Equipment maintenance triggering method and system based on state echo
By analyzing the equipment status echo stream, vector state abrupt changes, energy accumulation trends, and autonomous suppression failure behaviors in the equipment are identified. Combined with historical strategies for equipment maintenance, this solves the problems of identifying multivariate coupling conflicts and delayed response in traditional methods, and improves equipment operation and maintenance efficiency.
Patent Information
- Application Number
- CN202510879906.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-27
- Publication Date
- 2025-11-18
AI Technical Summary
Existing equipment maintenance methods rely on prediction and rules, making it difficult to identify conflicts in the coupled behaviors of multiple variables. Furthermore, traditional methods are prone to failure or false alarms in complex environments and fail to effectively capture abnormal signals of delayed response.
By collecting equipment operating status data, analyzing the delayed response of variables, extracting state echo streams, identifying vector state abrupt changes, energy accumulation trends, and autonomous suppression failure behaviors, and combining historical maintenance strategies for maintenance.
It enables equipment maintenance to be triggered without the need for manual pre-setting of time points or cycles, improving equipment operation and maintenance efficiency, accurately identifying equipment anomalies and performing timely maintenance.
Smart Images
Figure CN120974150A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of equipment maintenance technology, and more specifically, relates to an equipment maintenance triggering method and system based on status echo. Background Technology
[0002] In the field of equipment operation and maintenance, existing systems mostly rely on single-variable threshold judgments, making it difficult to identify behavioral conflicts arising from the coupling of multiple variables. For example, an increase in current accompanied by a decrease in temperature may be an early signal of a control loop fault, but traditional methods struggle to detect such coupling contradictions.
[0003] In addition, some traditional maintenance methods rely on a large number of preset rules (such as "maintenance is required after 1000 hours of operation" or "an alarm will be triggered if the temperature is >80°C"). These rules are prone to failure or frequent false alarms when the operating conditions are varied and the environment is complex. Furthermore, traditional methods tend to use immediate event triggering mechanisms, without paying attention to important abnormal signals carried by delayed responses, such as slowly accumulating thermal decay and electrical hysteresis.
[0004] Therefore, there is an urgent need for a technical solution that can address the technical problems of dependency prediction and dependency rules in existing equipment maintenance methods. Summary of the Invention
[0005] To address the above technical problems, this invention proposes a device maintenance triggering method based on status echo, comprising:
[0006] Collect equipment operating status data, detect anomalies, and analyze the delayed response of each variable in the operating status data within a certain time window after the anomaly, thereby extracting the current status echo stream. The variables in the operating status data constitute a time-series variable sequence.
[0007] Analyze whether there are vector state abrupt changes, energy accumulation trends, and autonomous inhibition failure behaviors among the variables from the current state echo stream. If all three are satisfied, they are combined into a contradictory behavior group.
[0008] The historical state echo stream of the device and the corresponding historical maintenance strategy are invoked to find the historical state echo stream that matches the current state echo stream, and the device is maintained according to the corresponding historical maintenance strategy.
[0009] Furthermore, anomalies are detected, and the delayed response of each variable in the operational status data is analyzed within a certain time window after the anomaly, thereby extracting the current status echo stream, specifically including:
[0010] Calculate the first derivative of each variable in the running status data, and identify the variables corresponding to the first derivative results that exceed the preset abnormal change threshold as outliers;
[0011] The residual of each outlier point within the backward time window is calculated as the delayed response vector, and the local window echo intensity of each backward time window is calculated based on the delayed response vector. The local window echo intensities of multiple local windows constitute the current state echo stream.
[0012] Furthermore, analyzing whether there are vector state abrupt changes between variables from the current state echo stream specifically includes: extracting the change in the vector at the current time in the time series variable sequence, and the change in the vector at a certain time step forward from the current time, and calculating the product between the two;
[0013] If the product result is greater than the preset product threshold, and the echo intensity of the local window corresponding to the vector at the current time is greater than the preset echo intensity threshold, then the vector at the current time has a vector state change.
[0014] Furthermore, analyzing whether there is an energy accumulation trend among the variables in the current state echo stream specifically includes: if Starting from the backward time window t′, the echo intensity of the local window corresponding to the backward time window t′ shows an energy accumulation trend, where k′ is the index of the backward time window, T is the number of backward time windows, E(t+k′) is the time at t, E(t+k′-1) is the sign function, and γ is the energy accumulation judgment threshold.
[0015] Furthermore, analyzing whether there is autonomous suppression failure behavior among variables from the current state echo stream specifically includes: if the difference between the adjusted anomaly point and the current anomaly point is greater than a preset reference threshold after the device autonomously adjusts the current anomaly point, then there is autonomous suppression failure behavior.
[0016] Furthermore, a historical state echo stream matching the current state echo stream is found, and the device is maintained according to the corresponding historical maintenance strategy. Specifically, this includes: finding a historical anomaly point matching a certain anomaly point, finding the historical state echo stream corresponding to the historical anomaly point, and determining whether the change in local window echo intensity in the historical state echo stream is less than a preset echo intensity change threshold after the device is maintained according to the corresponding historical maintenance strategy. If so, the device is maintained according to the historical maintenance strategy; otherwise, a new maintenance strategy is adopted.
[0017] This invention also proposes a device maintenance triggering system based on status echo, comprising:
[0018] The status echo extraction module is used to collect the operating status data of the equipment, detect abnormal points, and analyze the delayed response of each variable in the operating status data within a certain time window after the abnormality, thereby extracting the current status echo stream. The variables in the operating status data form a time-series variable sequence.
[0019] The module for identifying contradictory behavior groups is used to analyze whether there are vector state abrupt changes, energy accumulation trends, and autonomous inhibition failure behaviors among variables from the current state echo stream. If all three are satisfied, they are combined into a contradictory behavior group.
[0020] The maintenance module is used to call the device's historical status echo stream and corresponding historical maintenance strategy, find the historical status echo stream that matches the current status echo stream, and perform device maintenance according to the corresponding historical maintenance strategy.
[0021] Furthermore, anomalies are detected, and the delayed response of each variable in the operational status data is analyzed within a certain time window after the anomaly, thereby extracting the current status echo stream, specifically including:
[0022] Calculate the first derivative of each variable in the running status data, and identify the variables corresponding to the first derivative results that exceed the preset abnormal change threshold as outliers;
[0023] The residual of each outlier point within the backward time window is calculated as the delayed response vector, and the local window echo intensity of each backward time window is calculated based on the delayed response vector. The local window echo intensities of multiple local windows constitute the current state echo stream.
[0024] Furthermore, analyzing whether there are vector state abrupt changes between variables from the current state echo stream specifically includes: extracting the change in the vector at the current time in the time series variable sequence, and the change in the vector at a certain time step forward from the current time, and calculating the product between the two;
[0025] If the product result is greater than the preset product threshold, and the echo intensity of the local window corresponding to the vector at the current time is greater than the preset echo intensity threshold, then the vector at the current time has a vector state change.
[0026] Furthermore, analyzing whether there is an energy accumulation trend among the variables in the current state echo stream specifically includes: if Starting from the backward time window t′, the echo intensity of the local window corresponding to the backward time window t′ shows an energy accumulation trend, where k′ is the index of the backward time window, T is the number of backward time windows, E(t+k′) is the time at t, E(t+k′-1) is the sign function, and γ is the energy accumulation judgment threshold.
[0027] In summary, the technical solutions conceived by this invention have the following beneficial effects compared with the prior art:
[0028] This invention achieves a device maintenance triggering mechanism that does not require manual preset timing or cycle by identifying the state echo stream formed during equipment operation. The technical solution of this invention automatically determines whether maintenance intervention is required based on vector state mutations, energy accumulation trends, and autonomous suppression of failure behaviors, breaking the traditional maintenance system that relies on manual planning or preset rules, and improving equipment operation and maintenance efficiency. Attached Figure Description
[0029] Figure 1 This is a flowchart of the method in Embodiment 1 of the present invention;
[0030] Figure 2 This is a system structure diagram of Embodiment 2 of the present invention. Detailed Implementation
[0031] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.
[0032] The method provided by this invention can be implemented in a terminal environment that may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.
[0033] A processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the terminal, and performs various functions and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and by calling data stored in the storage medium.
[0034] Storage media can include random access memory (RAM) or read-only memory (ROM). Storage media can be used to store instructions, programs, code, code sets, or instructions.
[0035] The display screen is used to show the user interface of each application.
[0036] In addition, those skilled in the art will understand that the structure of the terminal described above does not constitute a limitation on the terminal. The terminal may include more or fewer components, or combine certain components, or have different component arrangements. For example, the terminal may also include radio frequency circuits, input units, sensors, audio circuits, power supplies, and other components, which will not be described in detail here.
[0037] Example 1
[0038] like Figure 1 As shown, this embodiment proposes a device maintenance triggering method based on status echo, including:
[0039] Step 101: Collect the operating status data of the equipment, detect abnormal points, and analyze the delayed response of each variable in the operating status data within a certain time window after the abnormality, so as to extract the current status echo stream. Among them, each variable in the operating status data constitutes a time-series variable sequence.
[0040] Preferably, the operating status data can be: speed, power, current, voltage and temperature, etc. The current status echo stream is extracted for each physical parameter, such as the current status echo stream of speed, power, current, voltage and temperature. In addition, the parameters in the above operating status data are time-series data, that is, the above parameters are collected according to time.
[0041] Specifically, it detects anomalies and analyzes the delayed response of various variables in the operational status data within a certain time window after the anomaly, thereby extracting the current status echo stream, which includes:
[0042] Calculate the first derivative of each variable in the running status data, and identify the variables corresponding to the first derivative results that exceed the preset abnormal change threshold as outliers;
[0043] The residual of each outlier point within the backward time window is calculated as the delayed response vector, and the local window echo intensity of each backward time window is calculated based on the delayed response vector. The local window echo intensities of multiple local windows constitute the current state echo stream.
[0044] Preferably, in this embodiment, the echo intensity of the local window is calculated using the following formula:
[0045]
[0046] Among them, E k Let W be the local window echo intensity of the k-th backward time window. k For the k-th backward time window, R echo (t) is the response vector delayed at time t.
[0047] Step 102: Analyze whether there are vector state abrupt changes, energy accumulation trends and autonomous inhibition failure behaviors among the variables in the current state echo stream. If all three are satisfied, they are combined into a contradictory behavior group.
[0048] Specifically, analyzing whether there are vector state abrupt changes between variables from the current state echo stream includes: extracting the change in the vector at the current time in the time series variable sequence, and the change in the vector at a certain time step forward from the current time, and calculating the product between the two;
[0049] If the product result is greater than the preset product threshold, and the echo intensity of the local window corresponding to the vector at the current time is greater than the preset echo intensity threshold, then the vector at the current time has a vector state change.
[0050] Specifically, analyzing whether there is an energy accumulation trend among variables from the current state echo stream includes: if Starting from the backward time window t′, the echo intensity of the local window corresponding to the backward time window t′ shows an energy accumulation trend, where k′ is the index of the backward time window, T is the number of backward time windows, E(t+k′) is the time at t, E(t+k′-1) is the sign function, and γ is the energy accumulation judgment threshold.
[0051] Specifically, analyzing whether there is autonomous suppression failure behavior among variables from the current state echo stream includes: if the difference between the adjusted anomaly point and the current anomaly point is greater than a preset reference threshold after the device autonomously adjusts the current anomaly point, then there is autonomous suppression failure behavior.
[0052] Step 103: Invoke the device's historical state echo stream and the corresponding historical maintenance strategy, find the historical state echo stream that matches the current state echo stream, and perform device maintenance according to the corresponding historical maintenance strategy.
[0053] Specifically, the historical state echo stream that matches the current state echo stream is found, and the device is maintained according to the corresponding historical maintenance strategy. This includes: finding a historical anomaly point that matches a certain anomaly point, finding the historical state echo stream corresponding to the historical anomaly point, and determining whether the change in local window echo intensity in the historical state echo stream is less than a preset echo intensity change threshold after the device is maintained according to the corresponding historical maintenance strategy. If so, the device is maintained according to the historical maintenance strategy; otherwise, a new maintenance strategy is adopted.
[0054] Example 2
[0055] like Figure 2 As shown, this embodiment proposes a device maintenance triggering system based on status echo, including:
[0056] The status echo extraction module is used to collect the operating status data of the equipment, detect abnormal points, and analyze the delayed response of each variable (single variable, not multiple variables, and multiple variables are separated) in the operating status data within a certain time window after the abnormality, thereby extracting the current status echo stream. The variables in the operating status data form a time-series variable sequence.
[0057] Specifically, it detects anomalies and analyzes the delayed response of various variables in the operational status data within a certain time window after the anomaly, thereby extracting the current status echo stream, which includes:
[0058] Calculate the first derivative of each variable in the running status data, and identify the variables corresponding to the first derivative results that exceed the preset abnormal change threshold as outliers;
[0059] The residual of each outlier point within the backward time window is calculated as the delayed response vector, and the local window echo intensity of each backward time window is calculated based on the delayed response vector. The local window echo intensities of multiple local windows constitute the current state echo stream.
[0060] The module for identifying contradictory behavior groups is used to analyze whether there are vector state abrupt changes, energy accumulation trends, and autonomous inhibition failure behaviors among variables from the current state echo stream. If all three are satisfied, they are combined into a contradictory behavior group.
[0061] Specifically, analyzing whether there are vector state abrupt changes between variables from the current state echo stream includes: extracting the change in the vector at the current time in the time series variable sequence, and the change in the vector at a certain time step forward from the current time, and calculating the product between the two;
[0062] If the product result is greater than the preset product threshold, and the echo intensity of the local window corresponding to the vector at the current time is greater than the preset echo intensity threshold, then the vector at the current time has a vector state change.
[0063] Specifically, analyzing whether there is an energy accumulation trend among variables from the current state echo stream includes: if Starting from the backward time window t′, the echo intensity of the local window corresponding to the backward time window t′ shows an energy accumulation trend, where k′ is the index of the backward time window, T is the number of backward time windows, E(t+k′) is the time at t, E(t+k′-1) is the sign function, and γ is the energy accumulation judgment threshold.
[0064] Specifically, analyzing whether there is autonomous suppression failure behavior among variables from the current state echo stream includes: if the difference between the adjusted anomaly point and the current anomaly point is greater than a preset reference threshold after the device autonomously adjusts the current anomaly point, then there is autonomous suppression failure behavior.
[0065] The maintenance module is used to call the device's historical status echo stream and corresponding historical maintenance strategy, find the historical status echo stream that matches the current status echo stream, and perform device maintenance according to the corresponding historical maintenance strategy.
[0066] Specifically, the historical state echo stream that matches the current state echo stream is found, and the device is maintained according to the corresponding historical maintenance strategy. This includes: finding a historical anomaly point that matches a certain anomaly point, finding the historical state echo stream corresponding to the historical anomaly point, and determining whether the change in local window echo intensity in the historical state echo stream is less than a preset echo intensity change threshold after the device is maintained according to the corresponding historical maintenance strategy. If so, the device is maintained according to the historical maintenance strategy; otherwise, a new maintenance strategy is adopted.
[0067] Example 3
[0068] This invention also proposes a storage medium storing multiple instructions for implementing the aforementioned device maintenance triggering method based on status echo.
[0069] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.
[0070] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following method steps: Step 101, collect the device's operating status data, detect anomalies and analyze the delayed response of each variable (a single variable is not multiple variables, multiple variables are separated) in the operating status data within a certain time window after the anomaly, thereby extracting the current state echo stream, wherein each variable in the operating status data constitutes a time-series variable sequence;
[0071] Specifically, it detects anomalies and analyzes the delayed response of various variables in the operational status data within a certain time window after the anomaly, thereby extracting the current status echo stream, which includes:
[0072] Calculate the first derivative of each variable in the running status data, and identify the variables corresponding to the first derivative results that exceed the preset abnormal change threshold as outliers;
[0073] The residual of each outlier point within the backward time window is calculated as the delayed response vector, and the local window echo intensity of each backward time window is calculated based on the delayed response vector. The local window echo intensities of multiple local windows constitute the current state echo stream.
[0074] Step 102: Analyze whether there are vector state abrupt changes, energy accumulation trends and autonomous inhibition failure behaviors among the variables in the current state echo stream. If all three are satisfied, they are combined into a contradictory behavior group.
[0075] Specifically, analyzing whether there are vector state abrupt changes between variables from the current state echo stream includes: extracting the change in the vector at the current time in the time series variable sequence, and the change in the vector at a certain time step forward from the current time, and calculating the product between the two;
[0076] If the product result is greater than the preset product threshold, and the echo intensity of the local window corresponding to the vector at the current time is greater than the preset echo intensity threshold, then the vector at the current time has a vector state change.
[0077] Specifically, analyzing whether there is an energy accumulation trend among variables from the current state echo stream includes: if Starting from the backward time window t′, the echo intensity of the local window corresponding to the backward time window t′ shows an energy accumulation trend, where k′ is the index of the backward time window, T is the number of backward time windows, E(t+k′) is the time at t, E(t+k′-1) is the sign function, and γ is the energy accumulation judgment threshold.
[0078] Specifically, analyzing whether there is autonomous suppression failure behavior among variables from the current state echo stream includes: if the difference between the adjusted anomaly point and the current anomaly point is greater than a preset reference threshold after the device autonomously adjusts the current anomaly point, then there is autonomous suppression failure behavior.
[0079] Step 103: Invoke the device's historical state echo stream and the corresponding historical maintenance strategy, find the historical state echo stream that matches the current state echo stream, and perform device maintenance according to the corresponding historical maintenance strategy.
[0080] Specifically, the historical state echo stream that matches the current state echo stream is found, and the device is maintained according to the corresponding historical maintenance strategy. This includes: finding a historical anomaly point that matches a certain anomaly point, finding the historical state echo stream corresponding to the historical anomaly point, and determining whether the change in local window echo intensity in the historical state echo stream is less than a preset echo intensity change threshold after the device is maintained according to the corresponding historical maintenance strategy. If so, the device is maintained according to the historical maintenance strategy; otherwise, a new maintenance strategy is adopted.
[0081] Example 4
[0082] This invention also proposes an electronic device, including a processor and a storage medium connected to the processor. The storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to execute the aforementioned device maintenance triggering method based on status echo.
[0083] Specifically, the electronic device in this embodiment can be a computer terminal, which may include one or more processors and a storage medium.
[0084] The storage medium can be used to store software programs and modules, such as the status echo-based device maintenance triggering method in this embodiment of the invention. The corresponding program instructions / modules allow the processor to execute various functional applications and data processing by running the software programs and modules stored in the storage medium, thus realizing the aforementioned status echo-based device maintenance triggering method. The storage medium may include high-speed random access storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely configured relative to the processor, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0085] The processor can call the information and application stored in the storage medium through the transmission system to execute the following steps: Step 101, collect the device's operating status data, detect abnormal points, and analyze the delay response of each variable (a single variable is not multiple variables, and multiple variables are separated) in the operating status data within a certain time window after the abnormality, thereby extracting the current status echo stream, wherein each variable in the operating status data constitutes a time-series variable sequence.
[0086] Specifically, it detects anomalies and analyzes the delayed response of various variables in the operational status data within a certain time window after the anomaly, thereby extracting the current status echo stream, which includes:
[0087] Calculate the first derivative of each variable in the running status data, and identify the variables corresponding to the first derivative results that exceed the preset abnormal change threshold as outliers;
[0088] The residual of each outlier point within the backward time window is calculated as the delayed response vector, and the local window echo intensity of each backward time window is calculated based on the delayed response vector. The local window echo intensities of multiple local windows constitute the current state echo stream.
[0089] Step 102: Analyze whether there are vector state abrupt changes, energy accumulation trends and autonomous inhibition failure behaviors among the variables in the current state echo stream. If all three are satisfied, they are combined into a contradictory behavior group.
[0090] Specifically, analyzing whether there are vector state abrupt changes between variables from the current state echo stream includes: extracting the change in the vector at the current time in the time series variable sequence, and the change in the vector at a certain time step forward from the current time, and calculating the product between the two;
[0091] If the product result is greater than the preset product threshold, and the echo intensity of the local window corresponding to the vector at the current time is greater than the preset echo intensity threshold, then the vector at the current time has a vector state change.
[0092] Specifically, analyzing whether there is an energy accumulation trend among variables from the current state echo stream includes: if Starting from the backward time window t′, the echo intensity of the local window corresponding to the backward time window t′ shows an energy accumulation trend, where k′ is the index of the backward time window, T is the number of backward time windows, E(t+k′) is the time at t, E(t+k′-1) is the sign function, and γ is the energy accumulation judgment threshold.
[0093] Specifically, analyzing whether there is autonomous suppression failure behavior among variables from the current state echo stream includes: if the difference between the adjusted anomaly point and the current anomaly point is greater than a preset reference threshold after the device autonomously adjusts the current anomaly point, then there is autonomous suppression failure behavior.
[0094] Step 103: Invoke the device's historical state echo stream and the corresponding historical maintenance strategy, find the historical state echo stream that matches the current state echo stream, and perform device maintenance according to the corresponding historical maintenance strategy.
[0095] Specifically, the historical state echo stream that matches the current state echo stream is found, and the device is maintained according to the corresponding historical maintenance strategy. This includes: finding a historical anomaly point that matches a certain anomaly point, finding the historical state echo stream corresponding to the historical anomaly point, and determining whether the change in local window echo intensity in the historical state echo stream is less than a preset echo intensity change threshold after the device is maintained according to the corresponding historical maintenance strategy. If so, the device is maintained according to the historical maintenance strategy; otherwise, a new maintenance strategy is adopted.
[0096] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0097] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0098] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, 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 interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.
[0099] 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.
[0100] Furthermore, the functional units in the various embodiments of the present invention 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.
[0101] 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 medium. Based on this understanding, the technical solution of the present invention, 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 storage medium 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 the present invention. The aforementioned storage medium includes: USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.
[0102] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.
Claims
1. A device maintenance triggering method based on status echo, characterized in that, include: Collect equipment operating status data, detect anomalies, and analyze the delayed response of each variable in the operating status data within a certain time window after the anomaly, thereby extracting the current status echo stream. The variables in the operating status data constitute a time-series variable sequence. Analyze whether there are vector state abrupt changes, energy accumulation trends, and autonomous inhibition failure behaviors among the variables from the current state echo stream. If all three are satisfied, they are combined into a contradictory behavior group. The historical state echo stream of the device and the corresponding historical maintenance strategy are invoked to find the historical state echo stream that matches the current state echo stream, and the device is maintained according to the corresponding historical maintenance strategy.
2. The device maintenance triggering method based on status echo as described in claim 1, characterized in that, Anomalies are detected, and the delayed response of each variable in the runtime status data is analyzed within a certain time window after the anomaly occurs, thereby extracting the current status echo stream. Specifically, this includes: Calculate the first derivative of each variable in the running status data, and identify the variables corresponding to the first derivative results that exceed the preset abnormal change threshold as outliers; The residual of each outlier point within the backward time window is calculated as the delayed response vector, and the local window echo intensity of each backward time window is calculated based on the delayed response vector. The local window echo intensities of multiple local windows constitute the current state echo stream.
3. The device maintenance triggering method based on status echo as described in claim 2, characterized in that, Analyzing whether there are vector state abrupt changes between variables from the current state echo stream specifically includes: extracting the change in the vector at the current time in the time series variable sequence, and the change in the vector at a certain time step forward from the current time, and calculating the product between the two; If the product result is greater than the preset product threshold, and the echo intensity of the local window corresponding to the vector at the current time is greater than the preset echo intensity threshold, then the vector at the current time has a vector state change.
4. The device maintenance triggering method based on status echo as described in claim 2, characterized in that, Analyzing whether there is an energy accumulation trend among variables from the current state echo stream specifically includes: if Starting from the backward time window t′, the echo intensity of the local window corresponding to the backward time window t′ shows an energy accumulation trend, where k′ is the index of the backward time window, T is the number of backward time windows, E(t+k′) is the time at t, E(t+k′-1) is the sign function, and γ is the energy accumulation judgment threshold.
5. The device maintenance triggering method based on status echo as described in claim 2, characterized in that, Analyzing whether there is autonomous suppression failure behavior among variables from the current state echo stream specifically includes: if the difference between the adjusted anomaly point and the current anomaly point is greater than a preset reference threshold after the device autonomously adjusts the current anomaly point, then there is autonomous suppression failure behavior.
6. The device maintenance triggering method based on status echo as described in claim 2, characterized in that, Find the historical state echo stream that matches the current state echo stream, and maintain the device according to the corresponding historical maintenance strategy. Specifically, this includes: finding a historical anomaly point that matches a certain anomaly point, finding the historical state echo stream corresponding to the historical anomaly point, and determining whether the change in local window echo intensity in the historical state echo stream is less than a preset echo intensity change threshold after the device is maintained according to the corresponding historical maintenance strategy. If so, maintain the device according to the historical maintenance strategy; otherwise, adopt a new maintenance strategy.
7. A device maintenance triggering system based on status echo, characterized in that, include: The status echo extraction module is used to collect the operating status data of the equipment, detect abnormal points, and analyze the delayed response of each variable in the operating status data within a certain time window after the abnormality, thereby extracting the current status echo stream. The variables in the operating status data form a time-series variable sequence. The module for identifying contradictory behavior groups is used to analyze whether there are vector state abrupt changes, energy accumulation trends, and autonomous inhibition failure behaviors among variables from the current state echo stream. If all three are satisfied, they are combined into a contradictory behavior group. The maintenance module is used to call the device's historical status echo stream and corresponding historical maintenance strategy, find the historical status echo stream that matches the current status echo stream, and perform device maintenance according to the corresponding historical maintenance strategy.
8. The equipment maintenance triggering system based on status echo as described in claim 7, characterized in that, Anomalies are detected, and the delayed response of each variable in the runtime status data is analyzed within a certain time window after the anomaly occurs, thereby extracting the current status echo stream. Specifically, this includes: Calculate the first derivative of each variable in the running status data, and identify the variables corresponding to the first derivative results that exceed the preset abnormal change threshold as outliers; The residual of each outlier point within the backward time window is calculated as the delayed response vector, and the local window echo intensity of each backward time window is calculated based on the delayed response vector. The local window echo intensities of multiple local windows constitute the current state echo stream.
9. The equipment maintenance triggering system based on status echo as described in claim 8, characterized in that, Analyzing whether there are vector state abrupt changes between variables from the current state echo stream specifically includes: extracting the change in the vector at the current time in the time series variable sequence, and the change in the vector at a certain time step forward from the current time, and calculating the product between the two; If the product result is greater than the preset product threshold, and the echo intensity of the local window corresponding to the vector at the current time is greater than the preset echo intensity threshold, then the vector at the current time has a vector state change.
10. The equipment maintenance triggering system based on status echo as described in claim 8, characterized in that, Analyzing whether there is an energy accumulation trend among variables from the current state echo stream specifically includes: if Starting from the backward time window t′, the echo intensity of the local window corresponding to the backward time window t′ shows an energy accumulation trend, where k′ is the index of the backward time window, T is the number of backward time windows, E(t+k′) is the time at t, E(t+k′-1) is the sign function, and γ is the energy accumulation judgment threshold.