Equipment state early warning method and system, electronic equipment and computer program product

Abstract

The invention relates to an equipment state early warning method and system, electronic equipment and a computer program product. The method comprises the following steps: receiving a current state value of each component of equipment detected and output by a sensor; determining the fault risk of each component according to the current state value of each component; obtaining the coupling degree between the components, and determining the health degree of each component according to the fault risk of each component and the coupling degree between the components; determining the health degree of the equipment according to the health degree of each component; performing equipment state early warning according to the health degree of the equipment; the real demand of high-reliability operation and maintenance is met, and the state of the equipment is evaluated more comprehensively and accurately, so that the accuracy of early warning is improved.

Description

Technical Field

[0001] This invention relates to the field of equipment monitoring technology, specifically to an equipment status early warning method and system, electronic equipment, and computer program product. Background Technology

[0002] With the continuous improvement of industrial automation and informatization, the integration level and operational complexity of equipment in production systems are increasing, and various key equipment have become the core links to ensure production continuity, safety, and efficiency. At the same time, the operating environment of equipment is becoming increasingly harsh, the workload is significantly increasing, and the status values ​​are showing characteristics such as high dynamism, multivariate coupling, and nonlinear evolution. As a result, traditional periodic maintenance and manual inspection methods can no longer meet the practical needs of high-reliability operation and maintenance. Summary of the Invention

[0003] The purpose of this invention is to propose a device status early warning method and system, electronic equipment, and computer program product to meet the practical needs of high-reliability operation and maintenance, and to more comprehensively and accurately assess the status of the device, thereby improving the accuracy of early warning.

[0004] To achieve the above objectives, the present invention provides a device status early warning method, comprising:

[0005] Receive the current status values ​​of each component of the device from the sensor output;

[0006] The failure risk of each component is determined based on its current state value.

[0007] The coupling degree between the components is obtained, and the health of each component is determined based on the failure risk of each component and the coupling degree between the components.

[0008] The health status of the device is determined based on the health status of each component.

[0009] The device status is alerted based on the device's health status.

[0010] Preferably, determining the failure risk of each component based on its current state value includes:

[0011] The failure risk of a component is determined using the following formula:

[0012]

[0013] Among them, P fault (i,t) represents the failure risk of the i-th component at time t, P health(i,t-1) represents the health state of the i-th component at time t-1, and ΔX(i,t) represents the change in the state value of the i-th component at time t relative to its state value at time t-1. max S represents the maximum state value of the i-th component when the device is operating normally. failure (i,t-1) represents the historical fault state of the i-th component at time t-1, and X(i,t) represents the state value of the i-th component at time t. normal (i,t) is the state value of the i-th component in the ideal state, X range It is the allowable fluctuation range of the i-th component when the equipment is running normally. α1, α2, α3, and α4 are weighting coefficients, β1 is the coefficient of the maximum output value of the nonlinear function, and β2 is the adjustment coefficient of the nonlinear growth rate.

[0014] Preferably, determining the health of each component based on the failure risk of each component and the coupling degree between the components includes:

[0015] The health of a component is determined using the following formula:

[0016]

[0017] Among them, S com (i,t) represents the health status of the i-th component at time t, N is the number of components in the device, and Γ ij N represents the coupling degree between the j-th component and the i-th component in terms of physical or energy flow structure. i|j This indicates that, among all historical moments when the j-th component fails, the i-th component exhibits metric fluctuations within a set time window. N j β is the number of failures of the j-th component, and β is the amplification factor of the frequency adjustment factor.

[0018] Preferably, determining the health status of the device based on the health status of each component includes:

[0019] The health status of the equipment is determined using the following formula:

[0020]

[0021] Among them, S system (t) represents the health status of the device at time t, W i It is the weight of the i-th component.

[0022] Preferably, the step of providing device status warnings based on the device's health includes:

[0023] When the health status of the device is less than or equal to a preset threshold, a device status warning is issued; when the health status of the device is greater than the preset threshold, no device status warning is issued.

[0024] The present invention also provides a system for performing the above-described device status early warning method, the system comprising:

[0025] The sensor data receiving module is used to receive the current status values ​​of various components of the device detected and output by the sensors;

[0026] The component fault determination module is used to determine the fault risk of each component based on the current state value of each component.

[0027] The component health determination module is used to obtain the coupling degree between the components and determine the health of each component based on the failure risk of each component and the coupling degree between the components.

[0028] The device health determination module is used to determine the health of the device based on the health of each component.

[0029] The device early warning module is used to provide device status warnings based on the health status of the device.

[0030] The present invention also provides an electronic device, comprising:

[0031] A communication interface used for communicating with other electronic devices;

[0032] Memory is used to store computer program instructions;

[0033] A processor is configured to execute the computer program instructions to support the electronic device in implementing the methods described above.

[0034] The present invention also provides a computer program product, including computer program instructions, which instruct a computer device to perform the operation corresponding to the above method.

[0035] The present invention has the following beneficial effects:

[0036] This invention achieves a shift from passive maintenance to proactive early warning by real-time monitoring and analysis of equipment status. It can promptly identify and resolve potential problems, effectively compensating for the shortcomings of traditional methods and meeting the high reliability requirements of modern industry for equipment operation and maintenance. Furthermore, this invention not only considers the current status values ​​of each component of the equipment detected by sensors, but also takes into account the coupling degree between components. Traditional early warning methods only focus on the status of individual components, ignoring the mutual influence between components. The coupling degree between components reflects their interdependence in equipment operation. When a component is at risk of failure, it may affect other components through coupling. This invention determines the health of components by comprehensively considering failure risk and coupling degree, enabling a more comprehensive and accurate assessment of the equipment status, thereby improving the accuracy of early warning. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required in the description of the embodiments 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.

[0038] Figure 1 This is a flowchart of a device status early warning method according to an embodiment of the present invention.

[0039] Figure 2 This is a structural diagram of a device status early warning system according to an embodiment of the present invention. Detailed Implementation

[0040] The detailed description of the accompanying drawings is intended to illustrate the present embodiments of the invention and is not intended to represent only the forms in which the invention can be implemented. It should be understood that the same or equivalent functions can be accomplished by different embodiments intended to be included within the spirit and scope of the invention.

[0041] like Figure 1 As shown, one embodiment of the present invention provides a device status early warning method, including the following steps:

[0042] Step S10: Receive the current status values ​​of each component of the device detected and output by the sensor;

[0043] Specifically, various types of sensors (such as temperature sensors, pressure sensors, vibration sensors, current sensors, flow sensors, etc.) are typically installed on the equipment. These sensors are responsible for monitoring the operating status of different components of the equipment (such as motors, bearings, pumps, valves, circuit boards, etc.) in real time. The sensors continuously collect data and convert this data into signals or values ​​that can be recognized by the system (i.e., "current status values"). For example, a temperature sensor will output the current temperature value of the bearing, and a vibration sensor will output the vibration amplitude value of the equipment casing. The system needs to first receive and acquire these real-time data from various sensors as the basis for subsequent analysis.

[0044] Step S20: Determine the failure risk of each component based on the current state value of each component;

[0045] Specifically, after obtaining the real-time status values ​​of each component, the system needs to analyze these values ​​to determine the likelihood of each component failing. This can be done through threshold comparison, trend analysis, machine learning, and other methods to determine the failure risk of each component.

[0046] Threshold comparison refers to comparing the current state value with a preset normal range (threshold). If a state value exceeds the normal range, it may mean that the component has a potential problem.

[0047] Trend analysis refers to observing the trend of state values ​​over time; even if the current value is within the normal range, if it shows a continuous upward or downward trend, it may indicate future failures.

[0048] Machine learning refers to using historical data and machine learning models (such as anomaly detection models, classification models, etc.) to identify whether the current state value deviates from the normal pattern. The model can learn the characteristics of the equipment under normal operation and different fault states, thereby more accurately judging the fault risk level corresponding to the current state.

[0049] After the above analysis, the system will assign a "failure risk" score to each component, which indicates the likelihood of the component failing at present; for example, the risk can be represented by a value between 0 and 1.

[0050] Step S30: Obtain the coupling degree between each component, and determine the health of each component based on the failure risk of each component and the coupling degree between each component;

[0051] Specifically, the components of a device do not operate in isolation but are interconnected and mutually influential. "Coupling degree" is used to quantify the strength of this mutual influence. For example, a gearbox failure may affect the motor connected to it via the drive shaft. Coupling degree can be obtained in various ways, such as modeling based on the device's design drawings and physical connections, or estimating it by analyzing the correlation between component state values ​​in historical data. Coupling degree can be a matrix representing the degree of mutual influence between any two components. After knowing the failure risk of each component and the degree of mutual influence between them, the system needs to further calculate the "health" of each component. The health of a component depends not only on its own state (failure risk) but also on the state of other components coupled with it. If a component's own state is acceptable, but its closely coupled components have a high risk, then the health of this component will decrease accordingly because it is likely to be affected soon.

[0052] Step S40: Determine the health status of the device based on the health status of each component;

[0053] Specifically, after obtaining the health status of each component of the equipment, these component health statuses need to be aggregated to form an "equipment health status" representing the overall state of the entire equipment. This can be an aggregation or weighted average process, where different weights are assigned to the health status of each component based on factors such as its importance in the equipment, cost, and impact on overall functionality. For example, the weight of core components (such as the main drive motor) may be higher than that of auxiliary components (such as indicator lights). Then, the health status of all components is multiplied by their corresponding weights and summed, or other aggregation functions are used (such as the minimum value method, where the equipment health status depends on the least healthy component) to obtain the final equipment health status. The equipment health status can be a continuous value (such as 0 to 100, where 100 represents perfect health) or a discrete level (such as healthy, alert, warning, danger).

[0054] Step S50: Issue a device status warning based on the health status of the device;

[0055] Specifically, the system can determine whether to issue an alert and the level of the alert, or the specific content of the alert message, based on the calculated health status of the device.

[0056] Warning information may include the following:

[0057] Fault type warning: Based on the equipment's operating parameters (such as vibration, temperature, etc.), the system will combine historical data to predict possible fault types (e.g., motor failure, transmission system abnormality, etc.).

[0058] Failure probability: The system calculates the probability of equipment failure and provides a risk probability of failure based on historical data and current equipment status to help maintenance personnel assess the urgency of the failure.

[0059] Expected failure time: Based on the current health status of the equipment and the failure development trend, the system can also predict the failure time or the failure window period, helping maintenance personnel to prepare in advance.

[0060] The warning information will be sent to the operation and maintenance personnel through the system's notification module (such as SMS, email, APP push, etc.) so that they can take timely measures such as repair or replacement of parts to avoid complete equipment failure and downtime;

[0061] Based on the severity of the warning information, maintenance personnel can adjust their daily maintenance plans, prioritize high-risk equipment, reduce potential downtime, ensure the normal operation of equipment, and minimize losses caused by failures.

[0062] In some embodiments, determining the failure risk of each component based on its current state value includes:

[0063] The failure risk of a component is determined using the following formula:

[0064]

[0065] Among them, P fault (i,t) represents the failure risk of the i-th component at time t, with a value range of [0,1]. health (i,t-1) represents the health state of the i-th component at time t-1, with a value range of [0,1]. ΔX(i,t) is the change in the state value of the i-th component at time t relative to its state value at time t-1. Since the change in sensor data has physical units, it is standardized as a dimensionless rate of change. X max S represents the maximum state value of the i-th component when the device is operating normally. failure (i,t-1) represents the historical fault state of the i-th component at time t-1, and X(i,t) represents the state value of the i-th component at time t. normal (i,t) is the state value of the i-th component in the ideal state, X rangeα1 represents the allowable fluctuation range of the i-th component during normal operation of the equipment. α2, α3, and α4 are weighting coefficients. The impact of health status on fault risk is linear, so a weighting coefficient α1 is used to represent the contribution of health status to the overall fault risk. α2 is the weighting coefficient for the impact of sensor change risk, used to adjust the degree of influence of nonlinear mapping output on the total fault risk value. α3 is the weighting coefficient for the impact of historical fault modes, measuring the contribution of the equipment's past fault frequency / severity to the current risk, extracted from maintenance logs. α4 is the weighting coefficient for the impact of anomaly, controlling the impact of the current sensor anomaly degree on fault risk. β1 is the coefficient for the maximum value of the nonlinear function output, set through normalization constraints, usually set to 1. β2 is the nonlinear growth rate adjustment coefficient, determining the slope of the sensor change in the mapping, obtained by fitting the relationship curve between historical sensor changes and fault occurrence frequency using the least squares method.

[0066] In some embodiments, determining the health of each component based on the failure risk of each component and the coupling degree between the components includes:

[0067] The health of a component is determined using the following formula:

[0068]

[0069] Among them, S com (i,t) represents the health status of the i-th component at time t, reflecting whether the i-th device component is operating normally at the current time. N is the number of components in the device. ij N represents the coupling degree between the j-th component and the i-th component in terms of physical or energy flow structure, assigned a value according to engineering definition. i|j This represents the number of times, within all historical moments when the j-th component fails, the i-th component is simultaneously or subsequently observed to exhibit index fluctuations (such as abnormal temperature, increased vibration, current jumps, etc.) within a set time window. N j is the number of failures of the j-th component, and β is the amplification coefficient of the frequency adjustment factor, with a value of (0.5~5.0), used to adjust the degree of correction of the influence of statistical behavior on static structure.

[0070] In some embodiments, determining the health of the device based on the health of each component includes:

[0071] The health status of the equipment is determined using the following formula:

[0072]

[0073] Among them, S system (t) represents the health status of the device at time t, W i It is the weight of the i-th component.

[0074] Specifically, the weights are set to reflect the degree of impact of different components on the overall health of the equipment. For example, if the failure of a certain component (such as the main bearing) will cause the entire equipment to stop, its weight may be set higher. Conversely, the weight of a minor component may be set lower. The weights can be determined based on the equipment's structure, functional importance, historical failure data, expert experience, etc. The formula can integrate the health status information of each component to obtain a single indicator that reflects the overall status of the equipment.

[0075] In some embodiments, the step of providing device status alerts based on the health of the device includes:

[0076] When the health status of the device is less than or equal to a preset threshold, a device status warning is issued; when the health status of the device is greater than the preset threshold, no device status warning is issued.

[0077] Specifically, a "preset threshold" is a pre-defined boundary value used to distinguish between good and bad equipment status. It can be determined based on equipment characteristics, historical operating data, maintenance experience, and production requirements. For example, if equipment health is quantified from 0 to 100, the preset threshold might be set to 70 or 80. This threshold represents the boundary at which the system considers the equipment to have entered a state of "requiring attention" or "increased potential risk." For instance, if the preset threshold is 70 and the calculated equipment health is 65, the system will determine that the equipment is in poor condition, requiring attention from relevant personnel and issuing corresponding warning information (such as displaying a warning icon, sending a notification, or logging). This reflects the system's sensitivity to potential risks and its timely response capability, ensuring that attention is received as soon as the equipment's condition begins to decline.

[0078] When the device health level is higher than the preset threshold, the system considers the device to be in an acceptable health state with no obvious risk that requires immediate alarm. In this case, the system will not issue any warning signal, and the device can continue to operate normally or maintain a normal monitoring level. This avoids unnecessary alarm interference and reduces "alarm fatigue," which is when operators become less attentive to alarm information due to too many alarms that may not be urgent.

[0079] like Figure 2 As shown, another embodiment of the present invention also provides a system for performing the device status early warning method described in the above embodiments, the system comprising:

[0080] The sensor data receiving module 1 is used to receive the current status values ​​of various components of the device detected and output by the sensor;

[0081] Component fault determination module 2 is used to determine the fault risk of each component based on the current state value of each component;

[0082] The component health determination module 3 is used to obtain the coupling degree between the components and determine the health of each component based on the failure risk of each component and the coupling degree between the components.

[0083] Device health determination module 4 is used to determine the health of the device based on the health of each component; and

[0084] The device early warning module 5 is used to provide device status early warnings based on the health status of the device.

[0085] It should be noted that the system provided in this embodiment can be used to execute the methods described in the above embodiments. Therefore, the contents not described in detail in this embodiment can be obtained by referring to the contents of the methods in the above embodiments, and will not be repeated here.

[0086] Another embodiment of the present invention provides an electronic device, comprising:

[0087] A communication interface used for communicating with other electronic devices;

[0088] Memory is used to store computer program instructions;

[0089] A processor is configured to execute the computer program instructions to support the electronic device in implementing the methods described in the embodiments above.

[0090] In this embodiment, the memory mainly includes a program storage area and a data storage area. The program storage area can store the operating device, applications required for at least one function, etc., and the data storage area can store related data, etc. Furthermore, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart media card (SMC), a secure digital card (SD), and a flash card, or other volatile solid-state storage devices.

[0091] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, or the processor can be any conventional processor. The processor is the control center of the electronic device and uses various interfaces and lines to connect the various parts of the electronic device.

[0092] Another embodiment of the present invention provides a computer program product including computer program instructions that instruct a computer device to perform operations corresponding to the methods described in the above embodiments.

[0093] Specifically, the computer program product includes a series of computer program instructions, which are codes written in a computer program. These instructions define how to perform specific operations. These instructions are designed to be loaded onto a computer device and instruct the device to perform specific operations, which refer to the various steps in the device status early warning method described in the above embodiments. In this way, the computer program product of this embodiment provides a complete software solution that can run on various computer devices to implement the device status early warning method of the above embodiments.

[0094] The various embodiments of the present invention have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for early warning of equipment status, characterized in that, include: Receive the current status values ​​of each component of the device from the sensor output; The failure risk of each component is determined based on its current state value. The coupling degree between the components is obtained, and the health of each component is determined based on the failure risk of each component and the coupling degree between the components. The health status of the device is determined based on the health status of each component. The device status is alerted based on the device's health status.

2. The method according to claim 1, characterized in that, The step of determining the failure risk of each component based on its current state value includes: The failure risk of a component is determined using the following formula: Among them, P fault (i,t) represents the failure risk of the i-th component at time t, P health (i,t-1) represents the health state of the i-th component at time t-1, and ΔX(i,t) represents the change in the state value of the i-th component at time t relative to its state value at time t-1. max S represents the maximum state value of the i-th component when the device is operating normally. failure (i,t-1) represents the historical fault state of the i-th component at time t-1, and X(i,t) represents the state value of the i-th component at time t. normal (i,t) is the state value of the i-th component in the ideal state, X range It is the allowable fluctuation range of the i-th component when the equipment is running normally. α1, α2, α3, and α4 are weighting coefficients, β1 is the coefficient of the maximum output value of the nonlinear function, and β2 is the adjustment coefficient of the nonlinear growth rate.

3. The method according to claim 2, characterized in that, The process of determining the health of each component based on the failure risk of each component and the coupling degree between the components includes: The health of a component is determined using the following formula: Among them, S com (i,t) represents the health status of the i-th component at time t, N is the number of components in the device, and Γ ij N represents the coupling degree between the j-th component and the i-th component in terms of physical or energy flow structure. i|j This indicates that, among all historical moments when the j-th component fails, the i-th component exhibits metric fluctuations within a set time window. N j β is the number of failures of the j-th component, and β is the amplification factor of the frequency adjustment factor.

4. The method according to claim 3, characterized in that, Determining the health status of the device based on the health status of each component includes: The health status of the equipment is determined using the following formula: Among them, S system (t) represents the health status of the device at time t, W i It is the weight of the i-th component.

5. The method according to claim 4, characterized in that, The method of providing device status warnings based on the device's health includes: When the health status of the device is less than or equal to a preset threshold, a device status warning is issued; when the health status of the device is greater than the preset threshold, no device status warning is issued.

6. A system for executing the equipment status early warning method according to any one of claims 1 to 5, characterized in that, The system includes: The sensor data receiving module is used to receive the current status values ​​of various components of the device detected and output by the sensors; The component fault determination module is used to determine the fault risk of each component based on the current state value of each component. The component health determination module is used to obtain the coupling degree between the components and determine the health of each component based on the failure risk of each component and the coupling degree between the components. The device health determination module is used to determine the health of the device based on the health of each component. The device early warning module is used to provide device status warnings based on the health status of the device.

7. An electronic device, characterized in that, include: A communication interface used for communicating with other electronic devices; Memory is used to store computer program instructions; A processor for executing the computer program instructions to support the electronic device in implementing the method according to any one of claims 1 to 5.

8. A computer program product, characterized in that, It includes computer program instructions that instruct a computer device to perform an operation corresponding to the method described in any one of claims 1 to 5.

Images