.

[0007] Optionally, obtaining a dynamic time window whose end is the current moment includes: obtaining a device type of the device to be managed, and obtaining a working condition change rate based on the device type; and obtaining a dynamic time window whose end is the current moment based on the working condition change rate.

[0008] Optionally, a dynamic time window with the end at the current moment is obtained based on the operating condition change rate as follows: ;in, is the length of the dynamic time window, is the length of the basic time window, is the rate of change of operating conditions, The standard ratio.

[0009] Optionally, the first indicator model in the load variation coefficient in the energy supply time period to be processed obtained based on the first indicator model and the load information is expressed as: ;in, is the load variation coefficient of the jth device to be managed during the energy supply period to be processed, is the number of loads obtained by the jth device to be managed during the energy supply period to be processed, is the i-th load of the j-th device to be managed in the energy supply time period to be processed, It is the standard load under the preset energy supply rate.

[0010] Optionally, the second indicator model in the temperature variation coefficient in the energy supply time period to be processed obtained based on the second indicator model and the surface temperature information is expressed as: ;in, is the temperature variation coefficient of the jth device to be managed during the power supply period to be processed, is the number of surface temperatures obtained by the jth device to be managed during the energy supply period to be processed, is the i+1th surface temperature of the jth device to be managed during the energy supply period to be processed, is the i-th surface temperature of the j-th device to be managed during the energy supply period to be processed, To obtain time point, To obtain time point.

[0011] Optionally, the device energy usage index of each device to be managed is obtained based on the preset energy supply rate, load variation coefficient, and temperature variation coefficient as follows: ;in, is the device energy usage index of the jth device to be managed, is the load variation coefficient of the jth device to be managed during the energy supply period to be processed, is the temperature variation coefficient of the jth device to be managed during the power supply period to be processed, The preset energy supply rate.

[0012] Optionally, obtaining an energy usage management strategy based on regional energy usage indicators and device energy usage indicators includes: obtaining a regional policy threshold; if the regional energy usage indicator is less than the regional policy threshold, all multiple managed devices in the management area are shut down and repaired; if the regional energy usage indicator is not less than the regional policy threshold, setting multiple different device policy threshold intervals, wherein each device policy threshold interval corresponds to an energy usage management strategy; matching the device energy usage indicator of each device to be managed with the corresponding device policy threshold interval, thereby obtaining the energy usage management strategy corresponding to each device to be managed.

[0013] An energy use management system based on the industrial Internet of Things is also provided. The system includes a management platform, a sensor network platform and an object platform that are communicatively connected in sequence. The management platform includes: an acquisition module for acquiring an area to be managed and multiple devices to be managed of the same device type in the area to be managed according to the industrial Internet of Things, and acquiring a dynamic time window with the current moment as the end, and acquiring historical status information of each device to be managed within the dynamic time window, and acquiring energy supply information based on the historical status information; a first data processing module for acquiring multiple continuous time periods corresponding to energy supply information exceeding a preset energy supply rate according to the energy supply information and using them as multiple pre-processing energy supply time periods, and acquiring a processing time period threshold according to the dynamic time window. If there is a pre-processing supply information exceeding the processing time period threshold, energy time period, the longest pre-processing energy supply time period is obtained and used as the energy supply time period to be processed; a second data processing module is used to obtain the load information and surface temperature information in the energy supply time period to be processed according to the historical status information, and obtain the load change coefficient in the energy supply time period to be processed based on the first indicator model and the load information, and obtain the temperature change coefficient in the energy supply time period to be processed based on the second indicator model and the surface temperature information, and obtain the device energy usage index of each device to be managed according to the preset energy supply rate, load change coefficient and temperature change coefficient; an energy management module is used to obtain the regional energy usage index of the area to be managed according to multiple device energy usage indicators that are less than a preset usage threshold, and obtain the energy usage management strategy according to the regional energy usage index and the device energy usage index.

[0014] An electronic device is also provided, comprising: a memory on which a computer program is stored; and a processor for executing the computer program in the memory to implement the above-mentioned energy usage management method based on the industrial Internet of Things.

[0015] A non-transitory computer-readable storage medium is also provided, on which a computer program is stored. When the program is executed by a processor, the energy usage management method based on the industrial Internet of Things is implemented.

[0016] The beneficial effects of the present invention are embodied in:

[0017] In the entire energy use management method based on the Industrial Internet of Things, first of all, the dynamic time window is adaptively adjusted based on the equipment type and the rate of change of the working condition, which effectively solves the lag problem of the traditional fixed time window in monitoring intermittent high-load working conditions. For example, the injection molding machine automatically shortens the window length when frequently adjusting the production parameters, and captures the instantaneous energy consumption anomalies caused by the clamping pressure fluctuation in real time, avoiding the omission of abnormal events caused by the long window; further, by screening the continuous time period that continuously exceeds the preset energy supply rate and setting the processing time period threshold, it can accurately distinguish between normal production fluctuations and progressive equipment failures. For example, the continuous load drop and temperature rise acceleration during the high energy supply period caused by the wear of the centrifugal pump bearing can be identified and eliminated in the early stage of short-term working condition interference, providing a high-quality data basis for subsequent analysis; further, through the coupled analysis of the load change coefficient and the temperature change coefficient, a single The limitations of energy consumption indicators, among which the load variation coefficient quantifies the effective working capacity of the equipment and can locate mechanical efficiency problems such as hydraulic leakage and transmission mechanism wear. The temperature variation coefficient reveals thermodynamic anomalies such as insulation aging and cooling failure through temperature rise rate monitoring. For example, the abnormal rise in air compressor exhaust temperature can provide early warning of cooling failure; finally, the equipment energy usage index realizes the quantitative assessment of the energy efficiency health status. The combined application of regional energy usage indicators and hierarchical strategy mechanism solves the drawbacks of "one-size-fits-all" management and control. When the regional indicator is lower than the threshold, a global shutdown is triggered to thoroughly investigate common problems. The hierarchical strategy divides the equipment strategy intervals, such as immediate shutdown of equipment with extremely low energy efficiency, load reduction operation of medium equipment, and enhanced monitoring of equipment close to the threshold. It not only avoids the production capacity loss caused by unplanned shutdown of normal equipment, but also realizes the precise isolation and rapid repair of faulty equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly describes the drawings required for the specific embodiments or the description of the prior art. Similar elements or parts are generally identified by similar reference numerals throughout the drawings. Elements or parts in the drawings are not necessarily drawn to scale.

[0019] Figure 1 Schematic diagram of the steps of the energy usage management method based on the Industrial Internet of Things of the present invention;

[0020] Figure 2 Schematic diagram of some steps in S1 of the energy usage management method based on the Industrial Internet of Things of the present invention;

[0021] Figure 3 Schematic diagram of some steps in S4 of the energy usage management method based on the Industrial Internet of Things of the present invention;

[0022] Figure 4Schematic diagram of the composition of the energy usage management system based on the Industrial Internet of Things of the present invention;

[0023] Figure 5 This is a schematic diagram of the composition of the optimized industrial Internet of Things involved in the present invention;

[0024] Figure 6 The present invention is a block diagram of an electronic device according to an embodiment of the present invention.

[0025] Reference numerals:

[0026] 700 - electronic device, 701 - processor, 702 - memory, 703 - multimedia component, 704 - I / O interface, 705 - communication component. DETAILED DESCRIPTION

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0028] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are intended to fall within the scope of protection of the present invention.

[0029] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings. In addition, the terms "first," "second," etc. are used only to distinguish the descriptions and are not to be understood as indicating or implying relative importance.

[0030] like Figure 1 As shown, a method for energy usage management based on industrial Internet of Things is provided, including:

[0031] S1. Obtain, based on the industrial Internet of Things, an area to be managed and multiple devices to be managed of the same device type within the area to be managed, obtain a dynamic time window with the current moment as the end, obtain historical status information of each device to be managed within the dynamic time window, and obtain energy supply information based on the historical status information;

[0032] S2. Obtain multiple consecutive time periods corresponding to energy supply information exceeding a preset energy supply rate based on the energy supply information and use them as multiple pre-processing energy supply time periods. Obtain a processing time period threshold based on a dynamic time window. If there is a pre-processing energy supply time period exceeding the processing time period threshold, obtain the longest pre-processing energy supply time period and use it as the energy supply time period to be processed.

[0033] S3. Obtaining load information and surface temperature information within the energy supply time period to be processed based on the historical status information, obtaining a load variation coefficient within the energy supply time period to be processed based on the first indicator model and the load information, obtaining a temperature variation coefficient within the energy supply time period to be processed based on the second indicator model and the surface temperature information, and obtaining a device energy usage indicator for each device to be managed based on the preset energy supply rate, load variation coefficient, and temperature variation coefficient;

[0034] S4. Obtain regional energy usage indicators of the area to be managed based on multiple device energy usage indicators that are less than a preset usage threshold, and obtain an energy usage management strategy based on the regional energy usage indicators and the device energy usage indicators.

[0035] In this embodiment, it should be noted that in S1, the target management area is first located in real time via the Industrial Internet of Things platform. Based on the device communication protocol and topology, clusters of managed devices within the area with the same device type identifier (e.g., the device classification code defined by the MES) are selected. The dynamic time window is constructed using a condition-adaptive adjustment mechanism: For different equipment types, such as injection molding machines and air compressors, a baseline time window is preset (e.g., 30 minutes for air compressors and 60 minutes for injection molding machines). The condition change rate factor is dynamically calculated by real-time monitoring of characteristics such as the frequency of device control signals and the number of process parameter adjustments. For example, if the clamping pressure of an injection molding machine fluctuates frequently due to mold changes, the time window is automatically shortened to improve monitoring sensitivity. Conversely, for centrifugal pumps operating continuously and smoothly, the window is extended to obtain more statistically significant data samples. This process ensures that the end of the time window is always anchored to the current moment, forming a forward-sliding data collection interval that effectively captures the latest operating status of the equipment.

[0036] Furthermore, within a defined dynamic time window, the Industrial Internet of Things (IIoT) simultaneously collects electrical parameters (such as three-phase current harmonics and power factor), mechanical status (such as bearing vibration spectrum and motor speed deviation), and thermodynamic data (such as surface temperature and coolant flow) from each device. After time series alignment, this heterogeneous data eliminates external interference factors such as ambient temperature fluctuations, accurately extracting energy supply feature vectors that reflect the device's true energy efficiency status, providing high-quality input for subsequent anomaly detection.

[0037] In S2, the system first identifies consecutive time periods in which energy supply data consistently exceeds a preset energy supply rate (e.g., 95% of the maximum power supply). These periods indicate that the equipment is operating at high load. "Continuity" here is defined as no instantaneous value falling below a threshold during the period, ensuring that the complete cycle of full energy supply is captured. When the equipment is fully powered, its load and thermodynamic characteristics can clearly reveal abnormal energy efficiency. For example, when a mechanical failure causes a reduction in the effective load rate, even if the energy supply is sufficient, the proportion of energy actually used for production decreases, and the excess energy is converted into ineffective heat. By extracting these periods of high energy supply, the true operating state of the equipment under extreme operating conditions can be accurately captured, avoiding data noise interference during low-load or intermittent operation. For example, if an air compressor has an air line leak when fully powered, its load (compressed air output) will be significantly lower than normal, and its surface temperature will rise abnormally due to energy loss. Such anomalies may be masked during low energy supply periods, but they will be amplified during high energy supply due to imbalances in the energy conversion pathway, thereby improving detection sensitivity.

[0038] Furthermore, the processing time period threshold is determined through a dynamic time window to ensure that the selected continuous high energy supply periods have sufficient analytical value. The design of this threshold is based on the equipment type and operating conditions. For example, for equipment such as injection molding machines with periodic load changes, if a period of high energy supply lasts for more than one-third of the length of the dynamic time window (the processing time period threshold), it is determined to be a valid analysis object. This mechanism can eliminate the interference of short-term operating condition fluctuations (such as instantaneous high energy consumption when the equipment starts) on the detection results and focus on continuous energy consumption anomalies. For example, a centrifugal pump may have increased friction due to bearing wear, and its high energy supply state may last for several hours. At this time, the load (liquid delivery volume) gradually decreases, while the surface temperature continues to accumulate heat due to mechanical friction. By identifying such long-term anomalies, normal production fluctuations and equipment degradation trends can be accurately distinguished, providing a reliable data basis for subsequent energy efficiency index calculations.

[0039] In S3, the dual characteristics of equipment load and surface temperature are first analyzed for the selected energy supply time periods to be processed. The calculation of the load variation coefficient focuses on the actual effective work capacity of the equipment under a continuous high energy supply state: when the equipment load value is lower than the preset standard, it indicates that the input energy is not fully converted into effective output (such as mechanical energy, pressure energy, etc.). At this time, the load variation coefficient increases, reflecting a decrease in energy utilization. For example, if the actual clamping force of an injection molding machine is insufficient due to a blocked hydraulic valve during the clamping phase, its load value will deviate significantly from the standard value despite sufficient energy supply. At this time, the load variation coefficient increases, indicating that the equipment has reduced mechanical efficiency or an abnormal actuator. By quantifying the degree of deviation of the load from the standard value, it is possible to accurately identify hidden energy efficiency losses caused by mechanical wear, transmission failure, or process parameter mismatch.

[0040] Further combined with the temperature variation coefficient, the degree of energy waste can be simultaneously assessed. The abnormal rise in surface temperature is related to ineffective energy conversion. For example, the aging of the motor winding insulation leads to increased resistance and increased loss of electrical energy into heat energy. The temperature variation coefficient captures the characteristics of abnormal heat dissipation or increased energy dissipation of the equipment by calculating the temperature rise rate per unit time. For example, if the exhaust temperature of the air compressor continues to rise due to a cooling failure, even if the load output is temporarily stable, its temperature variation coefficient will still increase significantly, providing an early warning of the hidden dangers of reduced cooling efficiency or increased internal friction. Finally, the load variation coefficient and the temperature variation coefficient are integrated, and an equipment energy usage index is generated based on the preset energy supply rate. This index can comprehensively reflect the energy efficiency health status of the equipment under high-load conditions. The lower the index, the lower the effective energy utilization rate and the more serious the waste, thus providing a key basis for fault location.

[0041] In S4, the energy usage indicators of all devices in the region are aggregated to generate a regional energy usage indicator that reflects the overall energy efficiency status. Specifically, this is done by directly adding up the energy usage indicators of each device and taking the average, with the average calculated as the regional energy usage indicator. This indicator quantifies the severity of regional energy waste by counting the number of devices below a preset threshold and the degree of deviation. For example, if the energy usage indicators of more than 70% of the injection molding machines in a workshop are consistently low, indicating that regional energy efficiency has deteriorated, the regional indicator will be significantly below the strategic threshold, triggering a global shutdown command to thoroughly investigate common problems (such as unstable grid voltage or cooling failures). This mechanism prevents single device anomalies from being overlooked, leading to the accumulation of regional energy losses, and prevents local failures from spreading to the entire production process.

[0042] If the regional energy usage index does not reach the shutdown threshold, the hierarchical strategy mechanism is activated. Multiple strategy intervals are divided according to the equipment energy usage index. For example, equipment with extremely low indicators will be shut down for maintenance immediately; equipment with medium indicators will run at a reduced load and trigger an early warning; and equipment with indicators close to the threshold will enter enhanced monitoring mode. For example, in a packaging line, the energy index of individual conveyor belt motors dropped sharply due to bearing wear. Only the faulty motor was isolated and switched to a backup unit, while the remaining equipment maintained normal operation. This refined strategy not only minimizes unnecessary downtime, but also achieves accurate positioning and rapid intervention of faulty equipment, ensuring dynamic matching of energy management strategies with the actual status of the equipment, and improving the targeted energy efficiency optimization and robustness of production.

[0043] To sum up, in the entire energy use management method based on the Industrial Internet of Things, first of all, the dynamic time window is adaptively adjusted based on the equipment type and the rate of change of the working condition, which effectively solves the lag problem of the traditional fixed time window in monitoring intermittent high-load working conditions. For example, the injection molding machine automatically shortens the window length when frequently adjusting the production parameters, and captures the instantaneous energy consumption anomalies caused by the clamping pressure fluctuation in real time, avoiding the omission of abnormal events caused by the long window; further, by screening the continuous time period that continuously exceeds the preset energy supply rate and setting the processing time period threshold, it can accurately distinguish between normal production fluctuations and progressive equipment failures. For example, the continuous load drop and temperature rise acceleration during the high energy supply period caused by the wear of the centrifugal pump bearing can be identified and the short-term working condition interference can be eliminated in the early stage, providing a high-quality data basis for subsequent analysis; further, through the coupling analysis of the load change coefficient and the temperature change coefficient, a breakthrough is achieved. The limitations of a single energy consumption indicator are overcome. Among them, the load variation coefficient quantifies the effective working capacity of the equipment and can locate mechanical efficiency problems such as hydraulic leakage and transmission mechanism wear. The temperature variation coefficient reveals thermodynamic anomalies such as insulation aging and cooling failure through temperature rise rate monitoring. For example, an abnormal rise in the exhaust temperature of an air compressor can provide early warning of cooling failures. Finally, the equipment energy usage indicator realizes a quantitative assessment of the health status of energy efficiency. The combined application of regional energy usage indicators and a grading strategy mechanism solves the drawbacks of "one-size-fits-all" management and control. When the regional indicator is lower than the threshold, a global shutdown is triggered to thoroughly investigate common problems. The grading strategy divides the equipment strategy intervals, such as immediate shutdown of equipment with extremely low energy efficiency, load reduction operation of medium equipment, and enhanced monitoring of equipment close to the threshold. This not only avoids the loss of production capacity caused by unplanned shutdown of normal equipment, but also achieves accurate isolation and rapid repair of faulty equipment.

[0044] In one embodiment, obtaining the dynamic time window whose end is the current time in S1 includes:

[0045] S11. Obtain the device type of the device to be managed, and obtain the operating condition change rate based on the device type;

[0046] S12. Obtain a dynamic time window whose end is the current moment according to the operating condition change rate.

[0047] In this embodiment, it should be noted that in S11, the operating characteristics of the device to be managed are identified through the device type identifier, and the corresponding operating condition change rate calculation logic is preset based on the device type. The operating condition change rate reflects the degree of dynamic fluctuation of the device's operating parameters, such as the mold switching frequency of an injection molding machine, the loading / unloading cycle of an air compressor, or the flow adjustment frequency of a centrifugal pump. For equipment that frequently adjusts process parameters (such as injection molding machines), the operating condition change rate is calculated in real time by monitoring the rate of change of control signals (such as the hydraulic valve opening adjustment frequency) or the production batch switching interval. For continuous process equipment (such as heat exchangers), operating condition stability is assessed by analyzing the stability indicators of parameters such as temperature and pressure. For example, when an injection molding machine performs small batch production of multiple products, mold changes may cause frequent jumps in the clamping force setpoint. This will automatically increase the weight of the operating condition change rate, providing a basis for subsequent dynamic adjustment of the time window.

[0048] In S12, dynamic time windows are generated by integrating equipment type baseline values ​​with real-time operating condition change rates to achieve adaptive adjustment. For equipment with high operating condition change rates (such as stamping presses that need to respond quickly to order changes), the time window is shortened to capture transient anomalies. For example, the base window is compressed from 60 minutes to 20 minutes to ensure timely identification of short-term energy consumption spikes caused by incorrect stroke parameters. Conversely, for equipment with low operating condition change rates (such as continuously operating drying kilns), the window is extended to several hours, using statistical averaging to eliminate interference from ambient temperature and humidity fluctuations in energy consumption analysis. For example, when an air compressor fleet enters a state of frequent loading due to a surge in gas demand, the operating condition change factor is increased, dynamically reducing the time window to 50% of its original length. This allows accurate capture of periodic load drops and inefficient energy supply caused by valve leaks. During normal operation, the base window length is restored to ensure data integrity. This mechanism ensures that the granularity of the time window is always synchronized with the actual operating rhythm of the equipment, avoiding the lag in detecting sudden events that occurs with fixed windows and preventing false alarms caused by oversensitivity.

[0049] In one embodiment, the dynamic time window whose end is the current moment is obtained according to the operating condition change rate in S12 is expressed as:

[0050] ;in,

[0051] is the length of the dynamic time window, is the length of the basic time window, is the rate of change of operating conditions, The standard ratio.

[0052] In this embodiment, it should be noted that when the equipment operating condition change rate For example, if the injection molding machine frequently changes the mold, the control signal will fluctuate violently. The item will be reduced, so that the dynamic window This design forces the monitoring window to be shortened in high-condition change scenarios to capture transient anomalies such as short-term energy consumption spikes; conversely, when Reduce the continuous and stable operation of the drying kiln, Automatic extension eliminates random interference by expanding the time span and improves the statistical significance of data.

[0053] Furthermore, the standard ratio The value is between 1 and 2, usually 1.5; at the same time, the value range of f is 0~1, the maximum value is 1, and the minimum value is 0; when =1, the maximum operating condition change rate, , the window length is compressed to 50% of the basic value to prevent data fragmentation caused by the window being too short under extreme working conditions. At the same time, the upper limit is expanded. =0 completely stable working condition, , the window is extended by 50% to meet the data smoothing needs of long-term stable operation.

[0054] To summarize, taking an air compressor as an example: when gas demand surges by f=0.8, the dynamic window is shortened from the base value of 60 minutes to 60*(1.5-0.8)=42 minutes. Within this window, periodic load drops caused by valve leakage can be captured, such as an abnormality where the energy supply rate exceeds the standard but the load is insufficient every 30 minutes. The traditional 24-hour fixed window cannot identify such short-term faults due to data dilution.

[0055] For injection molding machines operating in stable production, with f = 0.2, the window is extended to 60 * (1.5 - 0.2) = 78 minutes. This increases the amount of data to reduce the impact of brief external disturbances, such as transient grid voltage fluctuations, on energy efficiency assessment. For example, although a 0.5-second voltage dip may cause a transient power anomaly, statistical averaging within the 78-minute window will mitigate its impact and avoid triggering false alarms.

[0056] For example, the basic window of an injection molding machine = 60 minutes, the real-time monitoring shows that the mold switching frequency increases, and the working condition change rate f = 0.7. 60*(1.5-0.7)=48 minutes. The result: The window is shortened from 60 minutes to 48 minutes, focusing on the high-load period of 20 to 40 minutes after each mold change. During this period, the clamping force setting is frequently adjusted. This accurately captures abnormal load variation coefficients caused by delayed hydraulic valve response, resulting in sufficient energy supply but insufficient clamping force. If the original 60-minute window is maintained, the load fluctuations during these abnormal periods will be diluted by the low load data during non-production periods, resulting in an insufficient increase in the load variation coefficient and failure to reach the alarm threshold.

[0057] In one embodiment, the first indicator model in S3 in which the load variation coefficient in the energy supply time period to be processed is obtained based on the first indicator model and the load information is expressed as:

[0058] ;in,

[0059] is the load variation coefficient of the jth device to be managed during the energy supply period to be processed, is the number of loads obtained by the jth device to be managed during the energy supply period to be processed, is the i-th load of the j-th device to be managed in the energy supply time period to be processed, It is the standard load under the preset energy supply rate.

[0060] In this embodiment, it should be noted that middle, Keep only the load value Below standard value Negative deviations are detected to filter out normal load conditions. It indicates the theoretical standard load value that the equipment should achieve under the preset energy supply rate (such as 95% of the maximum power supply). It reflects the corresponding relationship between the input energy and the effective output load of the equipment under the relatively ideal state of trouble-free and efficient operation. It is the benchmark for evaluating the degree of deviation of the actual load. The initial value can be determined directly based on the rated performance parameters provided by the equipment manufacturer. For example, the initial value of the air compressor can be determined based on the gas output per unit time (m3) at the rated exhaust pressure. 3 The injection molding machine's hydraulic system output power can be calculated based on the rated clamping force (tons). Taking the motor as an example, the theoretical standard load value is the rated output power. Then, the negative deviations are summed. This design focuses on scenarios where energy is not effectively converted into mechanical output. For example, if the actual load is insufficient due to a hydraulic system leak, the cumulative value of the negative deviation increases. Finally, the average of the total negative deviations is calculated.

[0061] Furthermore, the exponential operation e^x is performed on the mean of the negative deviation, and its nonlinear compression characteristics are used to map the deviation to the range of 0~1. At the same time, using the value range of x, x is first scaled to ensure the consistency of the unit and to ensure that the calculated In line with the grading standards, there must be clear ladder values, such as Multiply by 10 for calculation; when all loads meet the standards , all min items are 0, and the exponent is e^0=1, then =0, indicating no abnormality. When the load continues to be insufficient and the negative deviation accumulates, the index value approaches 0. Approaching 1, it reflects a serious loss of energy efficiency. It is between [0, 1). The larger the value, the more serious the energy waste caused by insufficient load, providing standardized input for the subsequent equipment energy usage index I_j.

[0062] In summary, the existing methods rely on the average load rate, which may mask the transient load deficiency, such as the short-term pressure loss during the clamping phase of the injection molding machine. However, this model accumulates negative deviations, even if the single load drops slightly, such as Slightly lower , will also be recorded, thereby amplifying the signal of hidden performance loss; for example, in 10 sampling times, the load of an air compressor is 5% lower than the standard value 3 times. The traditional method of calculating the average load is still high, but this model can significantly improve it by accumulating negative deviations. , triggering an early warning. Furthermore, the exponential function has weak sensitivity to small negative deviations, but has a strong response to sustained large deviations. For example, a device may experience a single load drop of 0.6 ( ), if the rest of the load is normal, the average deviation is -0.2 (assuming =10), the exponent is e^{-0.2}≈0.818, then =0.182, which does not represent a serious abnormality; however, if the load drops by 0.6 for multiple times, the average deviation is -0.5, and the exponent is e^{-0.5}≈0.6, =0.4, indicating a certain degree of abnormality.

[0063] For example, a standard load is preset for an injection molding machine. =80%, 5 load values ​​are collected during the energy supply period to be processed: =50%, =95%, =60%, =96%, =64%. First, amplify each value by 10 times, and then substitute it into the formula to calculate the load variation coefficient: 0.733.

[0064] In one embodiment, the second indicator model in S3 in which the temperature variation coefficient in the energy supply time period to be processed is obtained based on the second indicator model and the surface temperature information is expressed as:

[0065] ;in,

[0066] is the temperature variation coefficient of the jth device to be managed during the power supply period to be processed, is the number of surface temperatures obtained by the jth device to be managed during the energy supply period to be processed, is the i+1th surface temperature of the jth device to be managed during the energy supply period to be processed, is the i-th surface temperature of the j-th device to be managed during the energy supply period to be processed, To obtain time point, To obtain time point.

[0067] In this embodiment, it should be noted that It is used to calculate the temperature change rate at adjacent time points and capture the instantaneous change trend of the equipment surface temperature. For example, when the insulation of the motor winding ages, the resistance increases, resulting in increased heat generation when the current passes through, and the temperature rise rate increases significantly. It is used to average all temperature change rates within a time period, eliminate occasional interference (such as short-term fluctuations in ambient temperature), and highlight continuous temperature rise anomalies. It is used to realize the nonlinear mapping of exponential function, mainly compressing the average temperature change rate x to the (0, 1) interval, and passing 1- Converted to positive indicator: When x=0 (no temperature rise): , indicating no energy waste; when x is large (dramatic temperature rise): Approaching 1 indicates that energy waste is extremely serious.

[0068] In summary, the existing methods only monitor the absolute value of temperature, but the initial stage of a fault may manifest as an abnormal temperature rise rate rather than an excessive temperature. For example, when the cooling efficiency of the air compressor decreases, it takes 10 minutes for the exhaust temperature to rise from 30°C to 50°C (a rate of 0.33°C / min), while under normal circumstances, the same temperature rise takes 20 minutes (a rate of 0.17°C / min). This model uses the rate difference (0.33 vs 0.17) to provide early warning, and can detect hidden dangers several hours earlier than traditional threshold alarms (such as temperature > 60°C). Furthermore, the temperature rise rate is positively correlated with invalid energy dissipation (such as friction and resistance loss). For example, the wear of a motor bearing causes the friction power loss to increase by 200W, and its surface temperature rise rate increases from 0.2°C / min to 0.5°C / min. Assuming that the model calculates ( ) increased from 0.18 to 0.39, which directly reflects the degree of energy efficiency degradation.

[0069] For example, during the waiting energy supply period, the surface temperature sampling data of an injection molding machine is as follows (the time interval is 5 minutes): =30°C, =35°C, =43°C, =52°C. Substitute this into the expression for calculation, ≈0.77.

[0070] Analyze the calculation results. If the value is close to 1, it indicates that the equipment has relatively serious energy waste (such as valve leakage or cooling failure). If the existing method only monitors the absolute value of temperature (the maximum temperature of 52°C does not exceed the safety threshold of 60°C), it will not trigger an alarm. However, this model exposes energy efficiency degradation through abnormal temperature rise rate. Assuming that the load change coefficient is combined (Load is normal), it can be inferred that the problem is caused by the cooling system (such as fan failure) rather than insufficient mechanical load.

[0071] In one embodiment, the device energy usage index of each device to be managed is obtained in S3 according to the preset energy supply rate, load variation coefficient, and temperature variation coefficient, and is expressed as:

[0072] ;in,

[0073] is the device energy usage index of the jth device to be managed, is the load variation coefficient of the jth device to be managed during the energy supply period to be processed, is the temperature variation coefficient of the jth device to be managed during the power supply period to be processed, The preset energy supply rate.

[0074] In this embodiment, it should be noted that the load variation coefficient Reflects the degree of effective energy utilization. The larger the value, the more serious the deviation of the actual load from the standard value, such as hydraulic system leakage leading to insufficient mechanical output; Temperature variation coefficient Reflects the degree of energy waste. The larger the value, the more significant the ineffective heat energy conversion, such as friction or resistance loss. The two types of energy efficiency issues are coupled to reflect the overall energy efficiency degradation level of the equipment; for example, a certain equipment may have high , cooling failure leads to high ,both cause the energy efficiency to deteriorate at the same time, and the denominator superimposes and amplifies the comprehensive abnormal signal.

[0075] Further, As a numerator, it represents the maximum energy supply capacity of the equipment under ideal conditions; when the actual energy efficiency deteriorates When it increases, Reduce, intuitively reflecting the gap between actual energy efficiency and theoretical upper limit. For example: assuming the equipment energy usage index =0.95 / (0.1+0.05)=6.33, indicating excellent energy efficiency, close to the theoretical upper limit; assuming that the equipment energy usage index =0.95 / (0.6+0.4)=0.95, the energy efficiency is seriously deteriorated, only 10% of the theoretical value.

[0076] Furthermore, the formula is divided by the operation to make right and The change of has nonlinear response characteristics: when When it is small, it is slightly abnormal, and at the same time, avoid being overly sensitive to small fluctuations; when When it is large, it is seriously abnormal. A sharp drop in alert priority.

[0077] In summary, existing methods only rely on the total energy consumption or average load rate, and cannot distinguish between effective energy utilization and waste; for example, a device is underloaded. =0.4 and abnormal temperature rise =0.3 comprehensive leads to low energy efficiency. Traditional methods miss detection because the total energy consumption does not exceed the standard, while this formula =0.95 / (0.4+0.3)=1.36, which can match a device policy threshold interval that triggers an alarm, thereby triggering an alarm. The numerical range of can be used to finely grade the energy efficiency status of multiple devices: >3.0 means normal equipment, maintaining operation; 1.5 3.0 represents mild abnormality and requires enhanced monitoring; 1.5 represents a serious abnormality, which immediately triggers an alarm and causes the equipment to be shut down for maintenance. At the same time, for example, the energy usage index of equipment A in a workshop =0.8 and the energy usage index of device B =1.2 are abnormal at the same time, but device A has a higher priority.

[0078] In one embodiment, obtaining the energy usage management strategy according to the regional energy usage index and the device energy usage index in S4 includes:

[0079] S41. Obtaining a regional policy threshold;

[0080] S42. If the regional energy usage index is less than the regional policy threshold, all the multiple managed devices in the managed area are shut down and repaired.

[0081] S43. If the regional energy usage index is not less than the regional policy threshold, set multiple different device policy threshold intervals, where each device policy threshold interval corresponds to an energy usage management policy;

[0082] S44: Match the device energy usage indicator of each device to be managed with the corresponding device policy threshold range, so as to obtain the energy usage management policy corresponding to each device to be managed.

[0083] In this embodiment, it should be noted that in S41, the setting of the regional policy threshold is based on the statistical distribution of historical energy efficiency data and the collaborative operation characteristics of the equipment group. By analyzing the distribution pattern of regional energy usage indicators during the normal production cycle (such as Gaussian distribution or quantile), combined with the equipment type, regional scale and historical failure frequency, the threshold boundary is dynamically determined. For example, in an injection molding machine cluster, if historical data shows that when the regional indicator is lower than 2 times the standard deviation of its normal mean, the risk of energy efficiency degradation of the equipment group increases sharply, this critical value is used as the threshold. The threshold update mechanism introduces sliding window statistics, and recalculates the latest data distribution regularly (such as weekly) to adapt to the energy efficiency baseline drift caused by equipment aging or process upgrades, ensuring that the threshold always reflects the true health status of the current production environment.

[0084] In S42, when a regional energy usage indicator falls below the policy threshold, it indicates system performance degradation within the region (e.g., a common cause failure or infrastructure anomaly). For example, a blockage in the cooling water circulation system in a workshop causes a simultaneous decrease in the cooling efficiency of multiple devices, leading to a continued decline in regional indicators. The system triggers a global shutdown command, forcibly interrupting energy supply and initiating a root cause diagnosis process. By correlating and analyzing the load and temperature anomaly patterns of the device cluster (e.g., a simultaneous increase in the temperature coefficient of variation across all devices), the root cause is identified (e.g., insufficient cooling water pressure). This strategy prioritizes device safety and energy conservation to prevent localized failures from spreading through the energy network (e.g., voltage fluctuations triggering a chain reaction).

[0085] In S43, if regional indicators do not trigger a global shutdown, multi-level policy intervals are created based on the statistical distribution of the equipment's energy usage indicators (e.g., percentiles or cluster analysis). For example, the Emergency Intervention Zone (lowest indicator, generally 10% of the faulty equipment's extreme value) indicates that equipment energy efficiency has severely deteriorated, requiring immediate shutdown and maintenance. The Optimized Operation Zone (intermediate, generally 10%-50% of the faulty equipment's extreme value) indicates that equipment has a tolerable energy efficiency loss, operates at reduced load, and triggers an alert. The Enhanced Monitoring Zone (high, generally 50%-100% of the faulty equipment's extreme value) indicates that equipment is in a sub-healthy state, increasing data collection frequency to real-time levels. The interval boundaries are calibrated using historical failure data and expert experience. For example, the extreme value of a faulty equipment's indicator corresponds to the extreme values ​​of 90% of past faulty equipment, ensuring that the policy aligns with actual risk.

[0086] In S44, each device's energy usage metrics are matched to preset intervals, triggering differentiated management and control. For example, on a packaging line, if conveyor motor A's metrics fall into the emergency intervention zone due to bearing wear, the system immediately cuts its power and dispatches a backup unit. If motor B's metrics fall into the optimized operating zone, its load is reduced to 70%, and an alarm is highlighted on the HMI interface. If motor C enters the enhanced monitoring zone, the vibration and temperature data sampling frequency is increased from 1 minute to 1 second. This tiered mechanism is executed in real time by edge computing nodes, ensuring policy response latency of less than 100ms, minimizing the impact of unplanned downtime on production cycles. At the same time, maintenance tasks are automatically generated through the work order system and pushed to the nearest available maintenance team.

[0087] An energy usage management system based on the industrial Internet of Things is also provided. The system includes a management platform, a sensor network platform, and an object platform that are sequentially communicatively connected. The object platform includes a plurality of managed devices within a to-be-managed area. The management platform includes:

[0088] An acquisition module is used to acquire, based on the industrial Internet of Things, an area to be managed and multiple devices to be managed of the same device type within the area to be managed, and acquire a dynamic time window with the current moment as the end, and acquire historical status information of each device to be managed within the dynamic time window, and acquire energy supply information based on the historical status information;

[0089] A first data processing module is configured to obtain, based on the energy supply information, multiple consecutive time periods corresponding to energy supply information exceeding a preset energy supply rate and use them as multiple pre-processing energy supply time periods, and obtain a processing time period threshold based on a dynamic time window. If there is a pre-processing energy supply time period exceeding the processing time period threshold, obtain the longest pre-processing energy supply time period and use it as the energy supply time period to be processed;

[0090] a second data processing module, configured to obtain load information and surface temperature information within a power supply time period to be processed based on the historical status information, obtain a load variation coefficient within the power supply time period to be processed based on the first indicator model and the load information, obtain a temperature variation coefficient within the power supply time period to be processed based on the second indicator model and the surface temperature information, and obtain a device energy usage indicator for each device to be managed based on a preset power supply rate, load variation coefficient, and temperature variation coefficient;

[0091] The energy management module is used to obtain the regional energy usage index of the area to be managed based on multiple equipment energy usage indicators that are less than a preset usage threshold, and to obtain the energy usage management strategy based on the regional energy usage index and the equipment energy usage index.

[0092] In this embodiment, it should be noted that, regarding the above-mentioned energy usage management system based on industrial Internet of Things, the specific method of performing operations has been described in detail in the implementation of the energy usage management method based on industrial Internet of Things, and will not be elaborated here.

[0093] It should also be noted that the entire energy usage management system based on the Industrial Internet of Things can be applied to the optimized Industrial Internet of Things, such as Figure 5 As shown, the optimized industrial Internet of Things includes a user platform, a service platform, a management platform, a sensor network platform, and an object platform that establish communication in sequence;

[0094] The user platform is configured to provide front-end services to users; users obtain the required perception service information through the user platform, process the perception service information, and convert it into user perception information; users analyze the user perception information and make corresponding decisions based on their own wishes, and convert the user perception information into user control information through the corresponding information system and send it to the service platform, thereby expressing the user's corresponding service demand intention.

[0095] The physical entities of the user platform include various user terminals, such as mobile phones, computers, dedicated terminals, etc., which realize user-end services through integration with user information system software.

[0096] The service platform is configured as an API server or other server used to establish communication between the management platform and the user platform to implement corresponding functions; the physical entity of the service platform includes various servers.

[0097] The management platform is configured to perform at least one of equipment operation status monitoring and management, data monitoring and management, equipment parameter management, and life cycle management; the management platform is the operation coordination platform of the Internet of Things, which may include various management sub-platforms, and different management sub-platforms perform different management services; the physical entities of the management platform include various servers.

[0098] The sensor network platform is configured to perform at least one of the following: network management, command management, device status management, data protocol management, data parsing, data classification, data transmission monitoring, and data transmission security management. The sensor network platform provides data communication, parsing, identification, and classification, preventing data from various object platforms from being directly aggregated on the management platform, which would result in data redundancy and inefficient data processing. The physical entities of the object platforms include various gateways, edge computing devices, and other devices.

[0099] The object platform is configured to perform specific production tasks such as production control, detection, and measurement; the physical entities of the production objects include various production equipment, sensors, etc.

[0100] Figure 6FIG is a block diagram of an electronic device showing an energy usage management method based on the industrial Internet of Things according to an exemplary embodiment. Figure 6 As shown, the electronic device 700 may include: a processor 701 , a memory 702 , and may further include one or more of a multimedia component 703 , an I / O interface 704 (input / output interface), and a communication component 705 .

[0101] The processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the aforementioned method for energy usage management based on the Industrial Internet of Things. The memory 702 is used to store various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, as well as application-related data such as contact information, sent and received messages, images, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 702 or transmitted via the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, such as a keyboard, a mouse, and buttons. These buttons may be virtual or physical. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G networks, or a combination thereof, without limitation. Accordingly, the communication component 705 may include a Wi-Fi module, a Bluetooth module, an NFC module, and the like.

[0102] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to execute the above-mentioned energy usage management method based on the Industrial Internet of Things.

[0103] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When executed by a processor, the program instructions implement the steps of the aforementioned method for managing energy usage based on the Industrial Internet of Things. For example, the computer-readable storage medium may be the aforementioned memory 702 including the program instructions. The program instructions may be executed by the processor 701 of the electronic device 700 to implement the aforementioned method for managing energy usage based on the Industrial Internet of Things.

[0104] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program that can be executed by a programmable device, and the computer program has a code portion for executing the above-mentioned energy usage management method based on the industrial Internet of Things when executed by the programmable device.

[0105] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details of the above embodiments. Within the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the scope of protection of the present disclosure.

[0106] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0107] In addition, the various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some or all of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and description of the present invention.

Claims

1. An energy usage management method based on industrial Internet of Things, characterized in that: include: Acquire an area to be managed and multiple devices to be managed of the same device type within the area to be managed according to the industrial Internet of Things, obtain a dynamic time window with the current moment as the end, obtain historical status information of each device to be managed within the dynamic time window, and obtain energy supply information based on the historical status information; The step of obtaining the dynamic time window whose end point is the current moment includes: obtaining the device type of the device to be managed, and obtaining the operating condition change rate according to the device type; obtaining the dynamic time window whose end point is the current moment according to the operating condition change rate; According to the energy supply information, multiple consecutive time periods corresponding to energy supply information exceeding a preset energy supply rate are obtained and used as multiple pre-processing energy supply time periods. A processing time period threshold is obtained according to a dynamic time window. If there is a pre-processing energy supply time period exceeding the processing time period threshold, the longest pre-processing energy supply time period is obtained and used as the energy supply time period to be processed. Obtaining load information and surface temperature information within the energy supply time period to be processed based on the historical status information, obtaining a load variation coefficient within the energy supply time period to be processed based on the first indicator model and the load information, obtaining a temperature variation coefficient within the energy supply time period to be processed based on the second indicator model and the surface temperature information, and obtaining a device energy usage indicator for each device to be managed based on the preset energy supply rate, load variation coefficient, and temperature variation coefficient; A regional energy usage index of a to-be-managed area is obtained based on multiple device energy usage indexes that are less than a preset usage threshold, and an energy usage management strategy is obtained based on the regional energy usage index and the device energy usage index.

2. The energy usage management method based on industrial Internet of Things according to claim 1 is characterized in that: The dynamic time window whose end is the current moment obtained according to the operating condition change rate is expressed as: ;in, is the length of the dynamic time window, is the length of the basic time window, is the rate of change of operating conditions, The standard ratio.

3. The energy usage management method based on industrial Internet of Things according to claim 1 is characterized in that: The first indicator model in the load variation coefficient in the energy supply time period to be processed obtained based on the first indicator model and load information is expressed as: ;in, is the load variation coefficient of the jth device to be managed during the energy supply period to be processed, is the number of loads obtained by the jth device to be managed during the energy supply period to be processed, is the i-th load of the j-th device to be managed in the energy supply time period to be processed, It is the standard load under the preset energy supply rate.

4. The energy usage management method based on industrial Internet of Things according to claim 1 is characterized in that: The second indicator model in the temperature variation coefficient in the energy supply time period to be processed obtained based on the second indicator model and the surface temperature information is expressed as: ;in, is the temperature variation coefficient of the jth device to be managed during the power supply period to be processed, is the number of surface temperatures obtained by the jth device to be managed during the energy supply period to be processed, is the i+1th surface temperature of the jth device to be managed during the energy supply period to be processed, is the i-th surface temperature of the j-th device to be managed during the energy supply period to be processed, To obtain time point, To obtain time point.

5. The energy usage management method based on industrial Internet of Things according to claim 1 is characterized in that: The device energy usage index of each device to be managed is obtained according to the preset energy supply rate, load variation coefficient and temperature variation coefficient as follows: ;in, is the device energy usage index of the jth device to be managed, is the load variation coefficient of the jth device to be managed during the energy supply period to be processed, is the temperature variation coefficient of the jth device to be managed during the power supply period to be processed, The preset energy supply rate.

6. The energy usage management method based on industrial Internet of Things according to claim 1 is characterized in that: The energy usage management strategy obtained based on the regional energy usage index and the equipment energy usage index includes: Get the regional policy threshold; If the regional energy usage index is less than the regional policy threshold, all managed devices in the management area will be shut down and repaired; If the regional energy usage index is not less than the regional policy threshold, multiple different device policy threshold intervals are set, where each device policy threshold interval corresponds to an energy usage management policy; The device energy usage indicator of each device to be managed is matched with the corresponding device policy threshold range, so as to obtain the energy usage management policy corresponding to each device to be managed.

7. An energy usage management system based on industrial Internet of Things, characterized in that: The system includes a management platform, a sensor network platform, and an object platform that are communicatively connected in sequence, and the management platform includes: An acquisition module is used to acquire, based on the industrial Internet of Things, an area to be managed and multiple devices to be managed of the same device type within the area to be managed, and acquire a dynamic time window with the current moment as the end, and acquire historical status information of each device to be managed within the dynamic time window, and acquire energy supply information based on the historical status information; The step of obtaining the dynamic time window whose end point is the current moment includes: obtaining the device type of the device to be managed, and obtaining the operating condition change rate according to the device type; obtaining the dynamic time window whose end point is the current moment according to the operating condition change rate; A first data processing module is configured to obtain, based on the energy supply information, multiple consecutive time periods corresponding to energy supply information exceeding a preset energy supply rate and use them as multiple pre-processing energy supply time periods, and obtain a processing time period threshold based on a dynamic time window. If there is a pre-processing energy supply time period exceeding the processing time period threshold, obtain the longest pre-processing energy supply time period and use it as the energy supply time period to be processed; a second data processing module, configured to obtain load information and surface temperature information within a power supply time period to be processed based on the historical status information, obtain a load variation coefficient within the power supply time period to be processed based on the first indicator model and the load information, obtain a temperature variation coefficient within the power supply time period to be processed based on the second indicator model and the surface temperature information, and obtain a device energy usage indicator for each device to be managed based on a preset power supply rate, load variation coefficient, and temperature variation coefficient; The energy management module is used to obtain the regional energy usage index of the area to be managed based on multiple equipment energy usage indicators that are less than a preset usage threshold, and to obtain the energy usage management strategy based on the regional energy usage index and the equipment energy usage index.

8. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the energy usage management method based on the industrial Internet of Things as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the energy usage management method based on the industrial Internet of Things described in any one of claims 1 to 6 is implemented.

Images