Energy consumption monitoring method and system based on industrial Internet of Things

Abstract

The invention 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 method comprises the following steps: inputting 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 period and the sub-energy consumption of target process equipment into a first energy consumption estimation model configured with an Nth network parameter to obtain the Nth estimated total energy consumption of each process equipment, the reliability of the obtained Nth estimated total energy consumption of each process device is high, the energy consumption of a production line system is monitored without depending on an electric meter, and the reinforcement learning model can continuously optimize the Nth working parameters corresponding to different process devices according to the obtained effective utilization value of the energy consumption. Under the condition that the quality of a produced target product is guaranteed to be qualified, the energy consumption of a production line system is the lowest, the energy consumption cost of an enterprise is saved, and energy conservation and environmental protection are achieved.

Description

Technical Field

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

[0002] In the era of Industry 4.0, the Industrial Internet of Things, as a product of the integration of new-generation information technology and manufacturing, interconnects the three elements of people, machines and objects through integrated intelligent perception, recognition and other communication perception technologies. By using the Industrial Internet of Things technology to monitor the energy consumption of the production line system used to produce target products (such as strip steel, diesel, gasoline or cartons, etc.), it can promote factories and enterprises to transform their energy consumption optimization management mode and help improve energy utilization.

[0003] At present, the energy consumption of production line systems can usually be monitored using electric meters. However, due to the complex structure of electric meters and the large number of electronic components (such as transformers, coils, etc.), they are easily corroded by the environment of the production line system (such as high temperature and humidity), resulting in damage to the electric meters, resulting in 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 consumption costs for enterprises and insufficient energy conservation and environmental protection. Summary of the invention

[0004] The present application provides an energy consumption monitoring method and system based on the industrial Internet of Things, which is used to solve the problem of poor reliability of energy consumption monitoring of production line systems in the prior art. Furthermore, the energy consumption of using the production line system to produce target products is high, resulting in high energy consumption costs for enterprises and insufficient energy conservation and environmental protection.

[0005] In a first aspect, the present application provides an energy consumption monitoring method based on the industrial Internet of Things, which is applied to an energy consumption monitoring device based on the industrial Internet of Things. The energy consumption monitoring device based on the industrial Internet of Things is used to monitor the energy consumption of a production line system that produces a target product. The production line system includes a plurality of different process equipment pre-configured with Nth working parameters, and each process equipment is configured with 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 a voltage acquisition module and a current acquisition module of the target process equipment arranged in the plurality of process equipment. The remote server is respectively connected to the monitoring terminal, the voltage acquisition module, and the current acquisition module through the industrial Internet of Things. The method provided by the present 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, wherein 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 according to the operating current, operating voltage, and operating duration of the Nth cycle of the target process equipment at each sampling moment;

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

[0009] Step 4: The remote server inputs the type of the target product, the specification of the target product, the number of target products 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 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 obtained by inputting multiple first training samples into the first neural network for training, and each first training sample includes the type of historical target products, the specification of historical target products, 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 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 of the production line system to the monitoring terminal for display;

[0011] Step 6: The remote server inputs the type of the target product, the specification of the target product, the number of target products produced by the production line in the Nth cycle, and the Nth estimated total energy consumption 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, wherein the energy consumption effective utilization value determination model is obtained by inputting multiple second training samples into the second neural network for training, and each second training sample includes the type of historical target products, the specification of historical target products, the number of target products produced by the production line in the Nth cycle in history, the Nth actual total energy consumption of the production line system in history, and the actual energy consumption effective utilization value of the production line system calibrated by the corresponding expert;

[0012] Step 7: The remote server determines whether the difference between the effective utilization value of energy consumption in the Nth cycle and the effective utilization value of energy consumption in the N-1th cycle is greater than a set difference threshold, wherein the type of the target product and the specification of the target product in each cycle are the same;

[0013] Step 8: When the difference between the effective utilization value of energy consumption in the Nth cycle and the effective utilization value of energy consumption in the N-1th cycle is greater than the set difference threshold, the remote server uses the preconfigured reinforcement learning model to update the Nth working parameters corresponding to different process equipment respectively within the preset working parameter ranges corresponding to different process equipment, and adds 1 to the value of N, and repeats the above steps 1 to 7, wherein when different process equipment works within the corresponding preset working parameter ranges, the target product produced by the production line system is qualified;

[0014] Step 9: When the difference between the effective utilization value of energy consumption in the Nth cycle and the effective utilization value of energy consumption in the N-1th cycle is less than or equal to the set difference threshold, the remote server sets the Nth working parameters corresponding to different process equipment as default working parameters, adds 1 to the value of N, and repeats the above steps 1 to 5 until receiving the stop monitoring instruction from the monitoring terminal.

[0015] In a possible implementation manner, 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 provided by the present application further includes:

[0016] The remote server obtains a plurality of estimated total energy consumptions corresponding to the first M consecutive cycles that are equal to the duration of the Nth cycle, where M is an integer greater than 2;

[0017] The deep belief DBN network is used to extract the temporal dependencies of multiple estimated total energy consumptions;

[0018] Determine energy consumption variation characteristics of the multiple estimated total energy consumptions according to the temporal dependencies of the multiple estimated total energy consumptions;

[0019] The energy consumption estimation amount of the Nth cycle is determined by using the pre-trained second energy consumption estimation model according to the energy consumption variation characteristics of the corresponding multiple estimated total energy consumptions of the consecutive first M cycles; wherein the second energy consumption estimation model is obtained by inputting multiple third training samples into the third neural network for training, and each third training sample includes the historical energy consumption variation characteristics of the corresponding multiple historical estimated total energy consumptions of the consecutive first M cycles that are equal to the duration of the historical Nth cycle and the corresponding historical energy consumption estimation amount of the historical Nth cycle;

[0020] According to the estimated energy consumption of the Nth cycle, the Nth estimated total energy consumption is corrected.

[0021] In a possible implementation, correcting the Nth estimated total energy consumption according to the estimated energy consumption of the Nth cycle includes:

[0022] The remote server uses the formula P 3 =k 1 P1 +k 2 P 2 , correct the Nth estimated total energy consumption, where P 1 is the Nth estimated total energy consumption before correction, P 2 is the estimated energy consumption of the Nth cycle, P 3 is the revised estimated total energy consumption of the Nth node, k 1 is the first weighting coefficient, k 2 is the second weighting coefficient, and 0 <k 2 <k 1 <1, k 1 +k 2 =1.

[0023] In a 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 effective utilization value of energy consumption in the Nth cycle is the reward of the reinforcement learning model.

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

[0025] When the Nth estimated total energy consumption is greater than a set energy consumption threshold, the remote server sends a prompt message indicating that the energy consumption is too high to the monitoring terminal.

[0026] In the second aspect, the present application also provides an energy consumption monitoring system based on the industrial Internet of Things, which is configured on a remote server. The remote server belongs to an energy consumption monitoring device based on the industrial Internet of Things. The energy consumption monitoring device based on the industrial Internet of Things is used to monitor the energy consumption of a production line system that produces a target product. The production line system includes a plurality of different process equipment pre-configured with Nth working parameters, and each process equipment is configured with 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 parameters to obtain the target product. The device also includes a monitoring terminal and a voltage acquisition module and a current acquisition module of the target process equipment arranged in the plurality of process equipment. The remote server is respectively connected to the monitoring terminal, the voltage acquisition module, and the current acquisition module through the industrial Internet of Things. The system provided by the present application includes:

[0027] An information receiving unit, used for receiving, at each sampling moment in the Nth cycle, the operating current of the target process equipment collected by the current collection module and the operating voltage of the target process equipment collected by the voltage collection module, wherein N is an integer greater than 2, and the initial value of N is 2;

[0028] A sub-energy consumption determination unit, used to determine the sub-energy consumption of the target process equipment according to the working current, working voltage and working duration of the Nth cycle of the target process equipment at each sampling moment;

[0029] The information receiving unit is further used to receive, at the end of the Nth cycle, the type of the target product, the specification 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] A total energy consumption estimation unit is used to input the type of target product, the specification of target product, the number of target products produced by the production line in the Nth cycle, and the sub-energy consumption of target process equipment into a pre-trained first energy consumption estimation model configured with an Nth network parameter, so as 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 the first neural network for training, each first training sample including the type of historical target product, the specification 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 target process equipment in history, and the corresponding Nth actual total energy consumption of the production line system in history;

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

[0032] An energy consumption effective utilization value determination unit, used for inputting the type of target product, the specification of target product, the number of target products 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, so as 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 obtained by inputting a plurality of second training samples into a second neural network for training, each second training sample including the type of historical target product, the specification of historical target product, the number of target products produced by the production line in the Nth cycle in history, the Nth actual total energy consumption of the production line system in history, and the actual energy consumption effective utilization value of the production line system calibrated by the corresponding expert;

[0033] A judging unit, used to judge whether the difference between the effective utilization value of energy consumption in the Nth cycle and the effective utilization value of energy consumption in the N-1th cycle is greater than a set difference threshold, wherein the type of target product and the specification of target product in each cycle are the same;

[0034] The parameter updating unit is used to update the Nth working parameters corresponding to different process equipment respectively within the preset working parameter ranges corresponding to different process equipment by using the preconfigured reinforcement learning model when the difference between the effective utilization value of energy consumption in the Nth cycle and the effective utilization value of energy consumption in the N-1th cycle is greater than the set difference threshold, and add 1 to the value of N, and repeatedly perform the above steps 1 to 7, wherein when different process equipment works within the corresponding preset working parameter ranges, the target product produced by the production line system is qualified;

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

[0036] In a possible implementation, the system provided by the present application further includes:

[0037] An information acquisition unit, used to acquire a plurality of estimated total energy consumptions corresponding to the first M consecutive cycles that are equal to the duration of the Nth cycle, where M is an integer greater than 2;

[0038] A dependency extraction unit, used to extract the temporal dependencies of multiple estimated total energy consumptions using a deep confidence DBN network;

[0039] a change characteristic determination unit, configured to determine energy consumption change characteristics of a plurality of estimated total energy consumptions according to a temporal dependency relationship between the plurality of estimated total energy consumptions;

[0040] An energy consumption estimation determination unit, configured to determine the energy consumption estimation of the Nth cycle by using a pre-trained second energy consumption estimation model according to energy consumption variation characteristics of a plurality of corresponding estimated total energy consumptions of the first M consecutive cycles; wherein the second energy consumption estimation model is obtained by inputting a plurality of third training samples into a third neural network for training, and each third training sample includes historical energy consumption variation characteristics of a plurality of corresponding historical estimated total energy consumptions of the first M consecutive cycles that are equal in length to the duration of the historical Nth cycle and the corresponding historical energy consumption estimation of the Nth cycle;

[0041] The energy consumption correction unit is used to correct the Nth estimated total energy consumption according to the estimated energy consumption of the Nth cycle.

[0042] In a possible implementation manner, the energy consumption correction unit is specifically configured to: 3 =k 1 P 1 +k 2 P2 , correct the Nth estimated total energy consumption, where P 1 is the Nth estimated total energy consumption before correction, P 2 is the estimated energy consumption of the Nth cycle, P 3 is the revised estimated total energy consumption of the Nth node, k 1 is the first weighting coefficient, k 2 is the second weighting coefficient, and 0 <k 2 <k 1 <1, k 1 +k 2 =1.

[0043] In a 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 effective utilization value of energy consumption in the Nth cycle is the reward of the reinforcement learning model.

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

[0045] The present application provides an energy consumption monitoring method and system based on the industrial Internet of Things, which can determine the sub-energy consumption of the target process equipment according to the working current, working voltage, and working time of the target process equipment at each sampling moment; the type of the target product, the specification of the target product, the number of target products produced by the production line in the Nth cycle, and the sub-energy consumption of the target process equipment are input into the pre-trained first energy consumption estimation model configured with the Nth network parameters to obtain the Nth estimated total energy consumption of each process equipment of the production line system. There is a certain regularity in the energy consumption between the production of multiple different process equipment (such as the existence of a corresponding ratio), and the energy consumption of each process equipment is related to the type of the target product, the specification of the target product, and the number of the target product. Therefore, through the above method, the reliability of the Nth estimated total energy consumption of each process equipment of the production line system is high, and it does not rely on the electric meter to monitor the energy consumption of the production line system, which further ensures the high reliability of the energy consumption monitoring of the production line system.

[0046] In addition, the type of target product, the specification of target product, the number of target products produced by the production line in the Nth cycle, and the Nth estimated total energy consumption are input 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, which has high reliability. In addition, the reinforcement learning model can continuously optimize the Nth working parameters corresponding to different process equipment according to the obtained energy consumption effective utilization value until the energy consumption effective utilization value of different process equipment is increased to a stable state. In this way, the energy consumption of the production line system can be minimized while ensuring the quality of the target products produced, saving the energy consumption cost of the enterprise and being energy-saving and environmentally friendly. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] Figure 1 A flowchart of an energy consumption monitoring method based on industrial Internet of Things provided in an embodiment of the present application;

[0049] Figure 2 A functional module block diagram of an energy consumption monitoring system based on industrial Internet of Things provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments made by ordinary technicians in this field under the enlightenment of the embodiments belong to the scope of protection of the present application.

[0051] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0052] The embodiment of the present application provides an energy consumption monitoring method based on the industrial Internet of Things, which is applied to an energy consumption monitoring device based on the industrial Internet of Things. The energy consumption monitoring device based on the 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 a plurality of different process equipment pre-configured with Nth working parameters, and each process equipment is configured with a different type of Nth working parameter. The raw materials of the target product are processed in sequence by the process equipment configured with the corresponding Nth working 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 blast furnace gas as a heating medium, and a heating device for heating qualified continuous casting billets to a target temperature (such as 1200°C), a descaling device for removing iron oxide scale on the surface of the billet using high-pressure water, a roughing mill for rolling the billet multiple times, a finishing mill for finishing the strip steel after rough rolling, and a laminar cooling device for cooling the strip steel. Different types of working parameters of multiple process equipment may include the target temperature of heating equipment, the water pressure of high-pressure water of the descaling equipment, the working power of the roughing mill, the working power of the finishing mill, the cooling temperature of the laminar cooling device, etc. For 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 a crude gasoline tower, an absorption tower, an air compressor, a condensed oil tank, a stabilization tower, and other equipment.

[0054] Furthermore, the energy consumption monitoring device based on the industrial Internet of Things includes a remote server, a monitoring terminal, and a voltage acquisition module and a current acquisition module of a target process device arranged in a plurality of process devices. The remote server is respectively connected to the monitoring terminal, the voltage acquisition module, and the current acquisition module through the industrial Internet of Things. Figure 1 As shown, the method provided in the embodiment of the present application 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 moment 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 according to the operating current, the operating voltage, and the operating duration of the Nth cycle of the target process equipment at each sampling moment.

[0057] For example, the working current and working voltage of the target process equipment at each sampling moment can be used to determine the power at the corresponding sampling moment. The power and working time at each sampling moment are integrated to determine the sub-energy consumption of the target process equipment. The target process equipment can be the most stable equipment among multiple process equipment.

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

[0059] S104: The remote server inputs the type of target product, the specification 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 estimation model configured with the Nth network parameters to obtain the Nth estimated total energy consumption of each process equipment of the production line system.

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

[0061] S105: 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.

[0062] S106: The remote server inputs the type of target product, the specification of the target product, the quantity of the target product produced by the production line in the Nth cycle, and the Nth estimated total energy consumption 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.

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

[0064] Exemplarily, the energy consumption effective utilization value may be understood as, but not limited to, data showing a positive correlation between the ratio of the minimum energy consumption required to produce target products of target type, target specification, 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 a set difference threshold. If yes, execute S108; if not, execute S109.

[0066] Among them, the type of target product and the specification of target product in each cycle are the same.

[0067] S108: The remote server uses a preconfigured reinforcement learning model to update the Nth working parameters corresponding to different process equipment within the preset working parameter ranges corresponding to different process equipment, and adds 1 to the value of N, and repeats the above S101-S107.

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

[0069] It can be understood that multiple process equipment may have multiple different types of operating parameter combinations, and in order to produce qualified target products of target type, target specification, and target quantity, an operating parameter combination that minimizes the energy consumption of the production line system can be selected.

[0070] Among them, when different process equipment works within 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 effective utilization value of energy consumption in the Nth cycle is the reward of the reinforcement learning model.

[0071] S109: The remote server sets the Nth working parameters corresponding to different process equipment as default working parameters, adds 1 to the value of N, and does not receive a stop monitoring instruction from the monitoring terminal, and repeats the above S101-S105.

[0072] In summary, the embodiment of the present application provides an energy consumption monitoring method based on the industrial Internet of Things, which can determine the sub-energy consumption of the target process equipment according to the working current, working voltage, and working time of the target process equipment at each sampling moment, and the sub-energy consumption of the target process equipment; the type of the target product, the specification of the target product, the number of target products produced by the production line in the Nth cycle, and the sub-energy consumption of the target process equipment are input into the pre-trained first energy consumption estimation model configured with the Nth network parameters to obtain the Nth estimated total energy consumption of each process equipment of the production line system. There is a certain regularity in the energy consumption between the production of multiple different process equipment (such as the existence of a corresponding ratio), and the energy consumption of each process equipment is related to the type of the target product, the specification of the target product, and the number of the target product. Therefore, through the above method, the reliability of the Nth estimated total energy consumption of each process equipment of the production line system is high, and it does not rely on the electric meter to monitor the energy consumption of the production line system, which further ensures the high reliability of the energy consumption monitoring of the production line system.

[0073] In addition, the type of target product, the specification of target product, the number of target products produced by the production line in the Nth cycle, and the Nth estimated total energy consumption are input 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, which has high reliability. In addition, the reinforcement learning model can continuously optimize the Nth working parameters corresponding to different process equipment according to the obtained energy consumption effective utilization value until the energy consumption effective utilization value of different process equipment is increased to a stable state. In this way, the energy consumption of the production line system can be minimized while ensuring the quality of the target products produced, saving the energy consumption cost of the enterprise and being energy-saving and environmentally friendly.

[0074] In a possible implementation manner, before S105, the method provided in the embodiment of the present application further includes:

[0075] Step A: The remote server obtains a plurality of estimated total energy consumptions corresponding to the first M consecutive cycles of equal duration to the Nth cycle, where M is an integer greater than 2. For example, M may be equal to 3, 4, 5, etc., which is not limited here.

[0076] Step B: Use the deep belief DBN network to extract the temporal dependencies of multiple estimated total energy consumption.

[0077] Step C: determining energy consumption variation characteristics of the multiple estimated total energy consumptions according to the temporal dependencies of the multiple estimated total energy consumptions.

[0078] Step D: using the pre-trained second energy consumption estimation model to determine the estimated energy consumption of the Nth cycle according to the energy consumption variation characteristics of the corresponding multiple estimated total energy consumptions of the first M consecutive cycles.

[0079] Among them, the second energy consumption estimation model is obtained by inputting multiple third training samples into the third neural network for training, and each third training sample includes historical energy consumption change characteristics of multiple historical estimated total energy consumption corresponding to the first M consecutive periods that are equal to the duration of the historical Nth period and the corresponding historical energy consumption estimated amount of the historical Nth period.

[0080] Step E: According to the estimated energy consumption of the Nth cycle, the Nth estimated total energy consumption is corrected.

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

[0082] Step E can be implemented as follows: the remote server calculates the 3 =k 1 P 1 +k 2 P 2 , correct the Nth estimated total energy consumption. Among them, P 1 is the Nth estimated total energy consumption before correction, P 2 is the estimated energy consumption of the Nth cycle, P 3 is the revised estimated total energy consumption of the Nth node, k 1 is the first weighting coefficient, k 2 is the second weighting coefficient, and 0 <k 2 <k 1 <1, k 1 +k 2 = 1. For example, k 1 =0.7, k 2 =0.3; or, k 1 =0.8, k 2 =0.2.

[0083] In a possible implementation, after S104, the method provided in the embodiment of the present application also includes the remote server sending a prompt message for indicating high energy consumption to the monitoring terminal when the Nth estimated total energy consumption is greater than a set energy consumption threshold, so as to enable monitoring personnel to perceive it.

[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 a remote server. It should be noted that the basic principle and technical effects of the energy consumption monitoring system based on the industrial Internet of Things provided in the embodiment of the present application are the same as those in 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 contents in the above embodiment.

[0085] The remote server belongs to an energy consumption monitoring device based on the Industrial Internet of Things. The energy consumption monitoring device based on the Industrial Internet of Things is used to monitor the energy consumption of the production line system that produces the target product. The production line system includes a plurality of different process equipment pre-configured with Nth working parameters, and each process equipment is configured with 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 provided in the embodiment of the present application also includes a monitoring terminal and a voltage acquisition module and a current acquisition module of a target process equipment arranged in the plurality of process equipment. The remote server is respectively connected to the monitoring terminal, the voltage acquisition module, and the current acquisition module through the Industrial Internet of Things. Figure 2 As shown, the system provided in the embodiment of the present application 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 updating unit, and a parameter configuration unit, wherein:

[0086] The information receiving unit is used to receive the working current of the target process equipment collected by the current collection module and the working voltage of the target process equipment collected by the voltage collection module at each sampling moment in the Nth cycle, wherein 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 according to the working current, working voltage and working duration of the Nth cycle of the target process equipment at each sampling moment.

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

[0089] The total energy consumption estimation unit is used to input the type of target product, the specification of target product, the number of target products produced by the production line in the Nth cycle, and the sub-energy consumption of target process equipment into a pre-trained first energy consumption estimation model 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 obtained by inputting multiple first training samples into the first neural network for training, and each first training sample includes the type of historical target product, the specification 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 target process equipment in history, and the corresponding Nth actual total energy consumption of the production line system in history.

[0090] The information sending unit is used to send the Nth estimated total energy consumption of each process equipment of 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 target product, the specification of target product, the number of target products 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 obtained by inputting multiple second training samples into the second neural network for training, and each second training sample includes the type of historical target product, the specification of historical target product, the number of target products produced by the production line in the Nth cycle in history, the Nth actual total energy consumption of the production line system in history, and the actual energy consumption effective utilization value of the production line system calibrated by the corresponding expert.

[0092] The judging unit is used to judge 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 a set difference threshold, wherein the type and specification of the target product of each cycle are the same.

[0093] The parameter updating unit is used to update the Nth working parameters corresponding to different process equipment respectively within the preset working parameter ranges corresponding to different process equipment using the preconfigured reinforcement learning model when the difference between the effective utilization value of energy consumption in the Nth cycle and the effective utilization value of energy consumption in the N-1th cycle is greater than the set difference threshold, and add 1 to the value of N, and repeat the above steps 1 to 7, wherein when different process equipment operates within the corresponding preset working parameter ranges, the target products produced by the production line system are qualified.

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

[0095] In a possible implementation, the system provided by the present application further includes:

[0096] The information acquisition unit is used to acquire a plurality of estimated total energy consumptions corresponding to the first M consecutive cycles that are equal in length to the Nth cycle, where M is an integer greater than 2.

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

[0098] The change characteristic determination unit is used to determine the energy consumption change characteristics of multiple estimated total energy consumptions according to the time sequence dependencies of the multiple estimated total energy consumptions.

[0099] An energy consumption estimate determination unit is used to determine the energy consumption estimate of the Nth cycle based on the energy consumption change characteristics of the corresponding multiple estimated total energy consumptions of the previous M consecutive cycles using a pre-trained second energy consumption estimation model; wherein the second energy consumption estimation model is obtained by inputting multiple third training samples into a third neural network for training, and each third training sample includes historical energy consumption change characteristics of multiple historical estimated total energy consumptions corresponding to the previous M consecutive cycles that are equal to the duration of the historical Nth cycle and the corresponding historical energy consumption estimate of the historical Nth cycle.

[0100] The energy consumption correction unit is used to correct the Nth estimated total energy consumption according to the estimated energy consumption of the Nth cycle.

[0101] In a possible implementation manner, the energy consumption correction unit is specifically configured to: 3 =k 1 P 1 +k 2 P 2 , correct the Nth estimated total energy consumption, where P 1 is the Nth estimated total energy consumption before correction, P 2 is the estimated energy consumption of the Nth cycle, P 3 is the revised estimated total energy consumption of the Nth node, k 1 is the first weighting coefficient, k 2 is the second weighting coefficient, and 0 <k 2 <k 1 <1, k 1 +k 2 =1.

[0102] In a 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 effective utilization value of energy consumption in the Nth cycle is the reward of the reinforcement learning model.

[0103] In a possible implementation manner, the information sending unit is further configured to send a prompt message indicating that the energy consumption is high to the monitoring terminal 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 the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An energy consumption monitoring method based on industrial Internet of Things, characterized in that: An energy consumption monitoring device based on the industrial Internet of Things is applied to monitor the energy consumption of a production line system for producing a target product. The production line system includes a plurality of different process equipment pre-configured with Nth working parameters, and each of the process equipment is configured with 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 a voltage acquisition module and a current acquisition module of a target process equipment arranged in the plurality of the process equipment. The remote server is respectively connected to the monitoring terminal, the voltage acquisition module, and the current acquisition module through the industrial Internet of Things. The method includes: 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, 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, and working duration of the Nth cycle of the target process equipment at each sampling moment; Step 3: At the end of the Nth cycle, the remote server receives from the monitoring terminal the type of the target product, the specification of the target product, and the quantity of the target product produced by the production line in the Nth cycle; Step 4: The remote server inputs 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 cycle, and the sub-energy consumption of the target process equipment into a pre-trained first energy consumption estimation model configured with an 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 for training, each of the first training samples including the historical type of the target product, the historical specification of the target product, the historical quantity of the target product produced by the production line in the Nth cycle, the historical sub-energy consumption of the target process equipment, and the corresponding historical Nth actual total energy consumption 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 quantity 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 obtained by inputting a plurality of second training samples into a second neural network for training, each of the second training samples including the historical type of the target product, the historical specification of the target product, the historical quantity of the target product produced by the production line in the Nth cycle, the historical Nth actual total energy consumption of the production line system, and the actual energy consumption effective utilization value of the production line system calibrated by the corresponding expert; Step 7: The remote server determines whether the difference between the effective utilization value of the energy consumption in the Nth cycle and the effective utilization value of the energy consumption in the N-1th cycle is greater than a set difference threshold, wherein the type of the target product in each cycle is the same as the specification of the target product; Step 8: When the difference between the effective utilization value of energy consumption in the Nth cycle and the effective utilization value of energy consumption in the N-1th cycle is greater than the set difference threshold, the remote server uses the preconfigured reinforcement learning model to update the Nth working parameters corresponding to the different process equipment respectively within the preset working parameter ranges corresponding to the different process equipment, and adds 1 to the value of N, and repeats the above steps 1 to 7, wherein when the different process equipment operates within the corresponding preset working parameter ranges, the target product produced by the production line system is qualified; Step 9: When the difference between the effective utilization value of the energy consumption in the Nth cycle and the effective utilization value of the energy consumption in the N-1th cycle is less than or equal to the set difference threshold, the remote server sets the Nth working parameters corresponding to the different process equipment as default working parameters, adds 1 to the value of N, and repeats the above steps 1 to 5 until receiving a stop monitoring instruction from the monitoring terminal.

2. The method according to claim 1, characterized in that 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 includes: The remote server obtains a plurality of estimated total energy consumptions corresponding to the first M consecutive cycles that are equal to the duration of the Nth cycle, where M is an integer greater than 2; The deep belief DBN network is used to extract the temporal dependencies of multiple estimated total energy consumptions; Determining energy consumption variation characteristics of the plurality of estimated total energy consumptions according to the temporal dependencies of the plurality of estimated total energy consumptions; The energy consumption estimation amount of the Nth cycle is determined by using a pre-trained second energy consumption estimation model according to the energy consumption change characteristics of the corresponding multiple estimated total energy consumptions of the consecutive first M cycles; wherein the second energy consumption estimation model is obtained by inputting multiple third training samples into a third neural network for training, and each of the third training samples includes historical energy consumption change characteristics of multiple historical estimated total energy consumptions corresponding to the consecutive first M cycles that are equal to the duration of the historical Nth cycle and the corresponding historical energy consumption estimation amount of the historical Nth cycle; The Nth estimated total energy consumption is corrected according to the estimated energy consumption of the Nth cycle.

3. The method according to claim 2, characterized in that The step of correcting the Nth estimated total energy consumption according to the estimated energy consumption of the Nth cycle includes: 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 estimated energy consumption of the Nth cycle, 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。 4. The method according to claim 1, characterized in that: 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 of the Nth cycle is the reward of the reinforcement learning model.

5. The method according to any one of claims 1 to 4, characterized in that: After obtaining the Nth estimated total energy consumption of each process equipment of the production line system, the method further includes: When the Nth estimated total energy consumption is greater than a set energy consumption threshold, the remote server sends a prompt message indicating that the energy consumption is high to the monitoring terminal.

6. An energy consumption monitoring system based on industrial Internet of Things, characterized in that: The device is configured on a remote server, the remote server belongs to an energy consumption monitoring device based on the industrial Internet of Things, the energy consumption monitoring device based on the 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 a plurality of different process equipment pre-configured with Nth working parameters, and each of the process equipment is configured with 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 also includes a monitoring terminal and a voltage acquisition module and a current acquisition module of a target process equipment arranged in the plurality of the process equipment, the remote server is respectively connected to the monitoring terminal, the voltage acquisition module, and the current acquisition module through the industrial Internet of Things, and the system includes: an information receiving unit, configured to receive, at each sampling moment in an Nth cycle, the operating current of the target process equipment collected by the current collection module and the operating voltage of the target process equipment collected by the voltage collection module, wherein N is an integer greater than 2, and an initial value of N is 2; A sub-energy consumption determination unit, configured to determine the sub-energy consumption of the target process equipment according to the operating current, the operating voltage, and the operating duration of the Nth cycle of the target process equipment at each sampling moment; The information receiving unit is further configured to receive, at the end of the Nth cycle, from the monitoring terminal the type of the target product, the specification of the target product, and the quantity of the target product produced by the production line in the Nth cycle; A total energy consumption estimation unit is used to input 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 an Nth network parameter, so as 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 for training, each of the first training samples including the historical type of the target product, the historical specification of the target product, the historical number of the target product produced by the production line in the Nth cycle, the historical sub-energy consumption of the target process equipment, and the corresponding historical Nth actual total energy consumption of the production line system; An information sending unit, used for sending 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, used for inputting 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 cycle, and the Nth estimated total energy consumption into a pre-trained energy consumption effective utilization value determination model, so as 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 obtained by inputting a plurality of second training samples into a second neural network for training, each of the second training samples including the historical type of the target product, the historical specification of the target product, the historical quantity of the target product produced by the production line in the Nth cycle, the historical Nth actual total energy consumption of the production line system, and the actual energy consumption effective utilization value of the production line system calibrated by the corresponding expert; A judging unit, used to judge whether the difference between the effective utilization value of energy consumption in the Nth cycle and the effective utilization value of energy consumption in the N-1th cycle is greater than a set difference threshold, wherein the type of the target product in each cycle is the same as the specification of the target product; A parameter updating unit is used for, when the difference between the effective utilization value of energy consumption in the Nth cycle and the effective utilization value of energy consumption in the N-1th cycle is greater than a set difference threshold, using a preconfigured reinforcement learning model to update the Nth working parameters corresponding to the different process equipment respectively within the preset working parameter ranges corresponding to the different process equipment, and adding 1 to the value of N, and repeatedly performing the above steps 1 to 7, wherein when the different process equipment operates within the corresponding preset working parameter ranges, the target product produced by the production line system is qualified; A parameter configuration unit is used to set the Nth working parameters corresponding to the different process equipment as default working parameters 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 add 1 to the value of N, and repeat the above steps 1 to 5 until a stop monitoring instruction is received from the monitoring terminal.

7. The system according to claim 6, characterized in that The system further comprises: An information acquisition unit, configured to acquire a plurality of estimated total energy consumptions corresponding to the first M consecutive cycles of equal duration to the Nth cycle, where M is an integer greater than 2; A dependency extraction unit, used to extract the temporal dependencies of multiple estimated total energy consumptions using a deep confidence DBN network; a change characteristic determination unit, configured to determine energy consumption change characteristics of a plurality of estimated total energy consumptions according to a temporal dependency relationship between the plurality of estimated total energy consumptions; An energy consumption estimation determination unit, configured to determine the energy consumption estimation of the Nth period by using a pre-trained second energy consumption estimation model according to energy consumption variation characteristics of a plurality of corresponding estimated total energy consumptions of the first M consecutive periods; wherein the second energy consumption estimation model is obtained by inputting a plurality of third training samples into a third neural network for training, and each of the third training samples includes historical energy consumption variation characteristics of a plurality of corresponding historical estimated total energy consumptions of the first M consecutive periods that are equal to the duration of the historical Nth period and correspond to the historical energy consumption estimation of the corresponding historical Nth period; The energy consumption correction unit is used to correct the Nth estimated total energy consumption according to the estimated energy consumption of the Nth cycle.

8. The system according to claim 7, characterized in that The energy consumption correction unit is specifically used to correct 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 estimated energy consumption of the Nth cycle, 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。 9. The system according to claim 6, characterized in that 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 of the Nth cycle is the reward of the reinforcement learning model.

10. The system according to any one of claims 6 to 9, characterized in that: The information sending unit is further configured to send a prompt message indicating that the energy consumption is high to the monitoring terminal when the Nth estimated total energy consumption is greater than a set energy consumption threshold.

Images