Industrial equipment management method and equipment based on current monitoring and medium

Abstract

The invention discloses an industrial equipment management method and equipment based on current monitoring and a medium, and the method comprises the steps: collecting the operation current of industrial equipment in real time, and processing the operation current to obtain a current data sequence; inputting the current data sequence into a pre-trained RNN model so as to perform waveform analysis on the current data sequence through the RNN model, and outputting probability values of the industrial equipment in each equipment operation state; wherein the equipment running state comprises a starting-up non-running state, a starting-up processing state, a fault state and an equipment preheating state; and performing energy efficiency state evaluation and fault mode identification on the industrial equipment according to the probability value so as to generate a scheduling plan for the industrial equipment through the obtained energy consumption state and fault mode, thereby realizing operation management of the industrial equipment.

Description

Technical Field

[0001] This application relates to the field of industrial automation technology, specifically to an industrial equipment management method, equipment, and medium based on current monitoring. Background Technology

[0002] Currently, the operation, management, and maintenance of industrial equipment generally rely on manual periodic inspections for planned maintenance. However, manual inspections cannot monitor industrial equipment in real time and continuously, making it difficult to provide early warnings of equipment failures. At the same time, there is a lack of accurate identification and energy efficiency assessment methods for inefficient operating conditions such as no-load and light-load conditions, resulting in serious energy waste. Summary of the Invention

[0003] To address the aforementioned problems, this application proposes an industrial equipment management method based on current monitoring, comprising: The operating current of industrial equipment is collected in real time, and the operating current is processed to obtain a current data sequence; The current data sequence is input into a pre-trained RNN model to perform waveform analysis on the current data sequence and output the probability value of the industrial equipment being in each equipment operating state; wherein, the equipment operating state includes power-on but not running state, power-on processing state, fault state, and equipment preheating state; Based on the probability values, the energy efficiency status assessment and fault mode identification of the industrial equipment are performed. In order to generate a scheduling plan for the industrial equipment through the obtained energy consumption status and fault modes, the operation management of the industrial equipment is realized.

[0004] In one implementation of this application, the energy efficiency status assessment and fault mode identification of the industrial equipment are performed based on the probability value, specifically including: When the probability value indicates that the industrial equipment is in the operation state, the current feature parameters in the current data sequence are extracted, and the energy efficiency status of the industrial equipment is determined according to the current feature parameters and the operating reference parameters corresponding to the operating status of the equipment. Based on the relationship between the probability value corresponding to the fault state and the preset threshold, the fault mode corresponding to the industrial equipment is determined; wherein, the fault mode includes an immediate fault mode and a predictive fault mode.

[0005] In one implementation of this application, the fault mode corresponding to the industrial equipment is determined based on the relationship between the probability value corresponding to the fault state and a preset threshold, specifically including: If the probability value exceeds a first preset threshold, the fault mode corresponding to the industrial equipment is determined to be an immediate fault mode. If the probability value does not exceed the first preset threshold and is greater than the second preset threshold, the fault mode corresponding to the industrial equipment is determined to be a predicted fault mode, and the historical operating data corresponding to the industrial equipment is obtained, so as to determine the fault probability corresponding to the industrial equipment based on the historical operating data and the current waveform corresponding to the operating current.

[0006] In one implementation of this application, the energy efficiency status of the industrial equipment is determined based on the current characteristic parameters and the operating reference parameters corresponding to the equipment operating status, specifically including: The current characteristic parameters include current amplitude, current fluctuation frequency, and load energy efficiency ratio; Calculate the standard deviation and mean of the current amplitude corresponding to the current amplitude, and compare the standard deviation, mean of the current amplitude, and the load energy efficiency ratio with the operating reference parameters corresponding to the start-up processing state to determine the energy efficiency state of the industrial equipment.

[0007] In one implementation of this application, the standard deviation of the current amplitude, the mean of the current amplitude, and the load energy efficiency ratio are compared with the operating reference parameters corresponding to the start-up processing state to determine the energy efficiency state of the industrial equipment, specifically including: If the standard deviation of the current amplitude is less than the preset standard deviation, the mean of the current amplitude is less than the preset mean, and the load energy efficiency ratio is greater than the preset value, the energy efficiency state of the industrial equipment is determined to be a high-efficiency state. If the standard deviation of the current amplitude is greater than the preset standard deviation, the mean of the current amplitude is greater than the preset mean, and the load energy efficiency ratio is less than the preset value, the energy efficiency state of the industrial equipment is determined to be an inefficient state. If the current characteristic parameter exceeds the allowable range of the operating reference parameter, the energy efficiency status of the industrial equipment is determined to be an abnormally high efficiency status.

[0008] In one implementation of this application, determining the fault probability of the industrial equipment based on the historical operating data and the current waveform corresponding to the operating current specifically includes: The RNN model is used to identify the current waveform corresponding to the operating current in order to determine the fault type corresponding to the current waveform. Based on the historical operating data, obtain the abnormal waveform corresponding to the fault type of the industrial equipment; The abnormal waveform is compared with the current waveform to determine the failure probability of the industrial equipment based on the degree of difference between the current waveform and the abnormal waveform.

[0009] In one implementation of this application, before inputting the current data sequence into a pre-trained RNN model, the method further includes: Determine a training set consisting of the operating currents of multiple industrial devices; Based on the current data characteristics of the operating current, generate the corresponding equipment operating status label for the industrial equipment; The operating current is input into a preset RNN model for training, so that the RNN model can output the predicted equipment operating status label corresponding to the industrial equipment. Based on the cross-entropy loss function, the error value between the device operating state label and the predicted device operating state label is calculated, and the network parameters of the RNN model are updated using the error value until the error value meets the preset error value through the updated network parameters, thus obtaining the trained RNN model.

[0010] In one implementation of this application, a scheduling plan for the industrial equipment is generated based on the obtained energy consumption status and fault modes, specifically including: When the fault mode is the immediate fault mode, an early warning prompt is generated for the industrial equipment; When the fault mode is the predicted fault mode, the maintenance priority of the industrial equipment is determined based on the energy consumption status and the fault probability. Based on the maintenance priority, the maintenance sequence and maintenance cycle of the industrial equipment are determined to obtain a scheduling plan for the industrial equipment.

[0011] This application provides an industrial equipment management device based on current monitoring, the device comprising: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which, when executed, enable the at least one processor to perform an industrial equipment management method based on current monitoring as described above.

[0012] This application provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows: An industrial equipment management method based on current monitoring, as described in any of the preceding items.

[0013] The industrial equipment management method based on current monitoring proposed in this application can bring the following beneficial effects: By collecting and analyzing the operating current of industrial equipment in real time, and using the RNN model to accurately identify the equipment's working status and energy efficiency status, the problem of traditional manual inspection being unable to monitor and assess energy efficiency in real time has been effectively solved. This has enabled a shift from passive maintenance to predictive maintenance, improving fault early warning capabilities while also accurately identifying inefficient operating conditions of the equipment. Attached Figure Description

[0014] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart illustrating an industrial equipment management method based on current monitoring, provided for an embodiment of this application; Figure 2 This is a schematic diagram of the structure of an industrial equipment management device based on current monitoring, provided as an embodiment of this application. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0016] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0017] like Figure 1 As shown in the embodiment of this application, an industrial equipment management method based on current monitoring is provided, including: S101: Real-time acquisition of the operating current of industrial equipment, processing of the operating current to obtain a current data sequence.

[0018] Industrial equipment, such as electric motors, compressors, and pumps, plays a vital role in industrial production. To improve production efficiency, it is necessary to monitor the faults and energy consumption of industrial equipment in real time to ensure its normal and efficient operation. Current signals directly reflect the energy consumption of equipment, which is directly related to the equipment's operating efficiency and health status. Therefore, this application selects current as the core indicator for judging equipment status. Hall effect sensors are installed on industrial equipment. Hall effect sensors are non-contact and high-precision, capable of measuring current changes in real time, and are suitable for long-term operation in industrial environments. The monitoring principle of Hall effect sensors is to convert the magnetic field generated by the induced current into a voltage signal. This voltage signal is proportional to the current magnitude, providing accurate current data. Therefore, Hall effect sensors can be used to collect the corresponding operating current of industrial equipment in real time during operation. After collecting the operating current, an analog signal converter converts the analog current signal into a digital signal, and the digital signal undergoes data filtering and noise reduction to ensure high accuracy of the collected data and avoid errors caused by environmental interference. The processed operating current data will be uploaded to the data center via industrial IoT devices. This data can be uploaded wirelessly via Wi-Fi, LoRaWAN, Zigbee, or transmitted via Ethernet or 4G / 5G networks. After collecting the operating current data from various industrial devices, the data center uses a distributed storage system for storage and management. The data will be indexed according to device ID, timestamps, and other information for subsequent querying and analysis.

[0019] Current data varies over time and is typically time-dependent. Recurrent Neural Networks (RNNs) are well-suited for processing this type of time-series data because they can pass information from previous time steps to the current time step through a recurrent structure, thereby capturing the temporal patterns in the data. Furthermore, current waveform data often contains periodicity and instantaneous fluctuations, which RNNs can effectively capture to predict the operating status of industrial equipment. Therefore, this application uses an RNN model for real-time prediction of equipment operating status. However, since operating current is usually collected in the form of time-series data, and this data needs to be input into a pre-trained RNN model for subsequent analysis, it is necessary to convert the data into a format suitable for RNN model input to facilitate data processing and analysis. Therefore, the data is divided into multiple time periods according to time sequence, that is, sampling is performed according to fixed-length time windows (e.g., 10 seconds, 30 seconds, etc.). The operating current at each time step can be represented by a feature vector. The operating current data corresponding to multiple time steps constitute a current data sequence. The input vector at each time step can represent the amplitude, frequency, and other features of the current waveform corresponding to the operating current.

[0020] S102: Input the current data sequence into the pre-trained RNN model to perform waveform analysis on the current data sequence through the RNN model and output the probability value of the industrial equipment being in each equipment operating state; wherein, the equipment operating state includes the power-on but not running state, the power-on processing state, the fault state, and the equipment preheating state.

[0021] Current data sequences are used to analyze the real-time operating status of industrial equipment, specifically identifying whether the equipment is faulty or experiencing abnormal energy consumption. This application's embodiments no longer employ manual analysis; instead, they use an RNN model to automatically identify the current data sequences and output the probability value of the industrial equipment's current operating state. These operating states include: powered on but not running, powered on and processing, faulty, and preheating. Compared to manual inspection, using an RNN model for prediction eliminates the need for manual provision of equipment status data and automatically identifies equipment faults and energy consumption, significantly improving both efficiency and accuracy.

[0022] The RNN model needs to be trained beforehand to enable it to accurately analyze the operating status of industrial equipment. First, a training set is constructed by collecting operating current data from multiple industrial devices. This training set needs to be labeled to indicate the operating status of the corresponding industrial equipment. During labeling, the operating status is determined based on the characteristics of the operating current data. Specifically, the "powered but not running" state indicates that the equipment is powered on but not yet started or is in an unloaded state. The current is low and without significant fluctuations; its characteristics are a stable current waveform, small current value, and almost zero load. The "powered and processing" state indicates that the equipment is powered on and has started processing tasks. At this time, the equipment load gradually increases, the current rises accordingly, and exhibits some fluctuation; its characteristics are larger current fluctuations. As the processing task is executed, the current value fluctuates and remains within a certain range. Fault status indicates equipment malfunction, such as overload, mechanical jamming, or component damage. When a fault occurs, the current waveform typically exhibits abnormal fluctuations, with the current being either too high or too low, and may remain unstable. Current data characteristics include drastic fluctuations in the current waveform, abnormally high or low current peak values, and frequent fluctuations. Equipment preheating status indicates that after equipment startup, it enters the preheating phase. The current is typically high, but as the equipment gradually reaches a stable operating state, the current tends to stabilize. Current data characteristics include a high current that gradually stabilizes, high fluctuation frequency, and a gradual decrease in current peak value. After determining the equipment operating status corresponding to the data in the training set, manual or automated label generation tools are used to generate equipment operating status labels for the industrial equipment in the training set data. After labeling the data, it is necessary to clean the data, removing abnormal or noisy data. Denoising algorithms (such as median filtering and mean filtering) can be used to process the data to ensure the accuracy of data labeling.

[0023] After data labeling, the operating current (the labeled training set) is input into a pre-defined RNN model for training. The RNN model employs a network structure based on Long Short-Term Memory (LSTM) or Gated Recurrent Unit (GRU). Through the RNN model, it outputs predicted equipment operating state labels for the industrial equipment. The LSTM or GRU layer processes the current data sequence, learning the dependencies between each time step to capture long-term dependencies in the current waveform. The data processed by the LSTM or GRU layer is then input into a fully connected layer, which maps the output to specific equipment operating states. The output layer is a softmax layer, used to predict the probability value corresponding to the industrial equipment and ultimately output the predicted equipment operating state label. The equipment operating state labels predicted by the RNN need to be compared with the actual equipment operating state labels to determine the prediction error of the current model. Therefore, the error value between the equipment operating state labels and the predicted equipment operating state labels needs to be calculated based on the cross-entropy loss function. If the error value is large, the network parameters of the RNN model need to be updated through the backpropagation algorithm until the error value between the predicted device working state label and the actual device working label, predicted again with the updated network parameters, meets the preset error value. Then the trained RNN model is obtained.

[0024] By inputting the real-time current data sequence of the industrial equipment into the pre-trained RNN model, the probability values ​​of the industrial equipment under various operating states can be obtained.

[0025] S103: Based on probability values, perform energy efficiency status assessment and fault mode identification on industrial equipment, and generate scheduling plans for industrial equipment through the obtained energy consumption status and fault modes to achieve operation management of industrial equipment.

[0026] The probability values ​​predicted by the aforementioned RNN can clearly define the current operating status of industrial equipment. Based on the operating current data and the predicted operating status, energy efficiency status assessment and fault mode identification are performed on the industrial equipment, thereby determining whether there are fault risks and energy consumption risks. In this way, a scheduling plan for the industrial equipment can be generated using the obtained energy consumption status and fault modes. Corresponding maintenance operations can then be performed on the industrial equipment according to the scheduling plan, achieving operational management of the industrial equipment.

[0027] In one embodiment, this application only considers the energy consumption of industrial equipment during operation. The current waveform can not only reflect the operating status of the industrial equipment, such as whether it is overloaded or malfunctioning, but also be used to evaluate the working efficiency of the industrial equipment. There is a certain relationship between the current waveform of industrial equipment and the load. When the industrial equipment is in a high-efficiency operating state, the current waveform is relatively stable, while when the efficiency of the industrial equipment decreases, such as due to overload, mechanical failure, or equipment aging, the current waveform will fluctuate abnormally.

[0028] Therefore, when the probability value indicates that the industrial equipment is in a processing state, it is necessary to extract the current characteristic parameters from the current data sequence and determine the corresponding energy efficiency status of the industrial equipment based on the current characteristic parameters and the corresponding operating benchmark parameters. Energy efficiency status is divided into high-efficiency, low-efficiency, and abnormally high-efficiency states. In the high-efficiency state, the current waveform of the industrial equipment is stable with small current fluctuations, indicating a reasonable equipment load. In the low-efficiency state, the current waveform of the industrial equipment fluctuates drastically, with large current values, indicating uneven or near-overloaded equipment load. In the abnormally high-efficiency state, due to faults or system configuration problems, the current waveform of the industrial equipment exhibits abnormally high load fluctuations. When assessing the energy consumption status of industrial equipment, three current characteristic parameters are used: current amplitude, current fluctuation frequency, and load energy efficiency ratio. Current amplitude reflects the load condition of the industrial equipment; during high-efficiency operation, the current amplitude is small and stable, while during low-efficiency operation, the current amplitude is large and fluctuates frequently. The frequency components of the current waveform can reflect the load fluctuation of the industrial equipment; large fluctuations in frequency components may indicate that the equipment is not in a stable operating state and there is efficiency loss. The load power ratio refers to the ratio between the operating current and the rated power of the equipment. It is used to evaluate the energy efficiency ratio of the equipment. If the equipment can maintain a low current under high load, it indicates that the equipment has high operating efficiency. Conversely, large current fluctuations may mean energy waste or low efficiency.

[0029] Therefore, based on the aforementioned current characteristic parameters, it is necessary to calculate the standard deviation of the current amplitude to reflect current amplitude fluctuations, and the mean current amplitude to reflect the magnitude of the current amplitude. Then, the standard deviation, mean current amplitude, and load efficiency ratio are compared with the operating baseline parameters corresponding to the start-up processing state to determine the energy efficiency status of the industrial equipment. The operating baseline parameters refer to the normal energy consumption standards of the industrial equipment when it is in the start-up processing state. By comparing the real-time operating parameters of the industrial equipment with the operating baseline parameters, the specific energy consumption of the current industrial equipment can be determined.

[0030] Specifically, when the standard deviation of the current amplitude is less than the preset standard deviation, the mean current amplitude is less than the preset mean, and the load efficiency ratio is greater than the preset value, the energy efficiency state of the industrial equipment is high-efficiency. When the standard deviation of the current amplitude is greater than the preset standard deviation, the mean current amplitude is greater than the preset mean, and the load efficiency ratio is less than the preset value, the energy efficiency state of the industrial equipment is determined to be low-efficiency. When the current characteristic parameters exceed the rated range of the operating reference parameters, that is, when the current waveform shows abnormally high load fluctuations and the load efficiency ratio deviates significantly from the rated range, the energy efficiency state of the industrial equipment is abnormally high-efficiency.

[0031] To ensure the smooth operation of industrial equipment, in addition to real-time assessment of its energy consumption, it is also necessary to determine whether there is a risk of failure during operation. After outputting the probability value of the current industrial equipment being in a fault state, the RNN can determine the corresponding fault mode based on the relationship between this probability value and a preset threshold. Fault modes include immediate fault modes and predictive fault modes. A first preset threshold represents the maximum critical value for the industrial equipment to fail, and a second preset threshold represents the maximum critical value for the industrial equipment to be in a normal state; the first preset threshold is greater than the second preset threshold. When the probability value exceeds the first preset threshold, it indicates that the RNN model predicts a very high probability of the industrial equipment failing, and a fault can be directly determined. This is the immediate fault mode, requiring immediate maintenance. When the probability value does not exceed the preset threshold, it indicates that the industrial equipment may fail, but the risk is not particularly high. This is the predictive fault mode. In the predictive fault mode, historical operating data of the industrial equipment needs to be obtained. Based on the historical operating data and the current waveform corresponding to the operating current, the fault risk of the industrial equipment is predicted, thus predicting whether the industrial equipment will fail in the future, allowing for early warning measures to be taken.

[0032] In one embodiment, the probability of failure of industrial equipment is predicted by using the historical operating data of the equipment. If there is a historical current waveform similar to the current current waveform in the historical operating data, the probability of failure of the industrial equipment can be predicted based on the fluctuation of the current current waveform.

[0033] Specifically, the RNN model can not only identify the current operating state of the equipment, but also identify the current waveform corresponding to the operating current, determining the fault type, including equipment overload, motor jamming, etc. After determining the fault type, based on historical operating data, the abnormal waveform corresponding to the fault type of the industrial equipment is obtained, and then the abnormal waveform is compared with the current waveform. Based on the degree of difference between the current waveform and the abnormal waveform, the probability of the fault corresponding to the industrial equipment can be determined. There is a mapping relationship between the degree of difference and the fault probability. When the degree of difference is relatively small, it means that the current waveform of the industrial equipment at this time has abnormal characteristics that are very similar to the abnormal waveform. If the industrial equipment continues to operate, a fault similar to the historical fault type will occur, and the probability of the industrial equipment failing at this time is relatively high.

[0034] Once the energy consumption status and failure probability of industrial equipment are determined, a corresponding scheduling plan needs to be generated based on the identified equipment status to ensure the efficient operation of the industrial equipment.

[0035] Specifically, when the fault mode of industrial equipment is identified as an immediate fault mode, it means that the RNN model predicts that the industrial equipment is already in a fault state. To ensure equipment safety and prevent production accidents, an early warning prompt needs to be generated immediately to alert relevant personnel to take emergency measures. When the fault mode is a predicted fault mode, although the industrial equipment has a certain risk of failure, the specific maintenance sequence needs to be further determined based on energy consumption status and fault probability. That is, the maintenance priority of the industrial equipment is determined according to energy consumption status and fault probability. For example, high fault risk and high energy efficiency loss are the highest priority; low fault risk and high energy efficiency loss are medium to high priority. In this case, although the equipment will not break down immediately, it is continuously wasting a lot of energy. Energy efficiency optimization maintenance should be arranged as soon as possible. High fault risk, low energy efficiency loss, and high priority should be prioritized for preventive maintenance to avoid downtime. Low fault risk, low energy efficiency loss, and low priority should be addressed after other industrial equipment has been processed before maintaining this equipment. Therefore, after determining the maintenance priority for each piece of industrial equipment, it is necessary to determine the maintenance sequence and cycle of the equipment in descending order of priority, thereby generating a scheduling plan for the industrial equipment. The higher the maintenance priority, the earlier the maintenance sequence and the shorter the maintenance cycle. Through the scheduling plan, intelligent maintenance scheduling can be provided when industrial equipment is about to fail, realizing real-time operation management of industrial equipment.

[0036] The above are embodiments of the methods proposed in this application. Based on the same idea, some embodiments of this application also provide devices and non-volatile computer storage media corresponding to the above methods.

[0037] Figure 2This is a schematic diagram of the structure of an industrial equipment management device based on current monitoring, provided as an embodiment of this application. Figure 2 As shown, it includes: At least one processor; and, At least one processor-communication-connected memory; wherein, The memory stores instructions that can be executed by at least one processor, and the instructions, when executed by at least one processor, enable at least one processor to: Implement an industrial equipment management method based on current monitoring as described in any of the preceding items.

[0038] This application provides a non-volatile computer storage medium storing computer-executable instructions, which are configured as follows: An industrial equipment management method based on current monitoring, as described in any of the preceding items.

[0039] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0040] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0041] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0042] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0043] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0044] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0045] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0046] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0047] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0048] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0049] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for managing industrial equipment based on current monitoring, characterized in that, The method includes: The operating current of industrial equipment is collected in real time, and the operating current is processed to obtain a current data sequence; The current data sequence is input into a pre-trained RNN model to perform waveform analysis on the current data sequence and output the probability value of the industrial equipment being in each equipment operating state; wherein, the equipment operating state includes power-on but not running state, power-on processing state, fault state, and equipment preheating state; Based on the probability values, the energy efficiency status assessment and fault mode identification of the industrial equipment are performed. In order to generate a scheduling plan for the industrial equipment through the obtained energy consumption status and fault modes, the operation management of the industrial equipment is realized.

2. The industrial equipment management method based on current monitoring according to claim 1, characterized in that, Based on the probability values, energy efficiency status assessment and fault mode identification are performed on the industrial equipment, specifically including: When the probability value indicates that the industrial equipment is in the operation state, the current feature parameters in the current data sequence are extracted, and the energy efficiency status of the industrial equipment is determined according to the current feature parameters and the operating reference parameters corresponding to the operating status of the equipment. Based on the relationship between the probability value corresponding to the fault state and the preset threshold, the fault mode corresponding to the industrial equipment is determined; wherein, the fault mode includes an immediate fault mode and a predictive fault mode.

3. The industrial equipment management method based on current monitoring according to claim 2, characterized in that, Based on the relationship between the probability value corresponding to the fault state and a preset threshold, the fault mode corresponding to the industrial equipment is determined, specifically including: If the probability value exceeds a first preset threshold, the fault mode corresponding to the industrial equipment is determined to be an immediate fault mode. If the probability value does not exceed the first preset threshold and is greater than the second preset threshold, the fault mode corresponding to the industrial equipment is determined to be a predicted fault mode, and the historical operating data corresponding to the industrial equipment is obtained, so as to determine the fault probability corresponding to the industrial equipment based on the historical operating data and the current waveform corresponding to the operating current.

4. The industrial equipment management method based on current monitoring according to claim 2, characterized in that, Based on the current characteristic parameters and the corresponding operating reference parameters of the equipment operating status, the energy efficiency status of the industrial equipment is determined, specifically including: The current characteristic parameters include current amplitude, current fluctuation frequency, and load energy efficiency ratio; Calculate the standard deviation and mean of the current amplitude corresponding to the current amplitude, and compare the standard deviation, mean of the current amplitude, and the load energy efficiency ratio with the operating reference parameters corresponding to the start-up processing state to determine the energy efficiency state of the industrial equipment.

5. The industrial equipment management method based on current monitoring according to claim 4, characterized in that, The standard deviation of the current amplitude, the mean of the current amplitude, and the load energy efficiency ratio are compared with the operating reference parameters corresponding to the start-up processing state to determine the energy efficiency state of the industrial equipment, specifically including: If the standard deviation of the current amplitude is less than the preset standard deviation, the mean of the current amplitude is less than the preset mean, and the load energy efficiency ratio is greater than the preset value, the energy efficiency state of the industrial equipment is determined to be a high-efficiency state. If the standard deviation of the current amplitude is greater than the preset standard deviation, the mean of the current amplitude is greater than the preset mean, and the load energy efficiency ratio is less than the preset value, the energy efficiency state of the industrial equipment is determined to be an inefficient state. If the current characteristic parameter exceeds the allowable range of the operating reference parameter, the energy efficiency status of the industrial equipment is determined to be an abnormally high efficiency status.

6. The industrial equipment management method based on current monitoring according to claim 3, characterized in that, Based on the historical operating data and the current waveform corresponding to the operating current, the failure probability of the industrial equipment is determined, specifically including: The RNN model is used to identify the current waveform corresponding to the operating current in order to determine the fault type corresponding to the current waveform. Based on the historical operating data, obtain the abnormal waveform corresponding to the fault type of the industrial equipment; The abnormal waveform is compared with the current waveform to determine the failure probability of the industrial equipment based on the degree of difference between the current waveform and the abnormal waveform.

7. The industrial equipment management method based on current monitoring according to claim 1, characterized in that, Before inputting the current data sequence into the pre-trained RNN model, the method further includes: Determine a training set consisting of the operating currents of multiple industrial devices; Based on the current data characteristics of the operating current, generate the corresponding equipment operating status label for the industrial equipment; The operating current is input into a preset RNN model for training, so that the RNN model can output the predicted equipment operating status label corresponding to the industrial equipment. Based on the cross-entropy loss function, the error value between the device operating state label and the predicted device operating state label is calculated, and the network parameters of the RNN model are updated using the error value until the error value meets the preset error value through the updated network parameters, thus obtaining the trained RNN model.

8. The industrial equipment management method based on current monitoring according to claim 3, characterized in that, Based on the obtained energy consumption status and fault modes, a scheduling plan for the industrial equipment is generated, specifically including: When the fault mode is the immediate fault mode, an early warning prompt is generated for the industrial equipment; When the fault mode is the predicted fault mode, the maintenance priority of the industrial equipment is determined based on the energy consumption status and the fault probability. Based on the maintenance priority, the maintenance sequence and maintenance cycle of the industrial equipment are determined to obtain a scheduling plan for the industrial equipment.

9. An industrial equipment management device based on current monitoring, characterized in that, The device includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform an industrial equipment management method based on current monitoring as described in any one of claims 1-8.

10. A non-volatile computer storage medium storing computer-executable instructions, characterized in that, The computer-executable instructions are set as follows: An industrial equipment management method based on current monitoring as described in any one of claims 1-8.

Images