Smart factory energy consumption supervision method and system

Abstract

The invention is suitable for the technical field of smart factories, and provides a smart factory energy consumption supervision method and system. According to the invention, factory supervision data are acquired, and equipment energy consumption data of a plurality of energy consumption supervision equipment are acquired through a direct wireless and auxiliary wired communication mode; generating a plurality of marked energy consumption data; importing the abnormal data into a supervision detection model, and exporting an abnormal detection result; and when the energy consumption is abnormal, determining equipment with abnormal energy consumption, alarming the abnormal energy consumption, and performing remote consumption reduction control. Through a direct wireless and auxiliary wired communication mode, equipment energy consumption data of multiple pieces of energy consumption supervision equipment can be periodically collected, data processing is carried out, the data are imported into a supervision detection model, anomaly detection is carried out, when energy consumption anomaly exists, energy consumption anomaly equipment is determined, energy consumption anomaly alarm is carried out, and remote consumption reduction control is carried out. Auxiliary cooperation of wireless communication and wired communication can be achieved, and therefore it is ensured that energy consumption data of all energy consumption supervision devices can be comprehensively obtained.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart factories, and in particular, relates to a method and system for monitoring energy consumption in smart factories. Background Art

[0002] A smart factory refers to a modern factory that achieves highly automated, intelligent and networked manufacturing processes through highly integrated cyber-physical systems and IoT technologies. Energy consumption supervision in a smart factory refers to the use of information technology and IoT technologies to monitor, manage and optimize energy usage within the factory to achieve energy conservation and emission reduction.

[0003] Since there are many types of equipment that need to be energy-monitored in smart factories, and some of the multiple devices are connected by wired communication, in the existing technology, wireless communication collection of energy consumption data is usually carried out through the Internet of Things technology. Due to the instability of wireless transmission, it is easy to cause the loss of energy consumption data collection, and it cannot ensure that the energy consumption data of all equipment can be fully obtained. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method and system for monitoring energy consumption in a smart factory, aiming to solve the technical problems existing in the prior art mentioned in the background technology.

[0005] The embodiment of the present invention is implemented as follows:

[0006] A method for monitoring energy consumption in a smart factory, the method comprising the following steps:

[0007] Obtain factory supervision data, determine multiple energy consumption supervision devices, and periodically collect equipment energy consumption data of the multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods;

[0008] Performing data verification, data cleaning, data conversion and data labeling processing on the energy consumption data of the plurality of devices to generate a plurality of labeled energy consumption data;

[0009] Selecting a supervision detection model, importing a plurality of the labeled energy consumption data into the supervision detection model, performing anomaly detection, and exporting anomaly detection results;

[0010] According to the abnormality detection result, when there is energy consumption abnormality, energy consumption abnormality equipment is determined, energy consumption abnormality alarm is issued, and energy consumption abnormality equipment is remotely controlled to reduce energy consumption.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the obtaining of factory supervision data, determining multiple energy consumption supervision devices, and periodically collecting the device energy consumption data of multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods specifically include the following steps:

[0012] Obtain factory regulatory data;

[0013] Performing object recognition on the factory monitoring data to determine a plurality of energy consumption monitoring devices;

[0014] Periodically generate and wirelessly send energy consumption collection instructions to multiple energy consumption monitoring devices;

[0015] receiving a plurality of first energy consumption data;

[0016] Based on the preset basic device address and device interconnection information, multiple first energy consumption data are fed back and identified, and multiple disconnected monitoring devices and multiple auxiliary monitoring devices are marked;

[0017] Through the plurality of auxiliary monitoring devices, the second energy consumption data of the plurality of lost monitoring devices are obtained by wired assistance.

[0018] As a further limitation of the technical solution of the embodiment of the present invention, the feedback identification of the plurality of the first energy consumption data based on the preset basic device address and device interconnection information, and marking the plurality of lost-connection monitoring devices and the plurality of auxiliary monitoring devices specifically include the following steps:

[0019] Performing feedback identification on the plurality of the first energy consumption data, and determining a plurality of feedback identification addresses;

[0020] Based on the preset basic device address, address matching is performed on the multiple feedback identification addresses, and the address matching results are recorded;

[0021] According to the address matching result, the plurality of energy consumption monitoring devices are divided into a plurality of connected monitoring devices and a plurality of disconnected monitoring devices;

[0022] Based on the preset device interconnection information, performing wired interconnection analysis on the plurality of connected supervision devices and the plurality of disconnected supervision devices, and recording the interconnection analysis results;

[0023] According to the interconnection analysis result, auxiliary supervision devices corresponding to the multiple disconnected supervision devices are selected from the multiple connected supervision devices.

[0024] As a further limitation of the technical solution of the embodiment of the present invention, the wired auxiliary acquisition of the second energy consumption data of the plurality of lost monitoring devices through the plurality of auxiliary monitoring devices specifically includes the following steps:

[0025] Generate and wirelessly send auxiliary collection instructions to multiple auxiliary monitoring devices;

[0026] Through the plurality of auxiliary monitoring devices, the plurality of auxiliary collection instructions are forwarded to the plurality of corresponding lost-connection monitoring devices via wire;

[0027] The second energy consumption data transmitted as feedback by the plurality of disconnected supervision devices is received through the plurality of auxiliary supervision devices.

[0028] As a further limitation of the technical solution of the embodiment of the present invention, the data verification, data cleaning, data conversion and data labeling processing of the multiple energy consumption data of the devices to generate multiple labeled energy consumption data specifically includes the following steps:

[0029] Verifying and processing the data validity of a plurality of energy consumption data of the devices to obtain a plurality of valid energy consumption data;

[0030] Performing data cleaning processing of missing filling on the plurality of effective energy consumption data to obtain a plurality of cleaning energy consumption data;

[0031] Converting the plurality of cleaning energy consumption data into a unified format to obtain a plurality of standard energy consumption data;

[0032] A plurality of standard energy consumption data are labeled to obtain a plurality of labeled energy consumption data.

[0033] As a further limitation of the technical solution of the embodiment of the present invention, the selecting of the supervision detection model, importing the plurality of the labeled energy consumption data into the supervision detection model, performing anomaly detection, and exporting the anomaly detection results specifically include the following steps:

[0034] Select a supervision detection model from multiple preset basic detection models;

[0035] Importing a plurality of the annotated energy consumption data into the supervision and detection model;

[0036] By using the supervision detection model, anomaly detection is performed on the plurality of labeled energy consumption data;

[0037] Export anomaly detection results.

[0038] As a further limitation of the technical solution of the embodiment of the present invention, the determining of energy consumption abnormality equipment according to the abnormality detection result, issuing an energy consumption abnormality alarm, and remotely reducing the energy consumption of the energy consumption abnormal equipment specifically includes the following steps:

[0039] According to the abnormality detection result, determining whether there is energy consumption abnormality;

[0040] When there is an energy consumption anomaly, selecting the abnormal energy consumption data from the plurality of annotated energy consumption data;

[0041] Determine the abnormal energy consumption device according to the abnormal energy consumption data;

[0042] According to the abnormal energy consumption equipment, an abnormal energy consumption alarm is issued;

[0043] The energy consumption adjustment strategy is matched to remotely control the energy consumption reduction of the abnormal energy consumption equipment.

[0044] A smart factory energy consumption monitoring system, the system includes an energy consumption data acquisition module, an energy consumption data processing module, a model anomaly detection module and an energy consumption anomaly processing module, wherein:

[0045] An energy consumption data collection module is used to obtain factory supervision data, determine multiple energy consumption supervision devices, and periodically collect equipment energy consumption data of multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods;

[0046] An energy consumption data processing module, used for performing data verification, data cleaning, data conversion and data labeling processing on a plurality of energy consumption data of the devices, and generating a plurality of labeled energy consumption data;

[0047] A model anomaly detection module, used for selecting a supervision detection model, importing a plurality of the labeled energy consumption data into the supervision detection model, performing anomaly detection, and exporting anomaly detection results;

[0048] The energy consumption anomaly processing module is used to determine the energy consumption anomaly equipment according to the anomaly detection result, issue an energy consumption anomaly alarm, and remotely control the energy consumption anomaly equipment to reduce energy consumption.

[0049] As a further limitation of the technical solution of the embodiment of the present invention, the energy consumption data collection module specifically includes:

[0050] A data acquisition unit, used to acquire factory supervision data;

[0051] An object identification unit, used to perform object identification on the factory supervision data to determine a plurality of energy consumption supervision devices;

[0052] A wireless sending unit, used for periodically generating and wirelessly sending energy consumption collection instructions to multiple energy consumption monitoring devices;

[0053] A data receiving unit, used for receiving a plurality of first energy consumption data;

[0054] A feedback identification unit, configured to perform feedback identification on a plurality of the first energy consumption data based on a preset basic device address and device interconnection information, and mark a plurality of lost-connection monitoring devices and a plurality of auxiliary monitoring devices;

[0055] The wired auxiliary unit is used to obtain the second energy consumption data of the multiple lost monitoring devices through the wired auxiliary monitoring devices.

[0056] As a further limitation of the technical solution of the embodiment of the present invention, the energy consumption abnormality processing module specifically includes:

[0057] An abnormality judgment unit, used for judging whether there is an energy consumption abnormality according to the abnormality detection result;

[0058] A data selection unit, used for selecting abnormal energy consumption data from a plurality of annotated energy consumption data when there is abnormal energy consumption;

[0059] A device determining unit, configured to determine a device with abnormal energy consumption according to the abnormal energy consumption data;

[0060] An abnormal alarm unit, used for alarming abnormal energy consumption according to the abnormal energy consumption equipment;

[0061] The consumption reduction control unit is used to match the energy consumption adjustment strategy and perform remote consumption reduction control on the energy consumption abnormal device.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] The embodiment of the present invention acquires factory supervision data, collects equipment energy consumption data of multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods; generates multiple labeled energy consumption data; imports them into the supervision detection model, and exports abnormality detection results; when there is energy consumption abnormality, determines the energy consumption abnormal equipment, issues an energy consumption abnormality alarm, and performs remote energy consumption reduction control. The equipment energy consumption data of multiple energy consumption supervision devices can be periodically collected through direct wireless and auxiliary wired communication methods, data processing is performed, and the data is imported into the supervision detection model for abnormality detection. When there is energy consumption abnormality, the energy consumption abnormal equipment is determined, an energy consumption abnormality alarm is issued, and remote energy consumption reduction control is performed. The auxiliary coordination of wireless communication and wired communication can be realized, thereby ensuring that the energy consumption data of all energy consumption supervision devices can be fully acquired. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A flow chart of a smart factory energy consumption monitoring method provided by an embodiment of the present invention is shown;

[0065] Figure 2 A flow chart showing the method for collecting device energy consumption data in an embodiment of the present invention is shown;

[0066] Figure 3 A flow chart showing energy consumption data feedback identification in the method provided by an embodiment of the present invention is shown;

[0067] Figure 4 A flowchart of wired assistance for data collection in a method provided by an embodiment of the present invention is shown;

[0068] Figure 5 A flow chart showing the processing of device energy consumption data in the method provided by an embodiment of the present invention;

[0069] Figure 6A flowchart of deriving anomaly detection results in the method provided in an embodiment of the present invention is shown;

[0070] Figure 7 A flow chart showing abnormal energy consumption alarm and remote energy consumption reduction control in the method provided by an embodiment of the present invention is shown;

[0071] Figure 8 The application architecture diagram of the smart factory energy consumption monitoring system provided by the embodiment of the present invention is shown;

[0072] Fig. 9 An application architecture diagram of an energy consumption data acquisition module in a system provided by an embodiment of the present invention is shown;

[0073] Fig.10 The application architecture diagram of the energy consumption exception processing module in the system provided by the embodiment of the present invention is shown. DETAILED DESCRIPTION

[0074] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0075] It is understandable that since there are many types of equipment that need to be energy-monitored in smart factories, and some of the multiple devices are connected by wired communication, in the existing technology, wireless communication collection of energy consumption data is usually carried out through Internet of Things technology. Due to the instability of wireless transmission, it is easy to cause the loss of energy consumption data collection, and it is impossible to ensure that the energy consumption data of all equipment can be fully obtained.

[0076] To solve the above problems, the embodiment of the present invention discloses a smart factory energy consumption supervision method and system, which obtains factory supervision data, determines multiple energy consumption supervision devices, and periodically collects the equipment energy consumption data of multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods; performs data verification, data cleaning, data conversion and data labeling processing on multiple equipment energy consumption data to generate multiple labeled energy consumption data; selects a supervision detection model, imports multiple labeled energy consumption data into the supervision detection model, performs anomaly detection, and exports anomaly detection results; according to the anomaly detection results, when there is an energy consumption anomaly, determines the energy consumption abnormal device, performs an energy consumption anomaly alarm, and remotely reduces the energy consumption of the energy consumption abnormal device. It can periodically collect the equipment energy consumption data of multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods, perform data processing, import it into the supervision detection model, perform anomaly detection, and when there is an energy consumption anomaly, determines the energy consumption abnormal device, performs an energy consumption anomaly alarm, and remotely reduces the energy consumption, and can achieve auxiliary coordination of wireless communication and wired communication, thereby ensuring that the energy consumption data of all energy consumption supervision devices can be fully obtained.

[0077] Specifically, Figure 1 A flow chart of a smart factory energy consumption monitoring method provided by an embodiment of the present invention is shown.

[0078] In a preferred embodiment of the present invention, a method for monitoring energy consumption in a smart factory comprises the following steps:

[0079] Step S101: Obtain factory supervision data, determine multiple energy consumption supervision devices, and periodically collect equipment energy consumption data of the multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods.

[0080] In an embodiment of the present invention, by acquiring factory supervision data, object identification is performed on the factory supervision data, and multiple energy consumption supervision devices that need to be energy consumption supervised in the smart factory are determined. According to a preset energy consumption supervision cycle, energy consumption collection instructions are periodically generated, and the energy consumption collection instructions are wirelessly sent to multiple energy consumption supervision devices. Then, multiple first energy consumption data are received, and multiple feedback identification addresses are determined by feedback identification of the multiple first energy consumption data. Based on a preset basic device address, address matching is performed on the multiple feedback identification addresses, and the address matching results are recorded. According to the address matching results, energy consumption supervision devices that can be address matched are marked as connected supervision devices, and energy consumption supervision devices that cannot be address matched are marked as disconnected supervision devices, so that multiple energy consumption supervision devices can be divided into multiple connected supervision devices and multiple disconnected supervision devices. Then, based on the preset device interconnection information, wired interconnection analysis is performed on the multiple connected supervision devices and the multiple disconnected supervision devices, and the interconnection analysis results are recorded. Then, according to the interconnection analysis results, multiple auxiliary supervision devices that have a wired interconnection communication relationship with the multiple disconnected supervision devices are selected from the multiple connected supervision devices.

[0081] Specifically, Figure 2 A flow chart of collecting equipment energy consumption data in the method provided by an embodiment of the present invention is shown.

[0082] Among them, in the preferred embodiment provided by the present invention, the acquisition of factory supervision data, determining multiple energy consumption supervision devices, and periodically collecting the equipment energy consumption data of multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods specifically include the following steps:

[0083] Step S1011, obtaining factory supervision data.

[0084] Step S1012: performing object identification on the factory monitoring data to determine a plurality of energy consumption monitoring devices.

[0085] Step S1013: periodically generate and wirelessly send energy consumption collection instructions to multiple energy consumption monitoring devices.

[0086] Step S1014: receiving a plurality of first energy consumption data.

[0087] Step S1015: Based on the preset basic device address and device interconnection information, feedback identification is performed on multiple first energy consumption data, and multiple lost-connection monitoring devices and multiple auxiliary monitoring devices are marked.

[0088] Specifically, Figure 3 A flow chart of energy consumption data feedback identification in the method provided by an embodiment of the present invention is shown.

[0089] Among them, in the preferred implementation manner provided by the present invention, the feedback identification of the plurality of the first energy consumption data based on the preset basic device address and device interconnection information, and marking the plurality of lost-connection monitoring devices and the plurality of auxiliary monitoring devices specifically include the following steps:

[0090] Step S10151: Perform feedback identification on the plurality of first energy consumption data to determine a plurality of feedback identification addresses.

[0091] Step S10152: Based on the preset basic device address, address matching is performed on the multiple feedback identification addresses, and the address matching results are recorded.

[0092] Step S10153: According to the address matching result, the plurality of energy consumption monitoring devices are divided into a plurality of connected monitoring devices and a plurality of disconnected monitoring devices.

[0093] Step S10154: Based on the preset device interconnection information, wired interconnection analysis is performed on the plurality of connected supervision devices and the plurality of disconnected supervision devices, and the interconnection analysis results are recorded.

[0094] Step S10155: According to the interconnection analysis result, select auxiliary supervision devices corresponding to the multiple disconnected supervision devices from the multiple connected supervision devices.

[0095] Furthermore, the obtaining of factory supervision data, determining a plurality of energy consumption supervision devices, and periodically collecting the equipment energy consumption data of the plurality of energy consumption supervision devices through direct wireless and auxiliary wired communication methods also includes the following steps:

[0096] Step S1016: Obtain the second energy consumption data of the plurality of lost monitoring devices through wired auxiliary means through the plurality of auxiliary monitoring devices.

[0097] Specifically, Figure 4 A flow chart of wired-assisted data collection in the method provided by an embodiment of the present invention is shown.

[0098] Among them, in the preferred implementation manner provided by the present invention, the wired auxiliary acquisition of the second energy consumption data of the plurality of the lost monitoring devices through the plurality of the auxiliary monitoring devices specifically includes the following steps:

[0099] Step S10161: Generate and wirelessly send auxiliary collection instructions to multiple auxiliary monitoring devices.

[0100] Step S10162: forward the plurality of auxiliary collection instructions to the plurality of corresponding lost-connection supervision devices via wire through the plurality of auxiliary supervision devices.

[0101] Step S10163: Receive the second energy consumption data transmitted as feedback by the multiple lost-connection monitoring devices through the multiple auxiliary monitoring devices.

[0102] Furthermore, the smart factory energy consumption monitoring method further includes the following steps:

[0103] Step S102: performing data verification, data cleaning, data conversion and data labeling processing on the energy consumption data of the plurality of devices to generate a plurality of labeled energy consumption data.

[0104] In an embodiment of the present invention, firstly, the validity of energy consumption data of multiple devices is verified, and invalid data or obviously erroneous data is eliminated to obtain multiple valid energy consumption data. Then, interpolation method, average value filling method and other methods are used to perform data cleaning processing on the multiple valid energy consumption data to fill in missing values ​​to obtain multiple cleaned energy consumption data. Thereafter, the multiple cleaned energy consumption data are converted into a unified format to obtain multiple standard energy consumption data. Finally, the multiple standard energy consumption data are annotated by adding labels or annotations to data points to obtain multiple annotated energy consumption data.

[0105] Specifically, Figure 5 A flow chart of device energy consumption data processing in the method provided by an embodiment of the present invention is shown.

[0106] Among them, in the preferred embodiment provided by the present invention, the data verification, data cleaning, data conversion and data labeling processing of the multiple energy consumption data of the devices to generate multiple labeled energy consumption data specifically include the following steps:

[0107] Step S1021: verify and process the validity of the energy consumption data of the multiple devices to obtain multiple valid energy consumption data.

[0108] Step S1022: performing data cleaning processing of missing filling on the plurality of effective energy consumption data to obtain a plurality of cleaning energy consumption data.

[0109] Step S1023: convert the plurality of cleaning energy consumption data into a unified format to obtain a plurality of standard energy consumption data.

[0110] Step S1024: labeling the plurality of standard energy consumption data to obtain a plurality of labeled energy consumption data.

[0111] Furthermore, the smart factory energy consumption monitoring method further includes the following steps:

[0112] Step S103: select a supervision detection model, import the plurality of labeled energy consumption data into the supervision detection model, perform anomaly detection, and export anomaly detection results.

[0113] In an embodiment of the present invention, a supervision detection model is selected from multiple preset basic detection models, and then multiple labeled energy consumption data are imported into the supervision detection model. Through the supervision detection model, anomaly detection is performed on the multiple labeled energy consumption data, and then the exported anomaly detection results are obtained.

[0114] It is understandable that the multiple preset basic detection models may include an isolation forest detection model, a K-means clustering detection model, and the like.

[0115] Specifically, Figure 6 A flow chart of deriving anomaly detection results in the method provided in an embodiment of the present invention is shown.

[0116] Among them, in the preferred embodiment provided by the present invention, the said selecting supervision detection model, importing a plurality of the said labeled energy consumption data into the said supervision detection model, performing anomaly detection, and exporting the anomaly detection result specifically comprises the following steps:

[0117] Step S1031: Select a supervision detection model from multiple preset basic detection models.

[0118] Step S1032: import the plurality of annotated energy consumption data into the supervision and detection model.

[0119] Step S1033: Perform anomaly detection on the plurality of labeled energy consumption data using the supervision detection model.

[0120] Step S1034: Export anomaly detection results.

[0121] Furthermore, the smart factory energy consumption monitoring method further includes the following steps:

[0122] Step S104: According to the abnormality detection result, when there is energy consumption abnormality, energy consumption abnormality equipment is determined, energy consumption abnormality alarm is issued, and energy consumption abnormality equipment is remotely controlled to reduce energy consumption.

[0123] In an embodiment of the present invention, the abnormal detection results are analyzed to determine whether there is an energy consumption abnormality. In the case of energy consumption abnormality, abnormal energy consumption data is selected from multiple labeled energy consumption data, and based on the abnormal energy consumption data, the energy consumption abnormal device is determined. Then, based on the energy consumption abnormal device, an energy consumption abnormality alarm is issued. At the same time, the energy consumption adjustment strategy is matched to remotely reduce the energy consumption of the energy consumption abnormal device.

[0124] Specifically, Figure 7 A flow chart of abnormal energy consumption alarm and remote energy consumption reduction control in the method provided by an embodiment of the present invention is shown.

[0125] Among them, in the preferred embodiment provided by the present invention, the abnormal energy consumption device is determined according to the abnormal detection result, an abnormal energy consumption alarm is issued, and the abnormal energy consumption device is remotely controlled to reduce energy consumption, which specifically includes the following steps:

[0126] Step S1041: Determine whether there is an energy consumption abnormality according to the abnormality detection result.

[0127] Step S1042: When there is an energy consumption anomaly, select abnormal energy consumption data from the multiple annotated energy consumption data.

[0128] Step S1043: Determine the abnormal energy consumption device according to the abnormal energy consumption data.

[0129] Step S1044: an abnormal energy consumption alarm is issued according to the abnormal energy consumption device.

[0130] Step S1045: matching the energy consumption adjustment strategy, and performing remote energy consumption reduction control on the abnormal energy consumption device.

[0131] Furthermore, Figure 8 The application architecture diagram of the smart factory energy consumption monitoring system provided by an embodiment of the present invention is shown.

[0132] Among them, in another preferred embodiment provided by the present invention, a smart factory energy consumption monitoring system includes:

[0133] The energy consumption data collection module 101 is used to obtain factory supervision data, determine multiple energy consumption supervision devices, and periodically collect equipment energy consumption data of the multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods.

[0134] In an embodiment of the present invention, the energy consumption data collection module 101 obtains factory supervision data, performs object identification on the factory supervision data, determines multiple energy consumption supervision devices that need to be energy consumption supervised in the smart factory, periodically generates energy consumption collection instructions according to a preset energy consumption supervision cycle, and wirelessly sends the energy consumption collection instructions to multiple energy consumption supervision devices, then receives multiple first energy consumption data, determines multiple feedback identification addresses by performing feedback identification on the multiple first energy consumption data, performs address matching on the multiple feedback identification addresses based on a preset basic device address, records the address matching results, and marks the energy consumption supervision devices that can be address matched as connected supervision devices according to the address matching results, and marks the energy consumption supervision devices that cannot be address matched as disconnected supervision devices, so that the multiple energy consumption supervision devices can be divided into multiple connected supervision devices and multiple disconnected supervision devices, and then performs wired interconnection analysis on the multiple connected supervision devices and the multiple disconnected supervision devices based on the preset device interconnection information, records the interconnection analysis results, and then selects multiple auxiliary supervision devices that have a wired interconnection communication relationship with the multiple disconnected supervision devices from the multiple connected supervision devices according to the interconnection analysis results.

[0135] Specifically, Fig. 9 The application architecture diagram of the energy consumption data acquisition module 101 in the system provided by the embodiment of the present invention is shown.

[0136] Among them, in the preferred embodiment provided by the present invention, the energy consumption data collection module 101 specifically includes:

[0137] The data acquisition unit 1011 is used to acquire factory supervision data.

[0138] The object identification unit 1012 is used to perform object identification on the factory monitoring data to determine multiple energy consumption monitoring devices.

[0139] The wireless sending unit 1013 is used to periodically generate and wirelessly send energy consumption collection instructions to multiple energy consumption monitoring devices.

[0140] The data receiving unit 1014 is configured to receive a plurality of first energy consumption data.

[0141] The feedback identification unit 1015 is used to perform feedback identification on multiple first energy consumption data based on the preset basic device address and device interconnection information, and mark multiple lost-connection monitoring devices and multiple auxiliary monitoring devices.

[0142] The wired auxiliary unit 1016 is used to obtain the second energy consumption data of the multiple lost monitoring devices through the wired auxiliary means.

[0143] Furthermore, the smart factory energy consumption monitoring system also includes:

[0144] The energy consumption data processing module 102 is used to perform data verification, data cleaning, data conversion and data labeling processing on the energy consumption data of the plurality of devices to generate a plurality of labeled energy consumption data.

[0145] In an embodiment of the present invention, the energy consumption data processing module 102 first verifies the validity of the energy consumption data of multiple devices, eliminates invalid data or obviously erroneous data, and obtains multiple valid energy consumption data. Then, interpolation method, average value filling method and other methods are used to perform data cleaning processing on the multiple valid energy consumption data to fill in missing values, and obtain multiple cleaned energy consumption data. Thereafter, the multiple cleaned energy consumption data are converted into a unified format to obtain multiple standard energy consumption data. Finally, the multiple standard energy consumption data are annotated by adding labels or annotations to the data points to obtain multiple annotated energy consumption data.

[0146] The model anomaly detection module 103 is used to select a supervision detection model, import a plurality of the labeled energy consumption data into the supervision detection model, perform anomaly detection, and export anomaly detection results.

[0147] In an embodiment of the present invention, the model anomaly detection module 103 selects a supervisory detection model from a plurality of preset basic detection models, and then imports a plurality of labeled energy consumption data into the supervisory detection model, performs anomaly detection on the plurality of labeled energy consumption data through the supervisory detection model, and then obtains an exported anomaly detection result.

[0148] The energy consumption anomaly processing module 104 is used to determine the energy consumption anomaly device according to the anomaly detection result, issue an energy consumption anomaly alarm, and remotely reduce the energy consumption of the energy consumption anomaly device when there is an energy consumption anomaly.

[0149] In an embodiment of the present invention, the energy consumption anomaly processing module 104 analyzes the anomaly detection results to determine whether there is an energy consumption anomaly. In the case of an energy consumption anomaly, the module selects abnormal energy consumption data from multiple labeled energy consumption data, and determines the energy consumption anomaly device based on the abnormal energy consumption data. Based on the energy consumption anomaly device, an energy consumption anomaly alarm is issued. At the same time, the energy consumption adjustment strategy is matched to remotely reduce the energy consumption of the energy consumption anomaly device.

[0150] Specifically, Fig.10 The application architecture diagram of the energy consumption exception processing module 104 in the system provided by the embodiment of the present invention is shown.

[0151] Among them, in the preferred embodiment provided by the present invention, the energy consumption abnormality processing module 104 specifically includes:

[0152] The abnormality determination unit 1041 is used to determine whether there is an energy consumption abnormality according to the abnormality detection result.

[0153] The data selection unit 1042 is used to select abnormal energy consumption data from the multiple labeled energy consumption data when there is abnormal energy consumption.

[0154] The device determining unit 1043 is used to determine the device with abnormal energy consumption according to the abnormal energy consumption data.

[0155] The abnormal alarm unit 1044 is used to issue an abnormal energy consumption alarm according to the abnormal energy consumption device.

[0156] The consumption reduction control unit 1045 is used to match the energy consumption adjustment strategy and perform remote consumption reduction control on the energy consumption abnormal device.

[0157] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0158] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0159] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for monitoring energy consumption in a smart factory, characterized in that: The method comprises the following steps: Obtain factory supervision data, determine multiple energy consumption supervision devices, and periodically collect equipment energy consumption data of the multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods; Performing data verification, data cleaning, data conversion and data labeling processing on the energy consumption data of the plurality of devices to generate a plurality of labeled energy consumption data; Selecting a supervision detection model, importing a plurality of the labeled energy consumption data into the supervision detection model, performing anomaly detection, and exporting anomaly detection results; According to the abnormality detection result, when there is energy consumption abnormality, energy consumption abnormality equipment is determined, energy consumption abnormality alarm is issued, and energy consumption abnormality equipment is remotely controlled to reduce energy consumption.

2. The smart factory energy consumption monitoring method according to claim 1 is characterized in that: The method of obtaining factory supervision data, determining multiple energy consumption supervision devices, and periodically collecting the equipment energy consumption data of the multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods specifically includes the following steps: Obtain factory regulatory data; Performing object recognition on the factory monitoring data to determine a plurality of energy consumption monitoring devices; Periodically generate and wirelessly send energy consumption collection instructions to multiple energy consumption monitoring devices; receiving a plurality of first energy consumption data; Based on the preset basic device address and device interconnection information, multiple first energy consumption data are fed back and identified, and multiple disconnected monitoring devices and multiple auxiliary monitoring devices are marked; Through the plurality of auxiliary monitoring devices, the second energy consumption data of the plurality of lost monitoring devices are obtained by wired assistance.

3. The smart factory energy consumption monitoring method according to claim 2 is characterized in that: The step of performing feedback identification on the plurality of the first energy consumption data based on the preset basic device address and device interconnection information, and marking the plurality of lost-connection monitoring devices and the plurality of auxiliary monitoring devices specifically comprises the following steps: Performing feedback identification on the plurality of the first energy consumption data, and determining a plurality of feedback identification addresses; Based on the preset basic device address, address matching is performed on the multiple feedback identification addresses, and the address matching results are recorded; According to the address matching result, the plurality of energy consumption monitoring devices are divided into a plurality of connected monitoring devices and a plurality of disconnected monitoring devices; Based on the preset device interconnection information, performing wired interconnection analysis on the plurality of connected supervision devices and the plurality of disconnected supervision devices, and recording the interconnection analysis results; According to the interconnection analysis result, auxiliary supervision devices corresponding to the multiple disconnected supervision devices are selected from the multiple connected supervision devices.

4. The smart factory energy consumption monitoring method according to claim 2 is characterized in that: The method of obtaining the second energy consumption data of the plurality of disconnected monitoring devices by wired auxiliary means through the plurality of auxiliary monitoring devices specifically comprises the following steps: Generate and wirelessly send auxiliary collection instructions to multiple auxiliary monitoring devices; Through the plurality of auxiliary monitoring devices, the plurality of auxiliary collection instructions are forwarded to the plurality of corresponding lost-connection monitoring devices via wire; The second energy consumption data transmitted as feedback by the plurality of disconnected supervision devices is received through the plurality of auxiliary supervision devices.

5. The smart factory energy consumption monitoring method according to claim 1 is characterized in that: The data verification, data cleaning, data conversion and data labeling processing of the plurality of energy consumption data of the devices to generate a plurality of labeled energy consumption data specifically comprises the following steps: Verifying and processing the data validity of a plurality of energy consumption data of the devices to obtain a plurality of valid energy consumption data; Performing data cleaning processing of missing filling on the plurality of effective energy consumption data to obtain a plurality of cleaning energy consumption data; Converting the plurality of cleaning energy consumption data into a unified format to obtain a plurality of standard energy consumption data; A plurality of standard energy consumption data are labeled to obtain a plurality of labeled energy consumption data.

6. The smart factory energy consumption monitoring method according to claim 1 is characterized in that: The step of selecting a supervision detection model, importing a plurality of the labeled energy consumption data into the supervision detection model, performing anomaly detection, and exporting anomaly detection results specifically includes the following steps: Select a supervision detection model from multiple preset basic detection models; Importing a plurality of the annotated energy consumption data into the supervision and detection model; By using the supervision detection model, anomaly detection is performed on the plurality of labeled energy consumption data; Export anomaly detection results.

7. The smart factory energy consumption monitoring method according to claim 1 is characterized in that: The method of determining the abnormal energy consumption device according to the abnormal detection result, performing abnormal energy consumption alarm, and remotely reducing the energy consumption of the abnormal energy consumption device when there is abnormal energy consumption specifically includes the following steps: According to the abnormality detection result, determining whether there is energy consumption abnormality; When there is an energy consumption anomaly, selecting the abnormal energy consumption data from the plurality of annotated energy consumption data; Determine the abnormal energy consumption device according to the abnormal energy consumption data; According to the abnormal energy consumption equipment, an abnormal energy consumption alarm is issued; The energy consumption adjustment strategy is matched to remotely control the energy consumption reduction of the abnormal energy consumption equipment.

8. A smart factory energy consumption monitoring system, characterized in that: The system includes an energy consumption data acquisition module, an energy consumption data processing module, a model anomaly detection module and an energy consumption anomaly processing module, wherein: An energy consumption data collection module is used to obtain factory supervision data, determine multiple energy consumption supervision devices, and periodically collect equipment energy consumption data of multiple energy consumption supervision devices through direct wireless and auxiliary wired communication methods; An energy consumption data processing module, used for performing data verification, data cleaning, data conversion and data labeling processing on a plurality of energy consumption data of the devices, and generating a plurality of labeled energy consumption data; A model anomaly detection module, used for selecting a supervision detection model, importing a plurality of the labeled energy consumption data into the supervision detection model, performing anomaly detection, and exporting anomaly detection results; The energy consumption anomaly processing module is used to determine the energy consumption anomaly equipment according to the anomaly detection result, issue an energy consumption anomaly alarm, and remotely control the energy consumption anomaly equipment to reduce energy consumption.

9. The smart factory energy consumption monitoring system according to claim 8 is characterized in that: The energy consumption data collection module specifically includes: A data acquisition unit, used to acquire factory supervision data; An object identification unit, used to perform object identification on the factory supervision data to determine a plurality of energy consumption supervision devices; A wireless sending unit, used for periodically generating and wirelessly sending energy consumption collection instructions to multiple energy consumption monitoring devices; A data receiving unit, used for receiving a plurality of first energy consumption data; A feedback identification unit, configured to perform feedback identification on a plurality of the first energy consumption data based on a preset basic device address and device interconnection information, and mark a plurality of lost-connection monitoring devices and a plurality of auxiliary monitoring devices; The wired auxiliary unit is used to obtain the second energy consumption data of the multiple lost monitoring devices through the wired auxiliary monitoring devices.

10. The smart factory energy consumption monitoring system according to claim 8, characterized in that: The energy consumption abnormality processing module specifically includes: An abnormality judgment unit, used for judging whether there is an energy consumption abnormality according to the abnormality detection result; A data selection unit, used for selecting abnormal energy consumption data from a plurality of annotated energy consumption data when there is abnormal energy consumption; A device determining unit, configured to determine a device with abnormal energy consumption according to the abnormal energy consumption data; An abnormal alarm unit, used for alarming abnormal energy consumption according to the abnormal energy consumption equipment; The consumption reduction control unit is used to match the energy consumption adjustment strategy and perform remote consumption reduction control on the energy consumption abnormal device.

Images