A method and system for managing device operating conditions

Abstract

The embodiment of the application provides a kind of equipment working condition management method and system, the method comprises: obtaining the monitoring physical quantity of target equipment, deploying the sensor of monitoring physical quantity, and establishing platform communication protocol, receiving monitoring data;Monitoring data is preprocessed, and the multidimensional feature of monitoring data is extracted, combined to generate multidimensional vector, and the feature vector is standardized;Collect the health state vector of target equipment under different operating conditions, calculate the Mahalanobis distance of multidimensional vector to health state vector, determine the health index of target equipment under current operating condition;Determine the health index of target equipment based on health index, and determine the corresponding maintenance priority and maintenance strategy after risk assessment.

Description

Technical Field

[0001] This invention relates to the field of record management technology, and in particular to a method and system for managing equipment operating conditions. Background Technology

[0002] In managing the operating conditions of large-scale equipment, systems, and factories that involve multiple devices working together, some equipment is already equipped with numerous sensors to collect corresponding data and monitor its operating condition. This, combined with human resource support, enables comprehensive monitoring of equipment operating conditions.

[0003] However, current equipment condition monitoring technologies often suffer from significant delays, hindering proactive equipment maintenance. Furthermore, over-reliance on human expertise can reduce the accuracy of equipment condition assessments. For instance, staff may rely on a few key data points to determine equipment condition, failing to comprehensively evaluate all available data and leading to misjudgments. Summary of the Invention

[0004] To address the problems existing in the prior art, embodiments of the present invention provide a method and system for managing equipment operating conditions.

[0005] This invention provides a method for managing equipment operating conditions, the method comprising:

[0006] Acquire the physical quantities of the target device, deploy sensors to monitor these physical quantities, establish a platform communication protocol, and receive monitoring data;

[0007] The monitoring data is preprocessed, and multi-dimensional features of the monitoring data are extracted, combined to generate a multi-dimensional vector, and the feature vector is standardized.

[0008] Collect the health status vector of the target device under different operating conditions, calculate the Mahalanobis distance from the multidimensional vector to the health status vector, and determine the health index of the target device under the current operating condition;

[0009] Based on the aforementioned health indicators, the health index of the target equipment is determined, and after risk assessment, the corresponding maintenance priority and maintenance strategy are determined.

[0010] In one embodiment, the method further includes:

[0011] Collect the health status vectors of the target device under different operating conditions, and calculate the health baseline mean and health baseline covariance matrix of the health status vectors;

[0012] Obtain multidimensional vectors under the same conditions, calculate the distance between the multidimensional vectors and the mean of the health benchmark, and determine the Mahalanobis distance by combining the covariance matrix of the health benchmark.

[0013] In one embodiment, the method further includes:

[0014] ,

[0015] Where, d current Let X be the Mahalanobis distance, μ be the mean of the health baseline, and Σ be the covariance matrix of the health baseline.

[0016] In one embodiment, the method further includes:

[0017] The Mahalanobis distance is transformed using an exponential transformation formula:

[0018]

[0019] Where HI is an exponent in the range of 0-1, and d threshold Distance thresholds are set based on historical fault data or statistical distributions.

[0020] In one embodiment, the method further includes:

[0021] Based on the HI value, the health index of the target device is determined by comparing it with the preset state boundary.

[0022] Obtain multi-dimensional vectors of devices whose health index is lower than a preset indicator, evaluate the maintenance criticality of the corresponding devices based on the multi-dimensional vectors, and generate corresponding maintenance strategies.

[0023] This invention provides a management system for equipment operating conditions, the system comprising:

[0024] The acquisition module is used to acquire the physical quantities monitored by the target device, deploy sensors to monitor the physical quantities, establish a platform communication protocol, and receive monitoring data.

[0025] The feature module is used to preprocess the monitoring data, extract multi-dimensional features of the monitoring data, combine them to generate a multi-dimensional vector, and standardize the feature vector.

[0026] The indicator module is used to collect the health status vector of the target device under different operating conditions, calculate the Mahalanobis distance from the multidimensional vector to the health status vector, and determine the health indicators of the target device under the current operating condition.

[0027] The maintenance module is used to determine the health index of the target device based on the health indicators, and to determine the corresponding maintenance priority and maintenance strategy after risk assessment.

[0028] In one embodiment, the system further includes:

[0029] The collection module is used to collect the health status vector of the target device under different operating conditions, and calculate the health benchmark mean and health benchmark covariance matrix of the health status vector;

[0030] The calculation module is used to obtain multidimensional vectors under the same conditions, calculate the distance between the multidimensional vectors and the mean of the health benchmark, and determine the Mahalanobis distance by combining the health benchmark covariance matrix.

[0031] In one embodiment, the system further includes a Mahalanobis distance calculation module for calculating Mahalanobis distance, including:

[0032] ,

[0033] Where, d current Let X be the Mahalanobis distance, μ be the mean of the health baseline, and Σ be the covariance matrix of the health baseline.

[0034] This invention provides an electronic device, including a processor and a memory;

[0035] The processor is connected to the memory;

[0036] The memory is used to store executable program code;

[0037] The processor runs a program corresponding to the executable program code stored in the memory to perform the methods described in one or more embodiments.

[0038] This invention provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the above-described device operating condition management method.

[0039] In view of the above, in one or more embodiments of this specification, the physical quantities of the target device are acquired, sensors for monitoring these physical quantities are deployed, and a platform communication protocol is established to receive monitoring data. The monitoring data is preprocessed, and multi-dimensional features are extracted, combined to generate multi-dimensional vectors, and the feature vectors are standardized. Health status vectors of the target device under different operating conditions are collected, and the Mahalanobis distance from the multi-dimensional vectors to the health status vectors is calculated to determine the health indicators of the target device under the current operating condition. Based on the health indicators, the health index of the target device is determined, and after risk assessment, the corresponding maintenance priority and maintenance strategy are determined. This allows for early warning of various operating conditions of the equipment, and by comparing health status vectors under different equipment conditions, the equipment's operating condition can be determined more simply and directly, improving accuracy while reducing the technical requirements for human resources. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a flowchart of a method for managing equipment operating conditions provided in one embodiment of this specification.

[0042] Figure 2 This is a schematic diagram of the structure of a device operating condition management system provided in one embodiment of this specification.

[0043] Figure 3 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this specification. Detailed Implementation

[0044] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed merely to enable those skilled in the art to better understand and implement the subject matter described herein, and are not intended to limit the scope, applicability, or examples set forth in the claims. The function and arrangement of the elements discussed may be changed without departing from the scope of this specification. Various processes or components may be omitted, substituted, or added as needed in the various examples. For example, the described methods may be performed in a different order than described, and steps may be added, omitted, or combined. Furthermore, features described in some examples may be combined in other examples.

[0045] As used herein, the term "comprising" and its variations are open terms meaning "including but not limited to". The term "based on" means "at least partially based on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other definitions, whether explicit or implicit, may be included below. Unless explicitly indicated by the context, the definition of a term shall remain consistent throughout the specification.

[0046] like Figure 1 As shown, this embodiment of the invention provides a method for managing equipment operating conditions, including:

[0047] Step S102: Obtain the classification information of the target file, deploy IoT devices based on the classification information, and package the target file into a meta data package through standardized conversion. The target file includes personal files, contract files, process files, and permission files.

[0048] Specifically, for monitoring the operating conditions of target equipment, historical fault modes of the target equipment can be obtained. Based on these historical fault modes, the physical quantities (such as vibration and temperature) that need to be monitored for the target equipment can be determined. After configuring sensors to acquire these physical quantities, a communication protocol is set between the device and the edge node / cloud platform, such as through the MQTT protocol, to achieve asynchronous communication between multiple devices and the platform in the Internet of Things. The various types of data acquired from the multiple target devices through asynchronous communication are then standardized. For example, the structure, field names, data types, and units of each type of message are preset. This eliminates data heterogeneity and lays the foundation for subsequent automated data processing.

[0049] Step S104: Based on the classification information, introduce the corresponding adaptive anomaly detection algorithm for the metadata package to perform data cleaning and generate a structured archive dataset.

[0050] Specifically, data from different sources undergoes preprocessing, including time synchronization and signal denoising. Time synchronization adds a uniform, precise microsecond-level timestamp to all data packets from different sensors, resolving timestamp misalignment issues caused by independent sensor clock drift or asynchronous acquisition. Signal denoising applies wavelet thresholding to each sensor data stream (especially high-frequency vibration signals), eliminating noise and timing misalignment interference.

[0051] Furthermore, multi-dimensional features of the data packet are acquired, including but not limited to: time-domain feature extraction, directly calculated from the waveform of the vibration signal, such as root mean square (RMS), kurtosis, peak-to-peak value, etc.; frequency-domain feature extraction, performing a Fast Fourier Transform (FFT) on the vibration signal to map the signal from the time domain to the frequency domain; and time-frequency domain feature extraction, generating a time-frequency map of the signal through continuous wavelet transform. All features extracted from the time, frequency, and time-frequency domains (such as RMS, kurtosis, 100Hz band energy, etc.) are combined into a multi-dimensional vector, representing a complete "state snapshot" of the device at a certain point in time. Additionally, for each feature dimension, Z-score standardization can be performed, calculating its mean and standard deviation separately, and then transforming it to (feature value - mean) / standard deviation. This converts all features to a unified scale with a mean of 0 and a standard deviation of 1, achieving feature standardization and eliminating the influence of dimensions.

[0052] The multidimensional vector can be decomposed not only into time-domain features (such as RMS, kurtosis, and peak-to-peak value), frequency-domain features (such as 1 / 3 octave band energy), and time-frequency-domain features (obtained through continuous wavelet transform), but also into thermodynamic and temperature features collected by other sensors, such as absolute temperature values ​​and rates of temperature change; electrical parameter features, including current and power characteristics; and acoustic and ultrasonic features, etc. Therefore, the final "state snapshot" can be structured to include multiple physical features, comprehensively representing the current state of the device.

[0053] Step S106: Obtain the feature vector corresponding to the archive dataset, perform integrated classification on the archive dataset based on the feature vector, and perform distributed storage of the metadata data of different classifications.

[0054] Specifically, feature vectors of the equipment under normal conditions are collected, and their feature mean and covariance matrix are calculated to construct a "health benchmark cloud". The health benchmark cloud covers feature vectors of all typical normal operating conditions of the equipment.

[0055] After determining the baseline vector for health, for the feature vectors input in real time, the Mahalanobis distance to the health baseline cloud can be calculated. The Mahalanobis distance can automatically handle the differences in units and magnitudes of different features without the need for manual normalization.

[0056]

[0057] Where X is the current feature vector, μ is the mean of the health baseline, and Σ is the health baseline covariance matrix.

[0058] The calculation process for the health baseline mean μ includes: calculating the average value of all samples for each feature dimension (such as vibration RMS, kurtosis, temperature, etc.). These average values ​​are arranged in dimensional order to form a vector, called the health baseline mean. This represents the center point or centroid of the health state in the multidimensional feature space. The health baseline covariance matrix Σ is a square matrix, where the diagonal elements are the variance of each feature itself, reflecting the fluctuation range of that feature under normal conditions. The off-diagonal elements are the covariances between different feature pairs, quantifying the degree of linear correlation between these features (e.g., vibration and temperature usually rise synchronously when the load increases). The health baseline cloud is essentially a multivariate statistical model centered on the health baseline mean, with its distribution shape described by the health baseline covariance matrix. It defines the elastic boundary of the fluctuation range of the normal state.

[0059] Then the Mahalanobis distance is converted into an exponent in the range of 0-1, including:

[0060]

[0061] Where, d threshold This is a distance threshold set based on historical fault data or statistical distribution (e.g., the 99th percentile of the Mahalanobis distance for healthy states). When d current When HI approaches 0, it approaches 1, indicating good health. current Approaching or exceeding d threshold When HI is close to 0 or negative, it indicates an anomaly. This condenses complex, multi-dimensional feature information into a single, interpretable health indicator, enabling continuous quantitative assessment of equipment status. Furthermore, for the aforementioned health monitoring, feature data of the equipment under different operating modes (e.g., no load, half load, full load) can be collected, and K-means clustering algorithm can be used to divide these data into several operating condition intervals. For each operating condition interval, the Mahalanobis distance distribution of its health status is calculated, and an independent threshold d is set for that operating condition. threshold Then, based on the current operating parameters, the current feature vector is determined, and the corresponding threshold is dynamically selected for calculation.

[0062] Step S108: Register the corresponding event channel based on the classification information, obtain IoT device data through the event channel, and then update the archive data in the distributed storage.

[0063] Specifically, based on the Health Index (HI) calculated in the above steps, clear state boundaries are established, such as using 0.8 and 0.5 as dividing lines. When HI is greater than 0.8, it indicates that the equipment is in a healthy state and only routine monitoring is required. When HI is less than 0.8 but greater than 0.5, it indicates that the equipment has begun to experience measurable degradation and requires planned maintenance. When HI is less than 0.5, the equipment performance has severely deteriorated and immediate intervention is required. Thus, by monitoring changes in the HI value in real time, corresponding warnings or actions are triggered when the HI value crosses the stage boundary.

[0064] In addition, maintenance strategies can be optimized using FMEA (Failure Mode and Effects Analysis) to assess equipment risk. This includes: after determining the HI (Highest Hit Rate) value, equipment with HI values ​​less than 0.8 can be evaluated in segments to identify multi-dimensional vectors for these devices, evaluating their severity, occurrence, and detectability from three perspectives. These three risk perspectives are then multiplied to calculate the Risk Priority Number (RPN) to determine the equipment's criticality. Severity represents the severity of a problem, occurrence represents the probability of a problem occurring, and detectability represents the difficulty of detecting a problem through data analysis. A higher RPN value indicates a higher maintenance criticality. Then, using equipment criticality and resource constraints as two dimensions, a decision matrix is ​​constructed to construct the maintenance priority matrix, determining the order of maintenance. Equipment with high criticality and low resource consumption is prioritized for maintenance, while equipment with low criticality and high resource consumption can have its maintenance appropriately delayed. Furthermore, maintenance decisions are output, generating structured maintenance work orders, including suggested maintenance time windows, maintenance steps, required spare parts, etc.

[0065] This invention provides a method for managing equipment operating conditions. The method involves acquiring monitored physical quantities of the target equipment, deploying sensors to monitor these quantities, establishing a platform communication protocol, and receiving monitoring data. The monitoring data is preprocessed, and multi-dimensional features are extracted, combined to generate multi-dimensional vectors, and then standardized. Health status vectors of the target equipment under different operating conditions are collected, and the Mahalanobis distance from the multi-dimensional vectors to the health status vectors is calculated to determine the health indicators of the target equipment under the current operating condition. Based on these health indicators, a health index for the target equipment is determined, and a risk assessment is performed to determine the corresponding maintenance priority and maintenance strategy. This method enables early warning of various equipment operating conditions and, by comparing health status vectors under different equipment conditions, allows for a simpler and more direct determination of equipment operating conditions, improving accuracy while reducing the technical requirements for human resources.

[0066] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a device operating condition management system provided in an embodiment of this application. For example... Figure 2 As shown, the system includes:

[0067] The acquisition module S202 is used to acquire the monitored physical quantities of the target device, deploy sensors to monitor the physical quantities, establish a platform communication protocol, and receive monitoring data.

[0068] The feature module S204 is used to preprocess the monitoring data, extract multi-dimensional features of the monitoring data, combine them to generate a multi-dimensional vector, and standardize the feature vector.

[0069] The indicator module S206 is used to collect the health status vector of the target device under different operating conditions, calculate the Mahalanobis distance from the multidimensional vector to the health status vector, and determine the health indicators of the target device under the current operating condition.

[0070] The maintenance module S208 is used to determine the health index of the target device based on the health indicators, and to determine the corresponding maintenance priority and maintenance strategy after risk assessment.

[0071] In another embodiment, a device operating condition management system further includes:

[0072] The collection module is used to collect the health status vector of the target device under different operating conditions, and calculate the health benchmark mean and health benchmark covariance matrix of the health status vector;

[0073] The calculation module is used to obtain multidimensional vectors under the same conditions, calculate the distance between the multidimensional vectors and the mean of the health benchmark, and determine the Mahalanobis distance by combining the health benchmark covariance matrix.

[0074] In another embodiment, a management system for equipment operating conditions further includes a Mahalanobis distance calculation module for calculating Mahalanobis distance, including:

[0075] ,

[0076] Where, d current Let X be the Mahalanobis distance, μ be the mean of the health baseline, and Σ be the covariance matrix of the health baseline.

[0077] Those skilled in the art will clearly understand that the technical solutions of the embodiments of this application can be implemented by means of software and / or hardware. In this specification, "unit" and "module" refer to software and / or hardware that can independently complete or cooperate with other components to complete a specific function, wherein the hardware may be, for example, a field-programmable gate array (FPGA), an integrated circuit (IC), etc.

[0078] Each processing unit and / or module in the embodiments of this application can be implemented by an analog circuit that implements the functions described in the embodiments of this application, or by software that executes the functions described in the embodiments of this application.

[0079] See Figure 3 It shows a schematic diagram of the structure of an electronic device according to an embodiment of this application, which can be used to implement... Figure 1 The method in the illustrated embodiment. (As shown) Figure 3 As shown, the electronic device 300 may include: at least one processor 301, at least one network interface 304, user interface 303, memory 305, and at least one communication bus 302.

[0080] The communication bus 302 is used to enable communication between these components.

[0081] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0082] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0083] The processor 301 may include one or more processing cores. The processor 301 connects to various parts within the electronic device 300 using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display on the screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0084] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. Figure 3 As shown, the memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and program instructions.

[0085] exist Figure 3 In the illustrated electronic device 300, the user interface 303 is mainly used to provide an input interface for the user and acquire user input data; while the processor 301 can be used to call the image-based interactive application stored in the memory 305 and specifically perform the following operations: acquire the monitored physical quantities of the target device, deploy sensors for monitoring the physical quantities, establish a platform communication protocol, and receive monitoring data; preprocess the monitoring data, extract multi-dimensional features of the monitoring data, combine them to generate multi-dimensional vectors, and standardize the feature vectors; collect the health status vectors of the target device under different operating conditions, calculate the Mahalanobis distance from the multi-dimensional vectors to the health status vectors, and determine the health indicators of the target device under the current operating conditions; determine the health index of the target device based on the health indicators, and determine the corresponding maintenance priority and maintenance strategy after risk assessment.

[0086] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0087] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0088] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0090] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0091] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0092] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0093] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0094] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

Claims

1. A method for managing equipment operating conditions, the method comprising: Acquire the physical quantities of the target device, deploy sensors to monitor these physical quantities, establish a platform communication protocol, and receive monitoring data; The monitoring data is preprocessed, and multi-dimensional features of the monitoring data are extracted, combined to generate a multi-dimensional vector, and the feature vector is standardized. Collect the health status vector of the target device under different operating conditions, calculate the Mahalanobis distance from the multidimensional vector to the health status vector, and determine the health index of the target device under the current operating condition; Based on the aforementioned health indicators, the health index of the target equipment is determined, and after risk assessment, the corresponding maintenance priority and maintenance strategy are determined.

2. The method according to claim 1, characterized in that, The process of collecting health state vectors of the target device under different operating conditions and calculating the Mahalanobis distance from the multidimensional vector to the health state vector includes: Collect the health status vectors of the target device under different operating conditions, and calculate the health baseline mean and health baseline covariance matrix of the health status vectors; Obtain multidimensional vectors under the same conditions, calculate the distance between the multidimensional vectors and the mean of the health benchmark, and determine the Mahalanobis distance by combining the covariance matrix of the health benchmark.

3. The method according to claim 2, characterized in that, The formula for calculating the Mahalanobis distance includes: ， Where, d current Let X be the Mahalanobis distance, μ be the mean of the health baseline, and Σ be the covariance matrix of the health baseline.

4. The method according to claim 3, characterized in that, The method further includes: The Mahalanobis distance is transformed using an exponential transformation formula: ， Where HI is an exponent in the range of 0-1, and d threshold Distance thresholds are set based on historical fault data or statistical distributions.

5. The method according to claim 4, characterized in that, The process of determining the health index of the target device based on the health indicators, and then determining the corresponding maintenance priority and maintenance strategy after risk assessment, includes: Based on the HI value, the health index of the target device is determined by comparing it with the preset state boundary. Obtain multi-dimensional vectors of devices whose health index is lower than a preset indicator, evaluate the maintenance criticality of the corresponding devices based on the multi-dimensional vectors, and generate corresponding maintenance strategies.

6. A management system for equipment operating conditions, characterized in that, The system includes; The acquisition module is used to acquire the physical quantities monitored by the target device, deploy sensors to monitor the physical quantities, establish a platform communication protocol, and receive monitoring data. The feature module is used to preprocess the monitoring data, extract multi-dimensional features of the monitoring data, combine them to generate a multi-dimensional vector, and standardize the feature vector. The indicator module is used to collect the health status vector of the target device under different operating conditions, calculate the Mahalanobis distance from the multidimensional vector to the health status vector, and determine the health indicators of the target device under the current operating condition. The maintenance module is used to determine the health index of the target device based on the health indicators, and to determine the corresponding maintenance priority and maintenance strategy after risk assessment.

7. The system according to claim 6, characterized in that, The system also includes: The collection module is used to collect the health status vector of the target device under different operating conditions, and calculate the health benchmark mean and health benchmark covariance matrix of the health status vector; The calculation module is used to obtain multidimensional vectors under the same conditions, calculate the distance between the multidimensional vectors and the mean of the health benchmark, and determine the Mahalanobis distance by combining the health benchmark covariance matrix.

8. The system according to claim 7, characterized in that, The system also includes a Mahalanobis distance calculation module for calculating Mahalanobis distance, including: ， Where, d current Let X be the Mahalanobis distance, μ be the mean of the health baseline, and Σ be the covariance matrix of the health baseline.

9. An electronic device, comprising a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, in order to perform the method as described in any one of claims 1-5.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of claims 1-5.

Images