Industrial equipment operation state identification method, system, equipment and medium

Abstract

The invention provides an industrial equipment operation state identification method, system, equipment and medium, and belongs to the technical field of industrial automatic measurement and control. The method comprises the following steps: synchronously acquiring voltage and current signals, vibration acceleration signals and mechanical position switch signals of industrial equipment through an electric power sensor, a vibration sensor and a travel switch; performing feature extraction and noise reduction processing on the voltage and current signal, the vibration acceleration signal and the mechanical position switch signal to obtain electric power feature data, vibration feature data and switch state data as data sources; synchronizing the electric power feature data, the vibration feature data and the switch state data to a unified time sequence, and converting each feature data into a unified quantitative score value; distributing a weight coefficient for each quantitative score value, calculating a comprehensive score through weighted summation, and outputting an equipment state according to the comprehensive score; and regularly verifying the recognition accuracy of each data source based on historical data, and dynamically adjusting the weight coefficient.

Description

Technical Field

[0001] This invention belongs to the field of industrial automation measurement and control technology, and more specifically relates to a method, system, equipment and medium for identifying the operating status of industrial equipment. Background Technology

[0002] Accurate identification of the operating status of industrial equipment is a key technological foundation for realizing intelligent manufacturing, energy management, and predictive maintenance. In existing technologies, identification methods based on "electrical fingerprinting" (non-intrusive load monitoring, NILM) have been widely applied. This method collects voltage and current signals from the equipment and extracts features such as power and harmonics during switching moments or steady-state operation as unique identifiers, thereby determining the equipment type, start-up and shutdown times, and operating status. For example, published patent CN115564324A proposes a method using multi-level margin window sliding sampling to extract load waveform features, aiming to improve the accuracy of electrical fingerprint identification.

[0003] However, this type of identification method, which relies on a single power fingerprint, has significant limitations in practical industrial applications. Its identification accuracy and reliability are often constrained by the following factors: First, the industrial power grid environment is complex. The start-up and shutdown of large adjacent equipment can cause instantaneous fluctuations in grid voltage or frequency distortion. These interferences directly change the actual power consumption waveform of the monitored equipment, causing the fingerprint features to deviate and resulting in misjudgments, such as misjudging normally operating equipment as idle or failing to identify its low-load operating state. Second, this method is highly sensitive to data quality. Signal noise and sampling loss during the data acquisition process directly affect the accuracy of feature extraction, thereby leading to a decline in the performance of the identification model.

[0004] Although existing research attempts to improve accuracy by refining sampling algorithms, it still fundamentally remains limited by the single data source. Power fingerprinting technology itself is still under development, lacking sufficient differentiation between different devices with similar characteristics. Furthermore, existing solutions generally fail to adequately consider complex interference factors in industrial environments, such as long transient processes, spike noise, and base load fluctuations. Consequently, their recognition models exhibit low robustness, making it difficult to meet the stringent requirements of industrial applications for accuracy and stability in state recognition.

[0005] Therefore, there is an urgent need for an industrial equipment operating status identification scheme with stronger anti-interference capabilities and more reliable identification results, in order to overcome the inherent defects of a single sensing mode and ensure accurate and stable status monitoring even in complex industrial environments. Summary of the Invention

[0006] To address the above problems, the present invention aims to provide a method, system, device, and medium for identifying the operating status of industrial equipment. Through multimodal sensor data fusion and dynamic weight optimization, the anti-interference capability and reliability of industrial equipment operating status identification in complex industrial environments are significantly improved.

[0007] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, embodiments of this application provide a method for identifying the operating status of industrial equipment, including: Voltage and current signals, vibration acceleration signals, and mechanical position switch signals of industrial equipment are collected synchronously using power sensors, vibration sensors, and limit switches. The voltage and current signals, vibration acceleration signals, and mechanical position switch signals are respectively subjected to feature extraction and noise reduction processing to obtain power feature data, vibration feature data, and switch status data, which serve as data sources. The power characteristic data, vibration characteristic data, and switch status data are synchronized to a unified time series, and the power characteristic data, vibration characteristic data, and switch status data are respectively converted into unified quantitative scoring values; Assign a weight coefficient to each quantitative score, calculate a comprehensive score by weighted summation, and output the device status based on the comprehensive score; The recognition accuracy of each data source is verified periodically based on historical data, and the weighting coefficients are dynamically adjusted.

[0008] In an optional implementation, the step of synchronously acquiring voltage and current signals, vibration acceleration signals, and mechanical position switch signals of industrial equipment through power sensors, vibration sensors, and limit switches includes: Configure a unified external clock source for the power sensor, vibration sensor and limit switch, so that the three can collect voltage and current signals, vibration acceleration signals and mechanical position switch signals of industrial equipment according to a preset sampling rate, so that the collected signal data frames have the same time start point.

[0009] In an optional implementation, the step of performing feature extraction and noise reduction processing on the voltage and current signals, vibration acceleration signals, and mechanical position switch signals to obtain electrical feature data, vibration feature data, and switch status data includes: For voltage and current signals, an adaptive notch filter is used to filter out 50Hz power frequency interference; the average active power within a time window is calculated, and the standard deviation of the amplitude of a specific harmonic is calculated; if data points are missing, linear interpolation is used to complete them and generate power characteristic data. For vibration acceleration signals, a wavelet threshold denoising algorithm based on the db4 wavelet basis is used to remove environmental noise; a sliding window maximum value extraction algorithm is used to process the denoised data, with a window length of 0.1 seconds, to extract the maximum amplitude within the window; if the maximum amplitude exceeds the sensor's range, the maximum amplitude is marked as abnormal data and excluded; vibration feature data is generated based on the processed maximum amplitude. For mechanical position switch signals, a signal with three consecutive high-level samples is determined as a valid trigger signal; the duration of the valid trigger signal is calculated, and if the duration is less than 0.5 seconds, it is determined as an invalid trigger and processed as an untriggered state; switch status data is generated based on the determination result.

[0010] In an optional implementation, synchronizing the power characteristic data, vibration characteristic data, and switch status data to a unified time series, and converting the power characteristic data, vibration characteristic data, and switch status data into unified quantitative scoring values, includes: Based on the acquisition time of the power characteristic data, higher frequency vibration characteristic data and switch status data are aggregated. The arithmetic mean of the vibration characteristic data within 1 second is calculated to generate one synchronized vibration characteristic data per second. The switch status data within 1 second is used to determine the status using a majority voting algorithm to generate one synchronized switch status data per second. The synchronized power characteristic data, vibration characteristic data, and switch status data are quantified into scoring values ​​through the following process: Read the switch status information from the synchronized switch status data. If it is in the triggered state, the corresponding switch status data quantization score is 100. If it is in the non-triggered state, the corresponding switch status data quantization score is 0. Read the vibration frequency from the synchronized vibration characteristic data; if the vibration frequency is in the range of 50-200Hz and the amplitude is greater than 0.5g, the corresponding vibration characteristic data quantization score is 80; if the vibration frequency is in the range of 50-200Hz and the amplitude is less than or equal to 0.5g, the corresponding vibration characteristic data quantization score is 30; otherwise, the corresponding vibration characteristic data quantization score is 0. Read the average active power and the standard deviation of harmonic amplitude from the synchronized power characteristic data; if the average active power is greater than 30% of the rated power and the standard deviation of harmonic amplitude is greater than 120% of the benchmark value, the corresponding power characteristic data quantification score is 80; if only one of the above conditions is met, the corresponding power characteristic data quantification score is 40; otherwise, the corresponding power characteristic data quantification score is 0.

[0011] In an optional implementation, the step of assigning weight coefficients to each quantitative score value, calculating a comprehensive score through weighted summation, and outputting the device status based on the comprehensive score includes: The weighting coefficient for the quantitative score of switch status data is set to 0.4, the weighting coefficient for the quantitative score of vibration characteristic data is set to 0.35, and the weighting coefficient for the quantitative score of power characteristic data is set to 0.25. The overall score is calculated using the formula: Overall Score = (Quantitative Score of Power Characteristic Data × 0.25) + (Quantitative Score of Vibration Characteristic Data × 0.35) + (Quantitative Score of Switch Status Data × 0.4). If the overall score is greater than or equal to 60 points, the equipment status is determined to be in operation; if the overall score is less than 40 points, the equipment status is determined to be in idle state; if the overall score is greater than or equal to 40 points and less than 60 points, the equipment status is determined to be in a contradictory state, and an abnormal alarm signal is triggered.

[0012] In an optional implementation, the step of periodically verifying the recognition accuracy of each data source based on historical data and dynamically adjusting the weighting coefficients includes: Periodically extract data samples from historical data where the equipment status is determined to be in operation, and compare them with the actual working records of the equipment; The independent identification accuracy rates of the switch status data, vibration characteristic data, and electrical characteristic data in the data sample were calculated separately. The corresponding weighting coefficients are dynamically adjusted based on the calculated range of independent recognition accuracy.

[0013] In one alternative implementation, the specific subharmonics are the 3rd and 5th harmonics.

[0014] Secondly, embodiments of this application also provide an industrial equipment operating status identification system, including: The multi-source data acquisition module is used to synchronously acquire voltage and current signals, vibration acceleration signals, and mechanical position switch signals of industrial equipment through power sensors, vibration sensors, and limit switches. The data preprocessing module is used to perform feature extraction and noise reduction on the voltage and current signals, vibration acceleration signals and mechanical position switch signals respectively, to obtain power feature data, vibration feature data and switch status data as data sources; The feature synchronization and quantization module is used to synchronize the power feature data, vibration feature data and switch status data to a unified time series, and to convert the power feature data, vibration feature data and switch status data into unified quantitative score values ​​respectively. The weighted voting decision module is used to assign weight coefficients to each quantitative score value, calculate the comprehensive score by weighted summation, and output the device status based on the comprehensive score; The dynamic optimization module is used to periodically verify the recognition accuracy of each data source based on historical data and dynamically adjust the weight coefficients.

[0015] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the industrial equipment operating status identification method described in any of the above descriptions.

[0016] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the industrial equipment operating status identification method described in any of the above claims.

[0017] As can be seen from the above technical solutions, the present invention has the following advantages: The industrial equipment operating status identification method provided in this application ensures the homogeneity of multimodal data through hardware synchronous acquisition of three-source sensors (electricity, vibration, and limit switch) using a unified external clock source. It effectively extracts interference-resistant electrical and vibration features using specific preprocessing methods such as adaptive notch filtering and wavelet threshold denoising. Furthermore, it solves the synchronization problem of multi-source heterogeneous data through time series alignment and majority voting mechanisms. Further, it employs a rule-based quantitative scoring and weighted voting fusion algorithm to transform physical features into a unified decision-making basis, significantly improving the fault tolerance and reliability of status identification. This method also periodically verifies the accuracy of each data source and adaptively adjusts the weight coefficients, enabling the system to overcome long-term problems such as equipment aging and sensor performance drift. Ultimately, it achieves high-precision and robust identification of equipment operation, idleness, and abnormal states in complex industrial environments, providing a reliable data foundation for energy management, predictive maintenance, and production optimization in intelligent manufacturing.

[0018] This application achieves hardware synchronous acquisition by configuring a unified external clock source for power sensors, vibration sensors, and limit switches, ensuring that multi-source heterogeneous data have the same time start point, thus laying a timing foundation for achieving accurate data fusion.

[0019] This application employs an adaptive notch filter to remove 50Hz power frequency interference from the power grid, and calculates the standard deviation of the average active power and the amplitude of a specific harmonic as power characteristics. Simultaneously, it uses a db4 wavelet base wavelet threshold noise reduction algorithm to remove environmental vibration noise, and then uses a 0.1-second sliding window maximum value extraction algorithm to enhance periodic impact characteristics. Finally, it implements anti-jitter processing for the limit switch signal by continuously sampling high-level confirmation three times and checking the shortest duration of 0.5 seconds, thus realizing the extraction of anti-interference specific characteristic data from the original signal.

[0020] This application achieves spatiotemporal synchronization and quantitative comparability of multi-source heterogeneous feature data by using the power data acquisition time as a benchmark, taking the arithmetic mean of higher frequency vibration data, aggregating switch status data using a majority voting algorithm, and establishing a rule system that maps physical features to a unified scoring scale. For example, a switch trigger scores 100 points, vibration simultaneously meeting the 50-200Hz frequency band and 0.5g amplitude scores 80 points, and power simultaneously meeting the power exceeding the rated value by 30% and the harmonic exceeding the benchmark value by 120%, etc.

[0021] This application assigns initial weighting coefficients of 0.4, 0.35, and 0.25 to switch status data, vibration characteristic data, and power characteristic data, respectively. It calculates the comprehensive score using a weighted summation formula and sets a dual-threshold decision-making mechanism with a 60-point operating threshold and a 40-point idle threshold. This enables fault-tolerant decision-making and early warning of state contradictions based on multi-source information fusion.

[0022] This application compares historical operating status samples with real work order records on a regular basis, calculates the independent recognition accuracy of each data source, and dynamically adjusts the weighting coefficients proportionally according to the changes in accuracy. This enables the system to adaptively optimize for long-term factors such as equipment aging and sensor performance drift, ensuring the continuous stability and reliability of recognition performance. Attached Figure Description

[0023] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart illustrating the industrial equipment operating status identification method provided in this application.

[0025] Figure 2 This is a schematic diagram of the industrial equipment operation status identification system provided in this application.

[0026] Figure 3 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0027] The various embodiments of this disclosure will be described more fully in the following detailed description of the specific steps of the method for identifying the operating status of industrial equipment. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0028] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] Please see Figure 1 The diagram shown is a flowchart of a method for identifying the operating status of industrial equipment in a specific embodiment. The method includes: S1: Synchronously acquire voltage and current signals, vibration acceleration signals, and mechanical position switch signals of industrial equipment through power sensors, vibration sensors, and limit switches.

[0031] In this specific implementation, this step achieves synchronous acquisition of multi-source data through power sensors, vibration sensors, and limit switches. To ensure data timing consistency, a unified external clock source is configured for all sensors to ensure that the acquired voltage and current signals, vibration acceleration signals, and mechanical position switch signals have the same starting point.

[0032] In practice, the power sensor acquires the equipment's voltage and current signals at a frequency of 1 time per second. The vibration sensor acquires the equipment's vibration acceleration signals at a frequency of 10 times per second. The limit switch acquires the mechanical position switch signals at a frequency of 10 times per second. Hardware synchronization signals ensure that all sensors start acquiring data synchronously, with timestamp errors controlled within milliseconds.

[0033] This step lays the temporal foundation for multimodal data fusion through a synchronous acquisition mechanism, ensuring the accuracy of subsequent processing.

[0034] S2: Perform feature extraction and noise reduction on the voltage and current signals, vibration acceleration signals and mechanical position switch signals respectively to obtain power feature data, vibration feature data and switch status data, which serve as data sources.

[0035] In a specific implementation, when extracting power characteristics from voltage and current signals, an adaptive notch filter is used to filter out the 50Hz fundamental frequency interference from the power grid. The average active power within a time window is calculated as the energy consumption characteristic, and the standard deviations of the 3rd and 5th harmonic amplitudes are calculated as the operational stability characteristics. When data points are missing, linear interpolation is used to complete the data to ensure data continuity.

[0036] When preprocessing the vibration acceleration signal, a wavelet threshold denoising algorithm based on the db4 wavelet basis is used to remove environmental vibration noise, retaining the 50-200Hz characteristic frequency band of equipment operation. A sliding window maximum extraction algorithm is then used to process the denoised data, with a window length of 0.1 seconds, highlighting the periodic vibration characteristics of the equipment. When the vibration amplitude exceeds the sensor's range, the data is marked as abnormal and excluded.

[0037] When preprocessing the mechanical position switch signal, digital debouncing is used. A valid trigger is determined only after three consecutive high-level samples. The duration of the valid trigger signal is calculated; if the duration is less than 0.5 seconds, it is considered an invalid trigger and processed as a non-triggered state.

[0038] After preprocessing, electrical characteristic data, vibration characteristic data, and switch status data are generated.

[0039] S3: Synchronize the power characteristic data, vibration characteristic data, and switch status data to a unified time series, and convert the power characteristic data, vibration characteristic data, and switch status data into unified quantitative scoring values ​​respectively.

[0040] In a specific implementation, feature data of different frequencies are synchronized to a unified time series. Using the acquisition time of the power feature data as a reference, higher-frequency vibration feature data and switch status data are aggregated. Specifically, the arithmetic mean of the vibration feature data within one second is calculated to generate one synchronized vibration feature data per second. The switch status data within one second is used to determine the status using a majority voting algorithm, generating one synchronized switch status data per second.

[0041] Then, a unified scoring system is used for feature quantification, converting power characteristic data, vibration characteristic data, and switch status data into unified quantitative score values. Specifically, switch status information is read from the synchronized switch status data, vibration frequency is read from the synchronized vibration characteristic data, and the average active power and standard deviation of harmonic amplitude are read from the synchronized power characteristic data. These data are used as the evaluation basis.

[0042] The unified scoring system is as follows: Limit switches are quantized as follows: 100 points when triggered and 0 points when not triggered; vibration characteristic data are quantized as follows: 80 points when the frequency range of 50-200Hz is greater than 0.5g; 30 points when only frequency matching is met; otherwise, 0 points. Power characteristic data are quantized as follows: 80 points when the average active power is greater than 30% of the rated power and the standard deviation of harmonic amplitude is greater than 120% of the benchmark value; 40 points when only one condition is met; otherwise, 0 points.

[0043] S4: Assign weight coefficients to each quantitative score value, calculate the comprehensive score by weighted summation, and output the device status based on the comprehensive score.

[0044] In a specific implementation, weighting coefficients are first assigned to the quantitative score values ​​of each data source: the weighting coefficient for switch status data is 0.4, the weighting coefficient for vibration characteristic data is 0.35, and the weighting coefficient for power characteristic data is 0.25.

[0045] Then, the weighted summation formula is used to calculate the comprehensive score: Comprehensive score = Quantitative score of power characteristic data × 0.25 + Quantitative score of vibration characteristic data × 0.35 + Quantitative score of switch status data × 0.4.

[0046] Finally, a dual-threshold mechanism is used for status determination: a comprehensive score of 60 or higher indicates an operating state; a comprehensive score of less than 40 indicates an idle state; and a comprehensive score between 40 and 60 indicates a status conflict, triggering an abnormal alarm signal. When a status conflict occurs, a detailed diagnostic report is generated to guide maintenance personnel in inspecting the equipment.

[0047] S5: Regularly verify the recognition accuracy of each data source based on historical data, and dynamically adjust the weight coefficients.

[0048] In a specific implementation, data samples identified as being in an operational state are periodically extracted from historical data and compared with actual equipment operating records for verification. The independent identification accuracy rates of switch status data, vibration characteristic data, and power characteristic data are calculated separately, and the actual performance indicators of each data source are calculated.

[0049] The weighting coefficients are dynamically adjusted based on accuracy changes: when the accuracy of a data source drops beyond a set threshold, its weighting coefficient is reduced accordingly, while the weighting coefficients of other data sources are increased proportionally. A long-term performance monitoring mechanism is established to issue sensor verification or maintenance reminders when the accuracy of a data source remains consistently low.

[0050] For example, a monthly verification mechanism is established, randomly selecting 100 "running" status samples from the database each month and comparing them with actual machine tool processing records for verification. The independent accuracy rate of each data source is calculated: Accuracy = Number of correct identifications / Total number of samples. A weight adjustment rule is set: when the accuracy rate of a data source drops by more than 5%, its weight is reduced by 5%, and the reduced weight is proportionally distributed to other data sources. Simultaneously, a sensor health assessment model is established; when the accuracy rate of a sensor consistently falls below 70%, the system issues a sensor maintenance reminder. Through this dynamic optimization mechanism, the system can adapt to changes such as equipment aging and sensor performance degradation, maintaining long-term identification accuracy.

[0051] This dynamic optimization mechanism adapts to factors such as equipment aging and environmental changes, maintaining long-term stability in recognition accuracy. Monthly system performance reports are generated to provide decision support for preventative maintenance.

[0052] In this embodiment, by fusing three-source sensing information—electricity, vibration, and mechanical position—and employing hardware synchronous acquisition and specific preprocessing techniques such as adaptive notch filtering and wavelet threshold denoising, anti-interference feature data is effectively extracted. Furthermore, multi-source heterogeneous data is transformed into a unified decision-making basis through time series alignment and quantitative scoring rules. The innovative use of a weighted voting fusion algorithm and dynamic weight optimization mechanism not only significantly improves the anti-interference capability and reliability of equipment status identification in complex industrial environments, achieving refined differentiation of operating, idle, and abnormal idling states, but also, through periodic accuracy verification and adaptive weight adjustment, enables the system to possess long-term robustness in the face of equipment aging and environmental changes. Ultimately, this provides highly reliable data support for refined energy management, predictive maintenance, and production optimization in intelligent manufacturing processes, effectively improving equipment utilization and reducing operation and maintenance costs.

[0053] like Figure 2As shown, the following are embodiments of the industrial equipment operating status identification system provided in this disclosure. This system and the industrial equipment operating status identification methods of the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the industrial equipment operating status identification system, please refer to the embodiments of the above industrial equipment operating status identification methods.

[0054] An industrial equipment operating status identification system includes: a multi-source data acquisition module, a data preprocessing module, a feature synchronization and quantification module, a weighted voting decision module, and a dynamic optimization module.

[0055] The multi-source data acquisition module is used to synchronously acquire voltage and current signals, vibration acceleration signals, and mechanical position switch signals of industrial equipment through power sensors, vibration sensors, and limit switches.

[0056] The data preprocessing module is used to perform feature extraction and noise reduction on the voltage and current signals, vibration acceleration signals and mechanical position switch signals respectively, to obtain power feature data, vibration feature data and switch status data as data sources.

[0057] The feature synchronization and quantization module is used to synchronize the power feature data, vibration feature data and switch status data to a unified time series, and to convert the power feature data, vibration feature data and switch status data into unified quantitative score values ​​respectively.

[0058] The weighted voting decision module is used to assign weight coefficients to each quantitative score value, calculate the comprehensive score by weighted summation, and output the device status based on the comprehensive score.

[0059] The dynamic optimization module is used to periodically verify the recognition accuracy of each data source based on historical data and dynamically adjust the weight coefficients.

[0060] The industrial equipment operation status identification system provided in this embodiment effectively solves the problems of susceptibility to interference and insufficient identification accuracy of single sensing modes by collaboratively utilizing data from power sensors, vibration sensors, and limit switches, and employing key technologies such as specific preprocessing, feature quantization synchronization, and dynamic weighted fusion. This system significantly improves the accuracy and reliability of status identification, possesses the ability to finely distinguish complex operating states, and ensures long-term stability through an adaptive optimization mechanism, providing effective technical support for intelligent management of industrial equipment.

[0061] Figure 3 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0062] The industrial equipment operating status identification method provided in this application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, electronic devices include, but are not limited to, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0063] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0064] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0065] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0066] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0067] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0068] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0069] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0070] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0071] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0072] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0073] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0074] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0075] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0076] The aforementioned electronic device realizes the industrial equipment operation status identification method of this application by integrating power, vibration and position three-source sensing information and adopting specific noise reduction processing, multimodal feature quantization synchronization and dynamic weight optimization fusion decision technology. It achieves a significant improvement in the anti-interference, reliability and long-term adaptive capability of industrial equipment status identification in complex environments, and finally realizes the comprehensive beneficial effect of accurate status perception and intelligent operation and maintenance management.

[0077] The storage medium provided in this application stores a program product capable of implementing a method for identifying the operating status of industrial equipment.

[0078] Methods for identifying the operating status of industrial equipment include: Voltage and current signals, vibration acceleration signals, and mechanical position switch signals of industrial equipment are collected synchronously using power sensors, vibration sensors, and limit switches. The voltage and current signals, vibration acceleration signals, and mechanical position switch signals are respectively subjected to feature extraction and noise reduction processing to obtain power feature data, vibration feature data, and switch status data, which serve as data sources. The power characteristic data, vibration characteristic data, and switch status data are synchronized to a unified time series, and the power characteristic data, vibration characteristic data, and switch status data are respectively converted into unified quantitative scoring values; Assign a weight coefficient to each quantitative score, calculate a comprehensive score by weighted summation, and output the device status based on the comprehensive score; The recognition accuracy of each data source is verified periodically based on historical data, and the weighting coefficients are dynamically adjusted.

[0079] In some possible implementations, the industrial equipment operating status identification method of this disclosure can be implemented as a program product that includes program code. When the program product is run on a terminal device, the program code is used to cause the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0080] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0081] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An industrial equipment operation state recognition method characterized by comprising: The method comprises the following steps: Synchronously collecting voltage and current signals, vibration acceleration signals and mechanical position switch signals of an industrial equipment through a power sensor, a vibration sensor and a travel switch; Respectively extracting features and performing noise reduction processing on the voltage and current signals, the vibration acceleration signals and the mechanical position switch signals to obtain power feature data, vibration feature data and switch state data as data sources; Synchronizing the power feature data, the vibration feature data and the switch state data to a unified time sequence, and respectively converting the power feature data, the vibration feature data and the switch state data into unified quantified score values; Assigning a weight coefficient to each quantified score value, calculating a comprehensive score through weighted summation, and outputting an equipment state according to the comprehensive score; Periodically verifying the identification accuracy of each data source based on historical data, and dynamically adjusting the weight coefficient.

2. The industrial equipment operation state recognition method according to claim 1, characterized by, The synchronously collecting voltage and current signals, vibration acceleration signals and mechanical position switch signals of an industrial equipment through a power sensor, a vibration sensor and a travel switch comprises: Configuring a unified external clock source for the power sensor, the vibration sensor and the travel switch, so that the three respectively collect voltage and current signals, vibration acceleration signals and mechanical position switch signals of the industrial equipment at a preset sampling rate, so that the collected signal data frames have the same time starting point.

3. The industrial equipment operation state recognition method according to claim 1, characterized by, The respectively extracting features and performing noise reduction processing on the voltage and current signals, the vibration acceleration signals and the mechanical position switch signals to obtain power feature data, vibration feature data and switch state data comprises: For voltage and current signals, an adaptive notch filter is used to filter out 50Hz power frequency interference; the average value of active power in a time window is calculated, and the standard deviation of the amplitude of a specific harmonic is calculated; if a data point is missing, linear interpolation is used to complete it, and power feature data is generated; For vibration acceleration signals, a wavelet threshold denoising algorithm based on db4 wavelet basis is used to remove environmental noise; a sliding window maximum value extraction algorithm is used to process the denoised data, the window length is 0.1 seconds, and the maximum amplitude in the window is extracted; if the maximum amplitude exceeds the sensor range, the maximum amplitude is marked as abnormal data and excluded; vibration feature data is generated based on the processed maximum amplitude; For mechanical position switch signals, signals with three consecutive sampling values as high level are determined as valid trigger signals; the duration of the valid trigger signals is calculated, and if the duration is less than 0.5 seconds, it is determined as invalid trigger and processed as untriggered state; switch state data is generated based on the determination result.

4. The industrial equipment operation state recognition method according to claim 3, characterized by, The synchronizing the power feature data, the vibration feature data and the switch state data to a unified time sequence, and respectively converting the power feature data, the vibration feature data and the switch state data into unified quantified score values comprises: The higher frequency vibration characteristic data and the switch state data are aggregated based on the collection time of the power characteristic data, the vibration characteristic data within 1 second is calculated for an arithmetic average value, and 1 second 1 vibration characteristic data after synchronization is generated; the switch state data within 1 second is determined for a state by using a majority voting algorithm, and 1 second 1 switch state data after synchronization is generated; The synchronized power characteristic data, vibration characteristic data and switch state data are quantified into score values through the following process: The switch state information is read from the synchronized switch state data, if it is a trigger state, the corresponding switch state data quantification score value is 100, if it is a non-trigger state, the corresponding switch state data quantification score value is 0; The vibration frequency is read from the synchronized vibration characteristic data; if the vibration frequency is within the range of 50-200Hz and the amplitude is greater than 0.5g, the corresponding vibration characteristic data quantification score value is 80; if the vibration frequency is within the range of 50-200Hz and the amplitude is less than or equal to 0.5g, the corresponding vibration characteristic data quantification score value is 30; otherwise, the corresponding vibration characteristic data quantification score value is 0; The active power average value and the standard deviation of the harmonic amplitude are read from the synchronized power characteristic data; if the active power average value is greater than 30% of the rated power and the standard deviation of the harmonic amplitude is greater than 120% of the reference value, the corresponding power characteristic data quantification score value is 80; if the active power average value is greater than 30% of the rated power or the standard deviation of the harmonic amplitude is greater than 120% of the reference value, the corresponding power characteristic data quantification score value is 40; otherwise, the corresponding power characteristic data quantification score value is 0.

5. The industrial equipment operation state recognition method according to claim 4, characterized by, The weight coefficients are assigned to each quantification score value, the comprehensive score is calculated by weighted summation, and the equipment state is output according to the comprehensive score, including: The weight coefficient of the quantification score value of the switch state data is set to 0.4, the weight coefficient of the quantification score value of the vibration characteristic data is set to 0.35, and the weight coefficient of the quantification score value of the power characteristic data is set to 0.25; The comprehensive score is calculated according to the formula: comprehensive score=(power characteristic data quantification score value x 0.25)+(vibration characteristic data quantification score value x 0.35)+(switch state data quantification score value x 0.4); If the comprehensive score is greater than or equal to 60 points, the equipment state is determined to be a running state; if the comprehensive score is less than 40 points, the equipment state is determined to be an idle state; if the comprehensive score is greater than or equal to 40 points and less than 60 points, the equipment state is determined to be a state contradiction state, and an abnormal alarm signal is triggered.

6. The industrial equipment operation state recognition method according to claim 5, characterized by, The identification accuracy of each data source is verified based on historical data periodically, and the weight coefficients are dynamically adjusted, including: The data samples of the equipment state determined to be a running state in the historical data are extracted periodically, and compared with the real work record of the equipment; The independent identification accuracy of the switch state data, the vibration characteristic data and the power characteristic data in the data samples is respectively counted; The corresponding weight coefficient is dynamically adjusted according to the change range of the calculated independent identification accuracy.

7. The industrial equipment operation state identification method according to claim 3, characterized by, The specific harmonic is the 3rd harmonic and the 5th harmonic.

8. An industrial equipment operating status identification system, characterized in that, The system adopts the industrial equipment operation state recognition method as claimed in any one of claims 1 to 7. The system comprises: a multi-source data acquisition module for synchronously acquiring voltage and current signals, vibration acceleration signals and mechanical position switch signals of the industrial equipment through power sensors, vibration sensors and travel switches; a data preprocessing module for performing feature extraction and noise reduction processing on the voltage and current signals, vibration acceleration signals and mechanical position switch signals respectively to obtain power feature data, vibration feature data and switch state data as data sources; a feature synchronization and quantization module for synchronizing the power feature data, vibration feature data and switch state data to a unified time sequence and converting the power feature data, vibration feature data and switch state data into unified quantized score values respectively; a weighted voting decision module for assigning weight coefficients to each quantized score value, calculating a comprehensive score through weighted summation and outputting the equipment state according to the comprehensive score; a dynamic optimization module for periodically verifying the recognition accuracy of each data source based on historical data and dynamically adjusting the weight coefficients.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the steps of the industrial equipment operation state recognition method as claimed in any one of claims 1 to 7.

10. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the steps of the industrial equipment operation state recognition method as claimed in any one of claims 1 to 7.

Images