Equipment health intelligent identification method and system

Abstract

The invention discloses an equipment health intelligent identification method and system. The method comprises the following steps: carrying out multi-dimensional analysis on an equipment degradation process and potential fault characteristics; according to a multi-dimensional analysis result, health features based on a degradation process are extracted; constructing a health state recognition model according to the extracted health features; and performing online recognition on the health state of the equipment by using the health state recognition model. According to the equipment health intelligent identification method and system provided by the invention, the intelligence, accuracy and diagnosis efficiency of fault identification are improved by uniformly depicting the evolution model of the degradation characteristic; by determining the fault position in time, the deterioration trend of the part is predicted, corresponding measures are taken in advance, and equipment shutdown and even safety accidents are prevented; the method can effectively predict the potential faults in the production process of the wrapping equipment, reduces the production loss and maintenance cost, improves the production reliability and safety, and promotes the predictive maintenance and the lean level of equipment management.

Description

Technical Field

[0001] The present invention relates to the technical field of tobacco processing, and more specifically, to a method and system for intelligently identifying equipment health. Background Art

[0002] At present, there are problems of false alarm and missed alarm at the unit monitoring points in the existing online monitoring system of cigarette machine equipment status, especially in equipment abnormal information identification, status classification and abnormal signal separation, abnormal feature extraction and classification, fault information tolerance, rapid online diagnosis and other aspects. In addition, the networked remote status monitoring system has problems of time lag and delay.

[0003] Therefore, there is an urgent need for an intelligent device health identification method and system. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for intelligently identifying equipment health to solve the above-mentioned problems in the prior art and to improve the intelligence, accuracy and diagnostic efficiency of fault identification.

[0005] The present invention provides a method for intelligently identifying equipment health, which includes the following steps:

[0006] Conduct multi-dimensional analysis of equipment degradation process and potential failure characteristics;

[0007] According to the results of multi-dimensional analysis, the health characteristics based on the degradation process are extracted;

[0008] Constructing a health status recognition model according to the extracted health characteristics;

[0009] The health status recognition model is used to perform online recognition of the health status of the device.

[0010] In the above-mentioned intelligent identification method for equipment health, preferably, the multi-dimensional analysis of the equipment degradation process and potential fault characteristics specifically includes:

[0011] According to the functional characteristics and working principles of the equipment, the various degradation processes and characteristics that cannot be directly observed are analyzed, and the formation mechanism and mutual correlation law of each degradation process are determined to extract key feature quantities, which are used to characterize the feature quantities of hidden degradation processes;

[0012] Based on the extracted key characteristic quantities, influence analysis diagrams of various degradation processes and failure modes are established.

[0013] In the method for intelligently identifying equipment health as described above, preferably, the key characteristic quantity includes at least one of a vibration signal, a vehicle speed, a temperature and a current.

[0014] In the above-mentioned method for intelligently identifying equipment health, preferably, extracting health features based on the degradation process according to the multi-dimensional analysis results specifically includes:

[0015] Construct equipment health status quantities that can comprehensively characterize the equipment, analyze the sensitivity and uncertainty of health parameters, and form health characteristics that are highly relevant to the production process.

[0016] In the method for intelligently identifying equipment health as described above, preferably, the extracted health features based on the degradation process include time domain features, frequency domain features and time-frequency domain features.

[0017] In the above-mentioned device health intelligent identification method, preferably, constructing a health status identification model based on the extracted health features specifically includes:

[0018] According to the extracted health features, a random degradation model is constructed by adopting a data-driven random degradation modeling method;

[0019] According to the extracted health characteristics, a dynamic model is constructed by using a dynamic modeling method based on the principle of physics;

[0020] The random degradation model and the dynamic model are subjected to multi-feature model fusion to obtain a health status recognition model fused with degradation characteristics.

[0021] In the above-mentioned device health intelligent identification method, preferably, the online identification of the health status of the device using the health status identification model specifically includes:

[0022] The health features extracted in real time based on the degradation process are input into the health status recognition model to obtain an online recognition result of the health status of the equipment.

[0023] The device health intelligent identification method as described above, wherein preferably, the device health intelligent identification method further includes:

[0024] Using the health status recognition model to perform visual status monitoring specifically includes: using an update iteration-based state transition visualization method to perform visual status monitoring.

[0025] The device health intelligent identification method as described above, wherein preferably, the device health intelligent identification method further includes:

[0026] And adaptively updating the health status recognition model, specifically including:

[0027] Based on the influence of degradation characteristics on prediction accuracy and prediction uncertainty, adaptively updating the parameters of the health status recognition model;

[0028] Based on the influence of the degradation characteristic process on the monitoring accuracy and the probability of each category, the structure of the health status recognition model is adaptively updated.

[0029] The present invention also provides an equipment health intelligent identification system using the above method, comprising:

[0030] Multi-dimensional analysis module, used to conduct multi-dimensional analysis of equipment degradation process and potential failure characteristics;

[0031] A health feature extraction module is used to extract health features based on the degradation process according to the multi-dimensional analysis results;

[0032] A device health status recognition model building module is used to build a health status recognition model based on the extracted health features;

[0033] The device health status online identification module is used to use the health status identification model to perform online identification of the health status of the device.

[0034] The present invention provides a method and system for intelligently identifying equipment health, which conducts multi-dimensional analysis on equipment degradation process and potential fault characteristics, extracts health features based on the degradation process, and constructs a health status identification model to identify the health status of the equipment online. The system can improve the intelligence, accuracy and diagnostic efficiency of fault identification by uniformly characterizing the evolution model of degradation characteristics, integrating identification and global fusion identification. The system can timely determine the fault location and predict the degradation trend of components, take corresponding measures in advance, and prevent equipment shutdown and even safety accidents. The system can effectively predict potential faults in the production process of ultra-high-speed wrapping equipment, reduce production losses and maintenance costs, improve production reliability and safety, and promote predictive maintenance and lean equipment management. The system can reduce maintenance costs, improve production efficiency and operational reliability by real-time monitoring and control of the health status of core production equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described below with reference to the accompanying drawings, in which:

[0036] Figure 1 A flowchart of an embodiment of a method for intelligently identifying device health provided by the present invention;

[0037] Figure 2 This is a structural block diagram of an embodiment of the device health intelligent identification system provided by the present invention. DETAILED DESCRIPTION

[0038] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and is in no way intended to limit the present disclosure and its application or use. The present disclosure can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to make the present disclosure thorough and complete and to fully express the scope of the present disclosure to those skilled in the art. It should be noted that unless otherwise specifically stated, the relative arrangement of the components and steps, the composition of the materials, the numerical expressions and the numerical values ​​set forth in these embodiments should be interpreted as being merely exemplary and not as limiting.

[0039] The words "first", "second" and similar words used in this disclosure do not indicate any order, quantity or importance, but are only used to distinguish different parts. The words "include" or "comprises" and similar words mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of including other elements. "Up", "down" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0040] In the present disclosure, when a specific component is described as being located between a first component and a second component, there may or may not be an intermediate component between the specific component and the first component or the second component. When a specific component is described as being connected to other components, the specific component may be directly connected to the other components without an intermediate component, or may not be directly connected to the other components but have an intermediate component.

[0041] All terms (including technical terms or scientific terms) used in the present disclosure have the same meanings as those understood by ordinary technicians in the field to which the present disclosure belongs, unless otherwise specifically defined. It should also be understood that terms defined in general dictionaries, such as general dictionaries, should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined herein.

[0042] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0043] like Figure 1 As shown, the device health intelligent identification method provided in this embodiment includes the following steps in actual execution:

[0044] Step S1: Perform multi-dimensional analysis on the equipment degradation process and potential failure characteristics.

[0045] Degradation characteristics are common features of equipment. In-depth research on this can provide reference for the maintenance of other equipment, and the developed fault identification algorithm is expected to be promoted and used on other models. In one embodiment of the device health intelligent identification method of the present invention, step S1 can specifically include:

[0046] Step S11, according to the functional characteristics and working principle of the equipment, analyze the various degradation processes and characteristics that cannot be directly observed, determine the formation mechanism and mutual correlation law of each degradation process, so as to extract key feature quantities, and the key feature quantities are used to characterize the feature quantities of hidden degradation processes.

[0047] In one embodiment of the present invention, vibration data of each monitoring point of each cigarette machine model is collected to analyze degradation characteristics. In addition, some monitoring points can be added, removed or moved in a targeted manner to optimize data collection for different faults. The key characteristic quantity includes at least one of vibration signal, vehicle speed, temperature and current.

[0048] Step S12: establishing an influence analysis diagram of each degradation process and failure mode according to the extracted key characteristic quantities.

[0049] In some embodiments of the present invention, the characteristic signal is matched and associated with different types of faults to achieve quantitative characterization. The faults here refer to hard faults, including cracks / fractures, pitting, wear, deformation, looseness / falling off, etc., which require replacement and repair, and do not include equipment instability caused by human operating errors, auxiliary material incompatibility, external environmental influences, etc.

[0050] Step S2: extracting health features based on the degradation process according to the multi-dimensional analysis results.

[0051] Specifically, a device health status quantity that can comprehensively characterize the equipment is constructed, the sensitivity and uncertainty of health parameters are analyzed, and health characteristics that are highly relevant to the production process are formed.

[0052] Among them, the extracted health features based on the degradation process include time domain features, frequency domain features and time-frequency domain features.

[0053] Step S3: construct a health status recognition model based on the extracted health features.

[0054] In one implementation of the device health intelligent identification method of the present invention, step S3 may specifically include:

[0055] Step S31: construct a stochastic degradation model based on the extracted health features by adopting a data-driven stochastic degradation modeling method.

[0056] Step S32: construct a dynamic model based on the extracted health characteristics using a dynamic modeling method based on the principles of physics.

[0057] Step S33: performing multi-feature model fusion on the random degradation model and the dynamic model to obtain a health status recognition model fused with degradation characteristics.

[0058] Step S4: Use the health status recognition model to perform online recognition of the health status of the device.

[0059] Specifically, the health features extracted in real time based on the degradation process are input into the health status recognition model to obtain an online recognition result of the health status of the equipment.

[0060] Furthermore, in some embodiments of the present invention, the robustness and reliability of the health status recognition model are also tested to achieve online real-time evaluation and dynamic prediction of equipment health.

[0061] The present invention can improve production reliability, reduce the equipment failure rate in the cigarette processing process and the indirect waste rejection, improve efficiency and ensure quality, and avoid safety hazards and human-machine accidents caused by abnormalities; it can reduce operation and maintenance costs, discover hidden faults in time, and promote maintenance personnel to repair them early and small, avoid further deterioration of faults, improve the level of predictive maintenance, and reduce the frequency of subsequent maintenance and spare parts replacement costs; it can achieve precise control of equipment, more accurately identify the health status of key equipment online, reduce invalid maintenance caused by false alarms, and achieve lean equipment control; it has broad promotion prospects, and degradation characteristics are a common feature of equipment. In-depth research on this can provide reference for the maintenance of other equipment in the enterprise, and the developed fault identification algorithm is expected to be promoted and used on other models.

[0062] Furthermore, in some embodiments of the present invention, the device health intelligent identification method further includes:

[0063] Step S5: Use the health status recognition model to perform visual status monitoring.

[0064] Specifically, a state transition visualization method based on update iteration is adopted for visual state monitoring.

[0065] Furthermore, in some embodiments of the present invention, the device health intelligent identification method further includes:

[0066] Step S6: adaptively update the health status recognition model.

[0067] In one embodiment of the device health intelligent identification method of the present invention, step S6 may specifically include:

[0068] Step S61: Based on the influence of degradation characteristics on prediction accuracy and prediction uncertainty, the parameters of the health status recognition model are adaptively updated.

[0069] Step S62: Based on the influence of the degradation characteristic process on the monitoring accuracy and the probability of each category, the structure of the health status recognition model is adaptively updated.

[0070] The intelligent equipment health identification method provided in the embodiment of the present invention performs multi-dimensional analysis on the equipment degradation process and potential fault characteristics, extracts health features based on the degradation process, and constructs a health status identification model to identify the health status of the equipment online. By uniformly characterizing the evolution model of the degradation characteristics, integrated identification, and global fusion identification, the intelligence, accuracy, and diagnostic efficiency of fault identification are improved; by timely determining the fault location and predicting the degradation trend of the components, corresponding measures are taken in advance to prevent equipment shutdown and even safety accidents; it can effectively predict potential faults in the production process of ultra-high-speed wrapping equipment, reduce production losses and maintenance costs, improve production reliability and safety, and promote predictive maintenance and lean equipment management levels; through real-time monitoring and control of the health status of core production equipment, maintenance costs are reduced, and production efficiency and operational reliability are improved.

[0071] Correspondingly, if Figure 2 As shown, the present invention also provides a device health intelligent identification system, comprising:

[0072] A multi-dimensional analysis module 101 is used to perform multi-dimensional analysis on the equipment degradation process and potential failure characteristics;

[0073] A health feature extraction module 102 is used to extract health features based on the degradation process according to the multi-dimensional analysis results;

[0074] The device health status recognition model building module 103 is used to build a health status recognition model according to the extracted health features;

[0075] The device health status online identification module 104 is used to perform online identification of the health status of the device using the health status identification model.

[0076] The equipment health intelligent identification system provided by the embodiment of the present invention performs multi-dimensional analysis on the equipment degradation process and potential fault characteristics, extracts health features based on the degradation process, and constructs a health status identification model to identify the health status of the equipment online. By uniformly characterizing the evolution model of the degradation characteristics, integrated identification, and global fusion identification, the intelligence, accuracy, and diagnostic efficiency of fault identification are improved; by timely determining the fault location and predicting the degradation trend of the components, corresponding measures are taken in advance to prevent equipment shutdown and even safety accidents; it can effectively predict potential faults in the production process of ultra-high-speed wrapping equipment, reduce production losses and maintenance costs, improve production reliability and safety, and promote predictive maintenance and lean equipment management levels; through real-time monitoring and control of the health status of core production equipment, maintenance costs are reduced, production efficiency and operational reliability are improved.

[0077] So far, various embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0078] Although some specific embodiments of the present disclosure have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified or some technical features may be replaced by equivalents without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for intelligently identifying equipment health, characterized in that: include: Conduct multi-dimensional analysis of equipment degradation process and potential failure characteristics; According to the results of multi-dimensional analysis, the health characteristics based on the degradation process are extracted; Constructing a health status recognition model according to the extracted health characteristics; The health status recognition model is used to perform online recognition of the health status of the device.

2. The device health intelligent identification method according to claim 1, characterized in that: The multi-dimensional analysis of the equipment degradation process and potential failure characteristics specifically includes: According to the functional characteristics and working principles of the equipment, the various degradation processes and characteristics that cannot be directly observed are analyzed, and the formation mechanism and mutual correlation law of each degradation process are determined to extract key feature quantities, which are used to characterize the feature quantities of hidden degradation processes; Based on the extracted key characteristic quantities, influence analysis diagrams of various degradation processes and failure modes are established.

3. The device health intelligent identification method according to claim 2, characterized in that: The key characteristic quantity includes at least one of a vibration signal, a vehicle speed, a temperature and a current.

4. The device health intelligent identification method according to claim 1, characterized in that: According to the multi-dimensional analysis results, the health characteristics based on the degradation process are extracted, specifically including: Construct equipment health status quantities that can comprehensively characterize the equipment, analyze the sensitivity and uncertainty of health parameters, and form health characteristics that are highly relevant to the production process.

5. The device health intelligent identification method according to claim 4, characterized in that: The extracted health features based on the degradation process include time domain features, frequency domain features and time-frequency domain features.

6. The device health intelligent identification method according to claim 1, characterized in that: The step of constructing a health status recognition model based on the extracted health features specifically includes: According to the extracted health features, a random degradation model is constructed by adopting a data-driven random degradation modeling method; According to the extracted health characteristics, a dynamic model is constructed by using a dynamic modeling method based on the principle of physics; The random degradation model and the dynamic model are subjected to multi-feature model fusion to obtain a health status recognition model fused with degradation characteristics.

7. The device health intelligent identification method according to claim 6, characterized in that: The online identification of the health status of the device by using the health status identification model specifically includes: The health features extracted in real time based on the degradation process are input into the health status recognition model to obtain an online recognition result of the health status of the equipment.

8. The device health intelligent identification method according to claim 1, characterized in that: The device health intelligent identification method also includes: Using the health status recognition model to perform visual status monitoring specifically includes: using an update iteration-based state transition visualization method to perform visual status monitoring.

9. The device health intelligent identification method according to claim 1, characterized in that: The device health intelligent identification method also includes: And adaptively updating the health status recognition model, specifically including: Based on the influence of degradation characteristics on prediction accuracy and prediction uncertainty, adaptively updating the parameters of the health status recognition model; Based on the influence of the degradation characteristic process on the monitoring accuracy and the probability of each category, the structure of the health status recognition model is adaptively updated.

10. An intelligent device health identification system using the method described in any one of claims 1 to 9, characterized in that: include: Multi-dimensional analysis module, used to conduct multi-dimensional analysis of equipment degradation process and potential failure characteristics; A health feature extraction module is used to extract health features based on the degradation process according to the multi-dimensional analysis results; A device health status recognition model building module is used to build a health status recognition model based on the extracted health features; The device health status online identification module is used to use the health status identification model to perform online identification of the health status of the device.

Images