An energy consumption monitoring method and system based on the Industrial Internet of Things

Abstract

The application provides an energy consumption monitoring method and system based on an industrial Internet of Things, and relates to the technical field of industrial production. The type of a target product, the specification of the target product, the number of target products produced by a production line in an Nth cycle, and the sub-energy consumption of target process equipment are input into a first energy consumption estimation model configured with Nth network parameters to obtain Nth estimated total energy consumption of each process equipment. The reliability of the obtained Nth estimated total energy consumption of each process equipment is high, and the energy consumption of the production line system is not dependent on an electric meter. A reinforcement learning model can continuously optimize the Nth working parameters corresponding to different process equipment respectively according to the obtained energy consumption effective utilization value until the energy consumption effective utilization value of different process equipment is improved to be stable. In the case of ensuring that the quality of the target product produced is qualified, the energy consumption of the production line system is minimized, the energy consumption cost of an enterprise is saved, and energy is saved and the environment is protected.

Description

Technical Field

[0001] This application relates to the field of industrial production technology, and in particular to an energy consumption monitoring method and system based on the Industrial Internet of Things. Background Technology

[0002] In the era of Industry 4.0, the Industrial Internet of Things (IIoT), as a product of the integration of next-generation information technology and manufacturing, connects people, machines, and things through the integration of intelligent sensing, identification, and other communication and sensing technologies. By using IIoT technology to monitor the energy consumption of production line systems used to produce target products (such as steel strips, diesel, gasoline, or cardboard boxes), factories and enterprises can be encouraged to transform their energy consumption optimization management models, which helps to improve energy efficiency.

[0003] Currently, electricity meters are commonly used to monitor the energy consumption of production line systems. However, due to the complex structure of electricity meters and the numerous electronic components they contain (such as transformers and coils), they are susceptible to corrosion from the production line environment (such as high temperature and humidity), leading to meter damage and poor reliability in monitoring the energy consumption of the production line system. Furthermore, the energy consumption when using the production line system to produce the target product is high, resulting in high energy costs for enterprises and being neither energy-efficient nor environmentally friendly. Summary of the Invention

[0004] This application provides an energy consumption monitoring method and system based on the Industrial Internet of Things (IIoT) to address the poor reliability of energy consumption monitoring in existing production line systems. Furthermore, the high energy consumption in producing target products using production line systems results in high energy costs for enterprises and is not energy-efficient or environmentally friendly.

[0005] Firstly, this application provides an energy consumption monitoring method based on the Industrial Internet of Things (IIoT), applied to an IIoT-based energy consumption monitoring device. The IIoT-based energy consumption monitoring device monitors the energy consumption of a production line system producing a target product. The production line system includes multiple different process equipment pre-configured with an Nth working parameter, and each process equipment has a different type of Nth working parameter. The raw materials of the target product are sequentially processed by the process equipment configured with the corresponding Nth working parameter to obtain the target product. The device includes a remote server, a monitoring terminal, and voltage and current acquisition modules for the target process equipment installed in the multiple process equipment. The remote server is communicatively connected to the monitoring terminal, voltage acquisition module, and current acquisition module via the IIoT. The method provided in this application includes:

[0006] Step 1: The remote server receives the operating current of the target process equipment collected by the current acquisition module and the operating voltage of the target process equipment collected by the voltage acquisition module at each sampling time in the Nth cycle, where N is an integer greater than 2 and the initial value of N is 2.

[0007] Step 2: The remote server determines the sub-energy consumption of the target process equipment based on the operating current, operating voltage, and operating duration of the Nth cycle of the target process equipment at each sampling time.

[0008] Step 3: At the end of the Nth cycle, the remote server receives from the monitoring terminal the type of the target product, the specifications of the target product, and the quantity of the target product produced by the production line in the Nth cycle;

[0009] Step 4: The remote server inputs the type of the target product, the specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the sub-energy consumption of the target process equipment into the pre-trained first energy consumption prediction model configured with the Nth network parameters, so as to obtain the Nth estimated total energy consumption of each process equipment in the production line system. The first energy consumption prediction model is trained by inputting multiple first training samples into the first neural network. Each first training sample includes the type of the target product in history, the specifications of the target product in history, the quantity of the target product produced by the production line in the Nth cycle in history, the sub-energy consumption of the target process equipment in history, and the corresponding Nth actual total energy consumption of the production line system in history.

[0010] Step 5: The remote server sends the Nth estimated total energy consumption of each process equipment in the production line system to the monitoring terminal for display;

[0011] Step 6: The remote server inputs the type of the target product, the specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the estimated total energy consumption in the Nth cycle into the pre-trained energy efficiency utilization value determination model to obtain the energy efficiency utilization value of the production line system in the Nth cycle. The energy efficiency utilization value determination model is trained by inputting multiple second training samples into the second neural network. Each second training sample includes the type of the target product in history, the specifications of the target product in history, the quantity of the target product produced by the production line in the Nth cycle in history, the actual total energy consumption of the production line system in the Nth cycle in history, and the corresponding expert-calibrated actual energy efficiency utilization value of the production line system.

[0012] Step 7: The remote server determines whether the difference between the energy efficiency value of the Nth cycle and the energy efficiency value of the (N-1)th cycle is greater than the set difference threshold. The type and specifications of the target product are the same for each cycle.

[0013] Step 8: If the difference between the energy efficiency value of the Nth cycle and the energy efficiency value of the (N-1)th cycle is greater than the set difference threshold, the remote server uses a pre-configured reinforcement learning model to update the Nth working parameter corresponding to different process equipment within the preset working parameter range, and increments the value of N by 1. Steps 1-7 above are repeated. When different process equipment are working within the corresponding preset working parameter range, the target product produced by the production line system is qualified.

[0014] Step 9: If the difference between the energy efficiency value of the Nth cycle and the energy efficiency value of the (N-1)th cycle is less than or equal to the set difference threshold, the remote server sets the Nth working parameter corresponding to different process equipment to the default working parameter, increments the value of N by 1, and repeats steps 1-5 above until a stop monitoring command is received from the monitoring terminal.

[0015] In one possible implementation, before sending the Nth estimated total energy consumption of each process equipment in the production line system to the monitoring terminal for display, the method provided in this application further includes:

[0016] The remote server retrieves multiple estimated total energy consumptions corresponding to the first M consecutive cycles with the same duration as the Nth cycle, where M is an integer greater than 2.

[0017] The temporal dependencies of multiple estimated total energy consumptions are extracted using a deep belief DBN network.

[0018] Based on the time-series dependencies of multiple estimated total energy consumptions, the energy consumption variation characteristics of multiple estimated total energy consumptions are determined;

[0019] A pre-trained second energy consumption prediction model is used to determine the energy consumption prediction for the Nth period based on the energy consumption change characteristics of multiple predicted total energy consumption corresponding to the previous M consecutive periods. The second energy consumption prediction model is obtained by inputting multiple third training samples into a third neural network for training. Each third training sample includes the historical energy consumption change characteristics of multiple historical predicted total energy consumption corresponding to the previous M consecutive periods with the same duration as the historical Nth period, as well as the historical energy consumption prediction for the corresponding historical Nth period.

[0020] Based on the energy consumption estimate for the Nth cycle, adjust the total energy consumption estimate for the Nth cycle.

[0021] In one possible implementation, the estimated total energy consumption for the Nth cycle is corrected based on the estimated energy consumption for the Nth cycle, including:

[0022] The remote server corrects the estimated total energy consumption for the Nth cycle based on the formula P3 = k1P1 + k2P2, where P1 is the original estimated total energy consumption for the Nth cycle, P2 is the estimated energy consumption for the Nth cycle, P3 is the corrected estimated total energy consumption for the Nth cycle, k1 is the first weighting coefficient, k2 is the second weighting coefficient, and 0 < k1 < k2 < k2. <k2<k1<1,k1+k2=1。

[0023] In one possible implementation, the Nth network parameter is the state of the reinforcement learning model, updating the Nth network parameter is the action of the reinforcement learning model, and the energy efficiency value of the Nth cycle is the reward of the reinforcement learning model.

[0024] In one possible implementation, after obtaining the Nth estimated total energy consumption of each process equipment in the production line system, the method provided in this application further includes:

[0025] If the Nth estimated total energy consumption exceeds the set energy consumption threshold, the remote server will send a warning message to the monitoring terminal to indicate that the energy consumption is too high.

[0026] Secondly, this application also provides an energy consumption monitoring system based on the Industrial Internet of Things (IIoT), configured on a remote server. The remote server is an IIoT-based energy consumption monitoring device used to monitor the energy consumption of a production line system producing a target product. The production line system includes multiple different process equipment pre-configured with Nth working parameters, and each process equipment has a different type of Nth working parameter. The raw materials of the target product are processed sequentially through the process equipment configured with the corresponding Nth working parameters to obtain the target product. The device also includes a monitoring terminal and voltage acquisition modules and current acquisition modules for the target process equipment installed in the multiple process equipment. The remote server is communicatively connected to the monitoring terminal, voltage acquisition modules, and current acquisition modules via the IIoT. The system provided by this application includes:

[0027] The information receiving unit is used to receive the operating current of the target process equipment collected by the current acquisition module and the operating voltage of the target process equipment collected by the voltage acquisition module at each sampling time in the Nth cycle, where N is an integer greater than 2 and the initial value of N is 2.

[0028] The sub-energy consumption determination unit is used to determine the sub-energy consumption of the target process equipment based on the operating current, operating voltage, and operating duration of the Nth cycle of the target process equipment at each sampling time.

[0029] The information receiving unit is also used to receive, at the end of the Nth cycle, the type of the target product, the specifications of the target product, and the quantity of the target product produced by the production line in the Nth cycle from the monitoring terminal.

[0030] The total energy consumption prediction unit is used to input the type of the target product, the specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the sub-energy consumption of the target process equipment into a pre-trained first energy consumption prediction model configured with the Nth network parameters, so as to obtain the Nth estimated total energy consumption of each process equipment of the production line system. The first energy consumption prediction model is trained by inputting multiple first training samples into the first neural network. Each first training sample includes the type of historical target product, the specifications of historical target product, the quantity of target product produced by the production line in the Nth cycle in history, the sub-energy consumption of the target process equipment in history, and the corresponding historical Nth actual total energy consumption of the production line system.

[0031] The information sending unit is used to send the Nth estimated total energy consumption of each process equipment in the production line system to the monitoring terminal for display.

[0032] The energy consumption effective utilization value determination unit is used to input the type of the target product, the specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the estimated total energy consumption in the Nth cycle into a pre-trained energy consumption effective utilization value determination model to obtain the energy consumption effective utilization value of the production line system in the Nth cycle. The energy consumption effective utilization value determination model is trained by inputting multiple second training samples into a second neural network. Each second training sample includes the type of historical target product, the specifications of historical target product, the quantity of the target product produced by the production line in the Nth cycle in history, the actual total energy consumption of the production line system in the Nth cycle in history, and the corresponding expert-calibrated actual energy consumption effective utilization value of the production line system.

[0033] The judgment unit is used to determine whether the difference between the energy consumption effective utilization value of the Nth cycle and the energy consumption effective utilization value of the (N-1)th cycle is greater than the set difference threshold, wherein the type and specifications of the target product are the same in each cycle.

[0034] The parameter update unit is used to update the Nth working parameter of different process equipment within the preset working parameter range of different process equipment when the difference between the energy consumption effective utilization value of the Nth cycle and the energy consumption effective utilization value of the (N-1)th cycle is greater than the set difference threshold. The unit also increments the value of N by 1 and repeats the above steps 1-7. When different process equipment are working within the corresponding preset working parameter range, the target product produced by the production line system is qualified.

[0035] The parameter configuration unit is used to set the Nth working parameter corresponding to different process equipment as the default working parameter when the difference between the energy consumption effective utilization value of the Nth cycle and the energy consumption effective utilization value of the N-1th cycle is less than or equal to the set difference threshold, and to increment the value of N by 1, and repeat the above steps 1-5 until a stop monitoring command is received from the monitoring terminal.

[0036] In one possible implementation, the system provided in this application further includes:

[0037] The information acquisition unit is used to acquire multiple estimated total energy consumptions corresponding to the first M consecutive cycles with the same duration as the Nth cycle, where M is an integer greater than 2.

[0038] The dependency extraction unit is used to extract the time-series dependencies of multiple estimated total energy consumptions using a deep belief DBN network.

[0039] The change characteristic determination unit is used to determine the energy consumption change characteristics of multiple estimated total energy consumptions based on the time-series dependence of multiple estimated total energy consumptions.

[0040] The energy consumption prediction unit is used to determine the energy consumption prediction for the Nth period by using a pre-trained second energy consumption prediction model based on the energy consumption change characteristics of multiple predicted total energy consumption corresponding to the previous M consecutive periods. The second energy consumption prediction model is obtained by inputting multiple third training samples into a third neural network for training. Each third training sample includes historical energy consumption change characteristics of multiple historical predicted total energy consumption corresponding to the previous M consecutive periods with the same duration as the historical Nth period, as well as the corresponding historical energy consumption prediction for the historical Nth period.

[0041] The energy consumption correction unit is used to correct the estimated total energy consumption for the Nth cycle based on the estimated energy consumption for the Nth cycle.

[0042] In one possible implementation, the energy consumption correction unit is specifically used to correct the Nth estimated total energy consumption according to the formula P3 = k1P1 + k2P2, where P1 is the Nth estimated total energy consumption before correction, P2 is the energy consumption estimate for the Nth period, P3 is the Nth estimated total energy consumption after correction, k1 is the first weighting coefficient, k2 is the second weighting coefficient, and 0 <k2<k1<1,k1+k2=1。

[0043] In one possible implementation, the Nth network parameter is the state of the reinforcement learning model, updating the Nth network parameter is the action of the reinforcement learning model, and the energy efficiency value of the Nth cycle is the reward of the reinforcement learning model.

[0044] In one possible implementation, the information sending unit is further configured to send a prompt message to the monitoring terminal indicating high energy consumption when the Nth estimated total energy consumption is greater than a set energy consumption threshold.

[0045] This application provides an energy consumption monitoring method and system based on the Industrial Internet of Things (IIoT). It determines the sub-energy consumption of the target process equipment based on the operating current, operating voltage, and operating duration of the Nth cycle at each sampling time. The type and specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the sub-energy consumption of the target process equipment are input into a pre-trained first energy consumption prediction model configured with Nth network parameters to obtain the Nth estimated total energy consumption of each process equipment in the production line system. There are certain patterns in energy consumption among multiple different process equipment (e.g., corresponding ratios), and the energy consumption of each process equipment is correlated with the type, specifications, and quantity of the target product. Therefore, the Nth estimated total energy consumption of each process equipment in the production line system obtained through the above method is highly reliable and does not rely on electricity meters to monitor the energy consumption of the production line system, further ensuring the high reliability of energy consumption monitoring of the production line system.

[0046] Furthermore, the type and specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the estimated total energy consumption in the Nth cycle are input into a pre-trained energy efficiency value determination model to obtain the energy efficiency value of the production line system in the Nth cycle, ensuring high reliability. In addition, the reinforcement learning model can continuously optimize the Nth operating parameters of different process equipment based on the obtained energy efficiency value until the energy efficiency value of different process equipment stabilizes. This allows for the lowest possible energy consumption of the production line system while ensuring the quality of the target product, saving energy costs for the enterprise and promoting energy conservation and environmental protection. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 A flowchart illustrating the energy consumption monitoring method based on the Industrial Internet of Things provided in this application embodiment;

[0049] Figure 2 A functional block diagram of an energy consumption monitoring system based on the Industrial Internet of Things provided in this application embodiment. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments made by those skilled in the art under the guidance of these embodiments are within the scope of protection of this application.

[0051] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application 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.

[0052] This application provides an energy consumption monitoring method based on the Industrial Internet of Things (IIoT), applied to an IIoT-based energy consumption monitoring device. The IIoT-based energy consumption monitoring device monitors the energy consumption of a production line system that produces a target product. The production line system includes multiple different process devices pre-configured with an Nth operating parameter, and each process device has a different type of Nth operating parameter. The raw materials for the target product are sequentially processed by the process devices configured with corresponding Nth operating parameters to obtain the target product.

[0053] For example, when the target product is strip steel and the production line system is a strip steel production line system, multiple process equipment includes heating equipment that uses blast furnace gas as the heating medium to heat qualified continuously cast billets to the target temperature (e.g., 1200℃), descaling equipment that uses high-pressure water to remove iron oxide scale from the surface of the billets, a roughing mill for multi-pass rolling of the billets, a finishing mill for finishing the rough-rolled strip steel, and a laminar flow cooling device for cooling the strip steel. Different types of operating parameters for these multiple process equipment can include the target heating temperature of the heating equipment, the water pressure of the high-pressure water in the descaling equipment, the operating power of the roughing mill, the operating power of the finishing mill, and the cooling temperature of the laminar flow cooling device. As another example, when the target product is gasoline and the production line system is an oil refining process production line system, multiple process equipment includes crude gasoline towers, absorption towers, air compressors, condensate tanks, and stabilization towers.

[0054] Furthermore, the energy consumption monitoring device based on the Industrial Internet of Things (IIoT) includes a remote server, a monitoring terminal, and voltage and current acquisition modules for the target process equipment installed in multiple process devices. The remote server communicates with the monitoring terminal, voltage acquisition module, and current acquisition module respectively via the IIoT. Figure 1 As shown, the method provided in this application embodiment includes:

[0055] S101: The remote server receives the operating current of the target process equipment collected by the current acquisition module and the operating voltage of the target process equipment collected by the voltage acquisition module at each sampling time in the Nth cycle, where N is an integer greater than 2 and the initial value of N is 2.

[0056] S102: The remote server determines the sub-energy consumption of the target process equipment based on the operating current, operating voltage, and operating duration of the Nth cycle of the target process equipment at each sampling time.

[0057] For example, the power at each sampling moment can be determined by analyzing the operating current and voltage of the target process equipment. The sub-energy consumption of the target process equipment is then determined by integrating the power and operating duration at each sampling moment. The target process equipment can be the most stable among multiple process equipment.

[0058] S103: At the end of the Nth cycle, the remote server receives from the monitoring terminal the type of the target product, the specifications of the target product, and the quantity of the target product produced by the production line in the Nth cycle.

[0059] S104: The remote server inputs the type of the target product, the specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the sub-energy consumption of the target process equipment into the pre-trained first energy consumption prediction model configured with the Nth network parameters, so as to obtain the Nth estimated total energy consumption of each process equipment in the production line system.

[0060] The first energy consumption prediction model is obtained by inputting multiple first training samples into the first neural network. Each first training sample includes the type of historical target product, the specifications of historical target product, the number of target products produced by the production line in the Nth cycle in history, the sub-energy consumption of the target process equipment in history, and the corresponding actual total energy consumption of the production line system in the Nth cycle in history.

[0061] S105: The remote server sends the Nth estimated total energy consumption of each process equipment in the production line system to the monitoring terminal for display.

[0062] S106: The remote server inputs the type of the target product, the specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the estimated total energy consumption in the Nth cycle into the pre-trained energy consumption effective utilization value determination model to obtain the energy consumption effective utilization value of the production line system in the Nth cycle.

[0063] The energy consumption effective utilization value determination model is obtained by inputting multiple second training samples into the second neural network for training. Each second training sample includes the type of historical target product, the specifications of historical target product, the number of target products produced by the production line in the Nth cycle in history, the actual total energy consumption of the production line system in the Nth cycle in history, and the corresponding expert-calibrated actual energy consumption effective utilization value of the production line system.

[0064] For example, the effective energy utilization value can be understood as, but is not limited to, data that shows a positive correlation between the minimum energy consumption required to produce a target product of a target type, target specifications, and target quantity and the actual energy consumption.

[0065] S107: The remote server determines whether the difference between the effective energy utilization value of the Nth cycle and the effective energy utilization value of the N-1th cycle is greater than the set difference threshold. If yes, then execute S108; otherwise, execute S109.

[0066] In each cycle, the type and specifications of the target product are the same.

[0067] S108: The remote server uses a pre-configured reinforcement learning model to update the Nth working parameter corresponding to different process equipment within the preset working parameter range, and increments the value of N by 1, repeating the above steps S101-S107.

[0068] For example, the target heating temperature of the heating equipment in the strip steel production line system, the water pressure of the high-pressure water in the descaling equipment, the working power of the roughing mill, the working power of the finishing mill, and the cooling temperature of the laminar flow cooling device can be updated.

[0069] Understandably, multiple process equipment can have various combinations of working parameters to produce qualified target products of the target type, target specifications, and target quantity. The combination of working parameters that minimizes the energy consumption of the production line system can be selected.

[0070] Specifically, when different process equipment operates within their respective preset operating parameter ranges, the target product produced by the production line system is deemed qualified. The Nth network parameter represents the state of the reinforcement learning model, updating the Nth network parameter represents the action of the reinforcement learning model, and the energy efficiency utilization value of the Nth cycle is the reward of the reinforcement learning model.

[0071] S109: The remote server sets the Nth working parameter corresponding to different process equipment to the default working parameter, increments the value of N by 1, and repeats the above steps S101-S105 if no stop monitoring instruction is received from the monitoring terminal.

[0072] In summary, this application provides an energy consumption monitoring method based on the Industrial Internet of Things (IIoT). It determines the sub-energy consumption of the target process equipment based on the operating current, operating voltage, and operating duration of the Nth cycle at each sampling time. The type and specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the sub-energy consumption of the target process equipment are input into a pre-trained first energy consumption prediction model configured with Nth network parameters to obtain the Nth estimated total energy consumption of each process equipment in the production line system. There is a certain pattern in the energy consumption among multiple different process equipment (e.g., a corresponding ratio), and the energy consumption of each process equipment is correlated with the type, specifications, and quantity of the target product. Therefore, the Nth estimated total energy consumption of each process equipment in the production line system obtained through the above method is highly reliable and does not rely on electricity meters to monitor the energy consumption of the production line system, further ensuring the high reliability of energy consumption monitoring of the production line system.

[0073] Furthermore, the type and specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the estimated total energy consumption in the Nth cycle are input into a pre-trained energy efficiency value determination model to obtain the energy efficiency value of the production line system in the Nth cycle, ensuring high reliability. In addition, the reinforcement learning model can continuously optimize the Nth operating parameters of different process equipment based on the obtained energy efficiency value until the energy efficiency value of different process equipment stabilizes. This allows for the lowest possible energy consumption of the production line system while ensuring the quality of the target product, saving energy costs for the enterprise and promoting energy conservation and environmental protection.

[0074] In one possible implementation, prior to S105, the method provided in this application embodiment further includes:

[0075] Step A: The remote server retrieves multiple estimated total energy consumptions corresponding to the first M consecutive cycles with the same duration as the Nth cycle, where M is an integer greater than 2. For example, M can be equal to 3, 4, or 5, etc., and is not limited here.

[0076] Step B: Use a deep belief DBN network to extract the time-series dependencies of multiple estimated total energy consumptions.

[0077] Step C: Based on the time-series dependencies of multiple estimated total energy consumptions, determine the energy consumption variation characteristics of multiple estimated total energy consumptions.

[0078] Step D: Using the pre-trained second energy consumption prediction model, determine the energy consumption prediction amount for the Nth cycle according to the energy consumption change characteristics of the corresponding multiple predicted total energy consumptions in the continuous first M cycles.

[0079] Among them, the second energy consumption prediction model is obtained by training multiple third training samples input into the third neural network. Each third training sample includes the historical energy consumption change characteristics of the corresponding multiple historical predicted total energy consumptions in the first M cycles that are equal in duration to the historical Nth cycle and are continuous, and the historical energy consumption prediction amount of the corresponding historical Nth cycle.

[0080] Step E: Correct the Nth predicted total energy consumption according to the energy consumption prediction amount for the Nth cycle.

[0081] Based on the above steps A - step E, the reliability of the Nth predicted total energy consumption can be made higher.

[0082] Step E can be implemented as: The remote server corrects the Nth predicted total energy consumption according to the formula P3 = k1P1 + k2P2. Where, P1 is the Nth predicted total energy consumption before correction, P2 is the energy consumption prediction amount for the Nth cycle, P3 is the Nth predicted total energy consumption after correction, k1 is the first weighting coefficient, k2 is the second weighting coefficient, and 0 < k2 < k1 < 1, k1 + k2 = 1. For example, k1 = 0.7, k2 = 0.3; or, k1 = 0.8, k2 = 0.2.

[0083] In a possible implementation manner, after S104, the method provided by the embodiment of the present application further includes that when the Nth predicted total energy consumption is greater than the set energy consumption threshold, the remote server sends a prompt message for indicating high energy consumption to the monitoring terminal for the monitoring personnel to perceive.

[0084] In addition, the embodiment of the present application also provides an energy consumption monitoring system based on the industrial Internet of Things, which is configured on the remote server. It should be noted that the basic principle and the technical effects generated by the energy consumption monitoring system based on the industrial Internet of Things provided by the embodiment of the present application are the same as those of the above embodiment. For the sake of brief description, for the parts not mentioned in the embodiment of the present application, reference can be made to the corresponding content in the above embodiment.

[0085] The remote server is an energy consumption monitoring device based on the Industrial Internet of Things (IIoT). This IIoT-based energy consumption monitoring device is used to monitor the energy consumption of a production line system that produces a target product. The production line system includes multiple different process devices pre-configured with Nth operating parameters, and each process device has a different type of Nth operating parameter. The raw materials for the target product are sequentially processed by the process devices configured with corresponding Nth operating parameters to obtain the target product. The device provided in this application embodiment also includes a monitoring terminal and voltage and current acquisition modules for the target process devices installed in the multiple process devices. The remote server communicates with the monitoring terminal, voltage acquisition module, and current acquisition module respectively via the IIoT. Figure 2 As shown, the system provided in this application embodiment includes an information receiving unit, a sub-energy consumption determination unit, an information receiving unit, a total energy consumption estimation unit, an information sending unit, an energy consumption effective utilization value determination unit, a judgment unit, a parameter update unit, and a parameter configuration unit, wherein,

[0086] The information receiving unit is used to receive the operating current of the target process equipment collected by the current acquisition module and the operating voltage of the target process equipment collected by the voltage acquisition module at each sampling time in the Nth cycle, where N is an integer greater than 2 and the initial value of N is 2.

[0087] The sub-energy consumption determination unit is used to determine the sub-energy consumption of the target process equipment based on the operating current, operating voltage, and operating duration of the Nth cycle of the target process equipment at each sampling time.

[0088] The information receiving unit is also used to receive, at the end of the Nth cycle, the type of the target product, the specifications of the target product, and the quantity of the target product produced by the production line in the Nth cycle from the monitoring terminal.

[0089] The total energy consumption prediction unit is used to input the type of the target product, the specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the sub-energy consumption of the target process equipment into a pre-trained first energy consumption prediction model configured with the Nth network parameters, so as to obtain the Nth estimated total energy consumption of each process equipment in the production line system. The first energy consumption prediction model is obtained by inputting multiple first training samples into the first neural network for training. Each first training sample includes the type of historical target product, the specifications of historical target product, the quantity of target product produced by the production line in the Nth cycle in history, the sub-energy consumption of the target process equipment in history, and the corresponding historical Nth actual total energy consumption of the production line system.

[0090] The information sending unit is used to send the Nth estimated total energy consumption of each process equipment in the production line system to the monitoring terminal for display.

[0091] The energy consumption effective utilization value determination unit is used to input the type of the target product, the specifications of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the estimated total energy consumption in the Nth cycle into a pre-trained energy consumption effective utilization value determination model to obtain the energy consumption effective utilization value of the production line system in the Nth cycle. The energy consumption effective utilization value determination model is trained by inputting multiple second training samples into a second neural network. Each second training sample includes the type of historical target product, the specifications of historical target product, the quantity of the target product produced by the production line in the Nth cycle in history, the actual total energy consumption of the production line system in the Nth cycle in history, and the corresponding expert-calibrated actual energy consumption effective utilization value of the production line system.

[0092] The judgment unit is used to determine whether the difference between the energy consumption effective utilization value of the Nth cycle and the energy consumption effective utilization value of the (N-1)th cycle is greater than a set difference threshold, wherein the type and specifications of the target product are the same for each cycle.

[0093] The parameter update unit is used to update the Nth working parameter of different process equipment within the preset working parameter range of different process equipment when the difference between the energy consumption effective utilization value of the Nth cycle and the energy consumption effective utilization value of the (N-1)th cycle is greater than the set difference threshold. The unit also increments the value of N by 1 and repeats the above steps 1-7. When different process equipment are working within the corresponding preset working parameter range, the target product produced by the production line system is qualified.

[0094] The parameter configuration unit is used to set the Nth working parameter corresponding to different process equipment as the default working parameter when the difference between the energy consumption effective utilization value of the Nth cycle and the energy consumption effective utilization value of the N-1th cycle is less than or equal to the set difference threshold, and to increment the value of N by 1, and repeat the above steps 1-5 until a stop monitoring command is received from the monitoring terminal.

[0095] In one possible implementation, the system provided in this application further includes:

[0096] The information acquisition unit is used to acquire multiple estimated total energy consumptions corresponding to the first M consecutive cycles with the same duration as the Nth cycle, where M is an integer greater than 2.

[0097] The dependency extraction unit is used to extract the time-series dependencies of multiple estimated total energy consumptions using a deep belief DBN network.

[0098] The change characteristic determination unit is used to determine the energy consumption change characteristics of multiple estimated total energy consumptions based on the time-series dependence of multiple estimated total energy consumptions.

[0099] The energy consumption prediction unit is used to determine the energy consumption prediction for the Nth period by using a pre-trained second energy consumption prediction model based on the energy consumption change characteristics of multiple corresponding predicted total energy consumptions in the previous M consecutive periods. The second energy consumption prediction model is obtained by inputting multiple third training samples into a third neural network for training. Each third training sample includes historical energy consumption change characteristics of multiple corresponding historical predicted total energy consumptions in the previous M consecutive periods with the same duration as the historical Nth period, as well as the corresponding historical energy consumption prediction for the historical Nth period.

[0100] The energy consumption correction unit is used to correct the estimated total energy consumption for the Nth cycle based on the estimated energy consumption for the Nth cycle.

[0101] In one possible implementation, the energy consumption correction unit is specifically used to correct the Nth estimated total energy consumption according to the formula P3 = k1P1 + k2P2, where P1 is the Nth estimated total energy consumption before correction, P2 is the energy consumption estimate for the Nth period, P3 is the Nth estimated total energy consumption after correction, k1 is the first weighting coefficient, k2 is the second weighting coefficient, and 0 <k2<k1<1,k1+k2=1。

[0102] In one possible implementation, the Nth network parameter is the state of the reinforcement learning model, updating the Nth network parameter is the action of the reinforcement learning model, and the energy efficiency value of the Nth cycle is the reward of the reinforcement learning model.

[0103] In one possible implementation, the information sending unit is further configured to send a prompt message to the monitoring terminal indicating high energy consumption when the Nth estimated total energy consumption is greater than a set energy consumption threshold.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. An energy consumption monitoring method based on industrial Internet of Things, characterized in that, The application is applied to an energy consumption monitoring device based on industrial internet of things, which is used for monitoring energy consumption of a production line system of a target product, the production line system comprises a plurality of different process equipment pre-configured with the Nth working parameter, and each process equipment is configured with different types of Nth working parameters, raw materials of the target product are processed by the process equipment configured with the corresponding Nth working parameter, and the target product is obtained, the device comprises a remote server, a monitoring terminal, and a voltage acquisition module and a current acquisition module arranged in the target process equipment of the plurality of process equipment, the remote server is in communication connection with the monitoring terminal, the voltage acquisition module, and the current acquisition module through industrial internet of things, and the method comprises: Step 1: the remote server receives the working current of the target process equipment collected by the current acquisition module and the working voltage of the target process equipment collected by the voltage acquisition module at each sampling time in the Nth cycle, wherein N is an integer greater than 2, and the initial value of N is 2; Step 2: the remote server determines the sub-energy consumption of the target process equipment according to the working current, working voltage of the target process equipment at each sampling time, and the working time length of the Nth cycle; Step 3: the remote server receives the type of the target product, the specification of the target product, and the number of the target product produced by the production line in the Nth cycle from the monitoring terminal at the end time of the Nth cycle; Step 4: the remote server inputs the type of the target product, the specification of the target product, the number of the target product produced by the production line in the Nth cycle, and the sub-energy consumption of the target process equipment into a pre-trained first energy consumption estimation model configured with the Nth network parameter to obtain the Nth estimated total energy consumption of each process equipment of the production line system, wherein the first energy consumption estimation model is obtained by inputting a plurality of first training samples into a first neural network, each first training sample comprises historical type of the target product, historical specification of the target product, historical number of the target product produced by the production line in the Nth cycle, historical sub-energy consumption of the target process equipment, and corresponding historical Nth actual total energy consumption of the production line system; wherein the first energy consumption estimation model utilizes the proportional relationship between the energy consumptions of a plurality of different process equipment in the process of obtaining the Nth estimated total energy consumption of each process equipment of the production line system; Step 5: the remote server sends the Nth estimated total energy consumption of each process equipment of the production line system to the monitoring terminal for display. Step 6: The remote server inputs the type of the target product, the specification of the target product, the number of the target product produced by the production line in the Nth cycle, and the Nth estimated total energy consumption into a pre-trained energy consumption effective utilization value determination model to obtain the energy consumption effective utilization value of the production line system in the Nth cycle, wherein the energy consumption effective utilization value determination model is trained by inputting a plurality of second training samples into a second neural network, each of the second training samples comprising a historical type of the target product, a historical specification of the target product, a historical number of the target product produced by the production line in the Nth cycle, a historical Nth actual total energy consumption of the production line system, and a corresponding expert-calibrated actual energy consumption effective utilization value of the production line system; Step 7: The remote server determines whether the difference between the energy consumption effective utilization value in the Nth cycle and the energy consumption effective utilization value in the (N-1)th cycle is greater than a set difference threshold, wherein the type of the target product and the specification of the target product are the same in each cycle; Step 8: When the difference between the energy consumption effective utilization value in the Nth cycle and the energy consumption effective utilization value in the (N-1)th cycle is greater than the set difference threshold, the remote server updates the Nth working parameter of each of the different process equipment in the corresponding preset working parameter range by using a pre-configured reinforcement learning model, and increases the value of N by 1, and repeats steps 1-7, wherein when the different process equipment works in the corresponding preset working parameter range, the target product produced by the production line system is qualified, the Nth network parameter is the state of the reinforcement learning model, updating the Nth network parameter is the action of the reinforcement learning model, and the energy consumption effective utilization value in the Nth cycle is the reward of the reinforcement learning model; Step 9: When the difference between the energy consumption effective utilization value in the Nth cycle and the energy consumption effective utilization value in the (N-1)th cycle is less than or equal to the set difference threshold, the remote server sets the Nth working parameter of each of the different process equipment as a default working parameter, increases the value of N by 1, and repeats steps 1-5 until a stop monitoring instruction from the monitoring terminal is received.

2. The method of claim 1, wherein, Before sending the Nth estimated total energy consumption of each process equipment of the production line system to the monitoring terminal for display, the method further comprises: The remote server acquires a plurality of recorded estimated total energy consumptions of the previous M cycles equal in length to the Nth cycle and continuous, wherein M is an integer greater than 2; extracting the time sequence dependency of the plurality of estimated total energy consumptions by using a deep belief DBN network; determining the energy consumption change characteristics of the plurality of estimated total energy consumptions according to the time sequence dependency of the plurality of estimated total energy consumptions; and The pre-trained second energy consumption estimation model is used to determine the energy consumption estimation amount of the Nth period according to the energy consumption change characteristics of the corresponding multiple estimated total energy consumptions of the continuous previous M periods; wherein the second energy consumption estimation model is obtained by inputting multiple third training samples into a third neural network for training, each third training sample includes historical energy consumption change characteristics of the corresponding multiple historical estimated total energy consumptions of the previous M periods which are equal in length to the historical Nth period, and a historical energy consumption estimation amount of the corresponding historical Nth period; The Nth estimated total energy consumption is corrected according to the energy consumption estimation amount of the Nth period.

3. The method of claim 2, wherein, The Nth estimated total energy consumption is corrected according to the energy consumption estimation amount of the Nth period. The remote server corrects the Nth estimated total energy consumption according to the formula P3=k1P1+k2P2, wherein P1 is the Nth estimated total energy consumption before correction, P2 is the energy consumption estimation amount of the Nth period, P3 is the Nth estimated total energy consumption after correction, k1 is the first weighting coefficient, k2 is the second weighting coefficient, and 0 4. The method according to any of claims 1 to 3, characterized in that, After obtaining the Nth estimated total energy consumption of each process equipment of the production line system, the method further comprises: If the Nth estimated total energy consumption is greater than the set energy consumption threshold, the remote server sends prompt information representing high energy consumption to the monitoring terminal.

5. An energy consumption monitoring system based on industrial internet of things, characterized in that, The remote server is configured in the remote server, and the remote server belongs to an energy consumption monitoring device based on industrial Internet of Things. The energy consumption monitoring device based on industrial Internet of Things is used to monitor the energy consumption of a production line system for producing a target product. The production line system includes multiple different process equipment preconfigured with the Nth working parameter, and each process equipment is configured with different types of Nth working parameters. The raw materials of the target product are processed by the process equipment configured with the corresponding Nth working parameter in turn to obtain the target product. The device further includes a monitoring terminal, a voltage acquisition module and a current acquisition module arranged in a target process equipment in the multiple process equipment. The remote server is communicatively connected with the monitoring terminal, the voltage acquisition module and the current acquisition module through industrial Internet of Things. The system comprises: The information receiving unit is configured to receive the working current of the target process equipment collected by the current acquisition module and the working voltage of the target process equipment collected by the voltage acquisition module at each sampling time in the Nth period, wherein N is an integer greater than 2, and the initial value of N is 2; The sub-energy consumption determination unit is configured to determine the sub-energy consumption of the target process equipment according to the working current and working voltage of the target process equipment at each sampling time and the working time length of the Nth period; The information receiving unit is further configured to receive the type of the target product, the specification of the target product and the number of the target product produced by the production line in the Nth period from the monitoring terminal at the end of the Nth period. a total energy consumption estimation unit, configured to input the type of the target product, the specification of the target product, the quantity of the target product produced by the production line in the Nth period, and the sub-energy consumption of the target process equipment into a first energy consumption estimation model pre-trained and configured with Nth network parameters, to obtain the Nth estimated total energy consumption of each process equipment of the production line system, wherein the first energy consumption estimation model is trained by inputting a plurality of first training samples into a first neural network, each of the first training samples comprising the type of the historical target product, the specification of the historical target product, the quantity of the historical target product produced by the production line in the Nth period, the sub-energy consumption of the historical target process equipment, and the corresponding Nth actual total energy consumption of the production line system, and wherein the first energy consumption estimation model utilizes the proportional relationship between the energy consumptions of a plurality of different process equipment in the process of obtaining the Nth estimated total energy consumption of each process equipment of the production line system; an information sending unit, configured to send the Nth estimated total energy consumption of each process equipment of the production line system to the monitoring terminal for display; an energy consumption effective utilization value determination unit, configured to input the type of the target product, the specification of the target product, the quantity of the target product produced by the production line in the Nth period, and the Nth estimated total energy consumption into a pre-trained energy consumption effective utilization value determination model, to obtain the energy consumption effective utilization value of the production line system in the Nth period, wherein the energy consumption effective utilization value determination model is trained by inputting a plurality of second training samples into a second neural network, each of the second training samples comprising the type of the historical target product, the specification of the historical target product, the quantity of the historical target product produced by the production line in the Nth period, the Nth actual total energy consumption of the production line system, and the corresponding expert-calibrated actual energy consumption effective utilization value of the production line system; a judgment unit, configured to judge whether the difference between the energy consumption effective utilization value of the Nth period and the energy consumption effective utilization value of the (N-1)th period is greater than a set difference threshold value, wherein the type of the target product and the specification of the target product are the same in each period. The parameter updating unit is configured to, in a case where the energy consumption effective utilization value of the Nth period and the energy consumption effective utilization value of the (N-1)th period have a difference greater than a set difference threshold value, update the Nth working parameter corresponding to each of the different process equipment in a preset working parameter range corresponding to each of the different process equipment by using a preconfigured reinforcement learning model, and increase the value of N by 1, and repeat the steps 1-7, wherein, in a case where the different process equipment works in the corresponding preset working parameter range, the target product produced by the production line system is qualified, the Nth network parameter is a state of the reinforcement learning model, the updating of the Nth network parameter is an action of the reinforcement learning model, and the energy consumption effective utilization value of the Nth period is a reward of the reinforcement learning model; The parameter configuration unit is configured to, in a case where the energy consumption effective utilization value of the Nth period and the energy consumption effective utilization value of the (N-1)th period have a difference less than or equal to a set difference threshold value, set the Nth working parameter corresponding to each of the different process equipment as a default working parameter, and increase the value of N by 1, and repeat the steps 1-5 until a stop monitoring instruction from the monitoring terminal is received.

6. The system of claim 5, wherein, The system further comprises: The information acquisition unit is configured to acquire a plurality of recorded estimated total energy consumptions corresponding to a plurality of continuous previous M periods with a length equal to that of the Nth period, wherein M is an integer greater than 2; The dependency relationship extraction unit is configured to extract a time sequence dependency relationship of the plurality of estimated total energy consumptions by using a deep belief DBN network. The change feature determination unit is configured to determine an energy consumption change feature of the plurality of estimated total energy consumptions according to the time sequence dependency relationship of the plurality of estimated total energy consumptions. The energy consumption estimation amount determination unit is configured to determine an energy consumption estimation amount of the Nth period according to the energy consumption change feature of the plurality of estimated total energy consumptions corresponding to the plurality of continuous previous M periods by using a pre-trained second energy consumption estimation model, wherein the second energy consumption estimation model is obtained by inputting a plurality of third training samples into a third neural network, and each of the third training samples includes a historical energy consumption change feature of a plurality of historical estimated total energy consumptions corresponding to a plurality of continuous previous M periods with a length equal to that of a historical Nth period and a historical energy consumption estimation amount of a corresponding historical Nth period. The energy consumption correction unit is configured to correct the Nth estimated total energy consumption according to the energy consumption estimation amount of the Nth period.

7. The system of claim 6, wherein, The energy consumption correction unit is specifically configured to correct the Nth estimated total energy consumption according to an algorithm P3=k1P1+k2P2, wherein P1 is the Nth estimated total energy consumption before correction, P2 is the energy consumption estimation amount of the Nth period, P3 is the Nth estimated total energy consumption after correction, k1 is a first weighting coefficient, k2 is a second weighting coefficient, and 0 8. The system of any of claims 5-7, wherein, The information sending unit is further configured to send prompt information for indicating that the energy consumption is high to the monitoring terminal in a case where the Nth estimated total energy consumption is greater than a set energy consumption threshold value.

Images