CN114548177A - Equipment health assessment method, system and equipment - Google Patents

Abstract

The invention provides a method, a system and equipment for evaluating equipment health, wherein the method comprises the following steps: acquiring operation parameters of equipment and calculating to obtain characteristic quantities of the operation parameters; weighting the characteristic quantity of each operation parameter based on a preset comprehensive weighting coefficient to obtain the evaluation characteristic of the equipment; calculating the distance between the evaluation feature and the sample feature representing that the equipment is in a complete health state; based on the comparison of the distance to the distance threshold interval in the running sample library, the health status of the device is determined. The method and the device are used for solving the defects of low state evaluation accuracy caused by sparse fault data under different health states of the equipment and insufficient consideration of the influence degree of various operation parameters on the health state of the equipment when the health state of the equipment is evaluated in the prior art, and realizing accurate evaluation of the health state of the equipment by utilizing the distance between the evaluation characteristics obtained by weighting the real-time operation parameters of the equipment and the sample characteristics representing the complete health state of the equipment in the operation sample library.

Description

Equipment health assessment method, system and equipment

Technical Field

The invention relates to the technical field of equipment health assessment, in particular to an equipment health assessment method, system and equipment.

Background

The engineering machinery equipment has a complex structure and complex and changeable working conditions, and how to ensure the stable and reliable work of important engineering machinery equipment and ensure the operating rate and the attendance rate is always the focus of attention of engineering machinery owners and equipment manufacturers. With the rapid development of science and technology, engineering machinery manufacturers begin to arrange various sensors on the engineering machinery equipment in the industrial internet for acquiring working condition data in real time, and then continuously transmit massive working condition data back to a data center to realize the working condition monitoring of the engineering machinery equipment. The massive working condition data contains the state information of equipment operation, and powerful basis can be provided for realizing health evaluation, fault diagnosis and intelligent operation and maintenance of engineering mechanical equipment.

The engineering machinery equipment has a plurality of structural forms, taking an excavator as an example, a primary system comprises a power system, a mechanical system, a hydraulic system, an electrical system and the like, and the sensors deployed in all the systems are combined with real-time monitoring data and preset thresholds, so that the ultra-threshold alarm of monitoring parameters can be realized, and the system is used for assisting troubleshooting and maintenance of operators and service engineers. However, since the creep failure of the engineering machinery equipment has a certain accumulation process, the failure has been developed for a period of time after the critical parameters are out of limit, and the failure diffusion and the unnecessary shutdown of the equipment are easily caused.

Based on the above defects, a technical scheme for evaluating the health state of the equipment also appears at present, but the evaluation scheme in the prior art is affected by a plurality of adverse factors: fault data under different health states are sparse, operation working condition data of equipment are numerous, and the fault data are difficult to be fused into a single health evaluation index, and noise and the like exist in measurement of various sensors arranged on engineering mechanical equipment, so that evaluation accuracy is difficult to guarantee.

Disclosure of Invention

The invention provides a method, a system and equipment for evaluating equipment health, which are used for solving the defect of low accuracy in evaluating the equipment health state in the prior art and realizing accurate evaluation of the equipment health state.

The invention provides an equipment health assessment method, which comprises the following steps:

acquiring operation parameters of equipment, and calculating to obtain characteristic quantities of the operation parameters;

weighting the characteristic quantity of each operation parameter based on a preset comprehensive weighting coefficient of each operation parameter to obtain the evaluation characteristic of the equipment;

calculating the distance between the evaluation feature and a sample feature which is called from a running sample library of the equipment and is used for representing that the equipment is in a full health state;

determining a health status of the device based on a comparison of the distance to different distance threshold intervals in the running sample library.

According to the equipment health assessment method, the preset comprehensive weighting coefficient is obtained based on fusion of a subjective weighting coefficient and an objective weighting coefficient;

the subjective weighting coefficient is determined based on a scoring result obtained by scoring each operation parameter sample according to a preset rule;

the objective weighting coefficients are determined based on the data-inherent relevance of each of the operational parameter samples.

According to the equipment health assessment method, the obtaining of the operation parameters of the equipment and the calculation of the characteristic quantity of each operation parameter comprises the following steps:

acquiring preset specific operating parameters of the equipment, and calculating to obtain characteristic quantities of the preset specific operating parameters;

the method for determining the preset specific operation parameter comprises the following steps:

obtaining each operation parameter sample of the equipment in a first time window width, and calculating to obtain the characteristic quantity of each operation parameter sample;

weighting the characteristic quantity of each operation parameter sample based on the preset comprehensive weighting coefficient to obtain the evaluation sample characteristic of the equipment;

and performing dimension reduction processing on the evaluation sample characteristics, and determining the preset specific operation parameters.

According to the equipment health assessment method, the acquiring of the preset specific operation parameters of the equipment and the calculation of the feature quantity of each preset specific operation parameter comprise the following steps:

acquiring preset specific operation parameters of the equipment in each second time window width based on a preset step length; the second time window width is at least greater than a set multiple of the first time window width;

and calculating and obtaining the characteristic quantity of each preset specific operation parameter based on the proportional relation between the second time window width and the first time window width.

According to the equipment health assessment method, the step of determining the health state of the equipment based on the comparison of the distance and different distance threshold intervals in the running sample library comprises the following steps:

determining a health status of the device based on a proportion of the distances falling within different distance threshold intervals in the running sample library.

According to the equipment health assessment method, the operation of different distance threshold intervals in the sample library comprises the following steps:

the distance interval between the sample characteristics representing the equipment in different health states and the sample characteristics representing the equipment in a complete health state;

the acquisition method for characterizing the sample characteristics of the equipment in different health states comprises the following steps:

operating parameter samples of the equipment in different health states are called by the operating sample library;

and obtaining sample characteristics characterizing the equipment in different health states based on the operation parameter samples of the equipment in different health states.

According to the equipment health assessment method, the running parameter samples of the equipment called by the running sample library in different health states are running parameter samples obtained by deleting and/or modifying running parameter samples which do not meet the aging rules based on preset aging rules; and

based on a data amplification method, when the number of any one of the operation parameter samples is less than the corresponding set sample standard quantity, carrying out sample quantity amplification on the operation parameter samples with the number less than the corresponding set sample standard quantity; wherein the sample size of the amplified running parameter sample does not exceed a set number threshold.

According to the equipment health assessment method, the operation parameter samples of the equipment, which are called by the operation sample library, in different health states are operation parameters extracted from operation parameter big data of the equipment based on the maintenance service feedback information and the customer feedback information of the equipment.

The present invention also provides an equipment health assessment system, comprising:

the data acquisition module is used for acquiring the operating parameters of the equipment;

the characteristic calculation module is used for calculating the characteristic quantity of the operation parameters, and weighting the characteristic quantity of each operation parameter based on the preset comprehensive weighting coefficient of each operation parameter to obtain the evaluation characteristic of the equipment;

the distance calculation module is used for calculating the distance between the evaluation feature and a sample feature which is called from a running sample library of the equipment and is used for representing that the equipment is in a complete health state;

a state evaluation module to determine a health state of the device based on a comparison of the distance to different distance threshold intervals in the running sample library.

The invention also provides equipment comprising the equipment health assessment system.

According to the equipment health assessment method, the system and the equipment, firstly, the acquired running parameters of the equipment are weighted based on the predetermined comprehensive weighting coefficient corresponding to each running parameter, so that the evaluation characteristics capable of reflecting the health state of the whole equipment are obtained; then calculating the distance between the evaluation characteristics and the characteristics of the samples representing the equipment in a complete health state in the running sample library; finally, the overall health state of the equipment can be accurately evaluated based on the comparison of the distance between the evaluation characteristics of the equipment and the sample characteristics of the equipment in the complete health state and different distance threshold intervals stored in a running sample library.

Drawings

In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic flow chart of a method for evaluating health of a device according to the present invention;

FIG. 2 is a second schematic flow chart of a method for evaluating health of a device according to the present invention;

FIG. 3 is a schematic structural diagram of an equipment health assessment system provided by the present invention;

fig. 4 is a schematic structural diagram of an electronic device provided in the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the equipment health assessment method provided by the invention realizes the health assessment of the engineering machinery equipment; the health evaluation of the engineering mechanical equipment refers to the steps of extracting key features capable of reflecting the running state of the equipment by combining running condition data of the engineering mechanical equipment, calculating the distance between the key features of the running state of the equipment and the features in the complete health state, and evaluating the running health state of the equipment by combining distance thresholds of different health state grades.

At present, in order to evaluate the running health state of equipment more accurately, the following problems are mainly faced:

1. health status label data of construction machines is scarce: the operation data of the engineering mechanical equipment mostly belong to normal data, and fault data under different health states are scarce and difficult to define.

2. The engineering mechanical equipment has numerous monitoring working condition data and is difficult to be fused into a single health evaluation index: the existing multivariate information fusion method is used for weighting and summing the monitoring data and characteristics of different sensor devices, and the internal relevance of working condition data, the difficulty of maintaining different parts and the cost influence are not comprehensively considered;

3. noise is present in the various sensor measurements: the health assessment results aggregated from noisy sensor data may fluctuate under the influence of noise.

Based on the above, the invention provides a device health assessment method, which is used for solving the problem of inaccurate device health assessment caused by the factors.

An apparatus health assessment method of the present invention is described below with reference to fig. 1 and 2, and as shown in fig. 1, the apparatus health assessment method includes the following steps:

101. and acquiring the operating parameters of the equipment, and calculating to obtain the characteristic quantity of each operating parameter.

Specifically, the health status of the whole equipment is mainly reflected in various operating parameters, such as: real-time oil consumption, pump pressure, pump displacement, engine output torque, critical rotary mechanism vibration acceleration, and the like. The characteristic quantity of the operating parameter is a characteristic quantity of the operating state of the equipment based on the corresponding operating parameter in a set time length.

102. And weighting the characteristic quantity of each operation parameter based on the preset comprehensive weighting coefficient of each operation parameter to obtain the evaluation characteristic of the equipment.

It can be understood that the operating parameters of the equipment are numerous, and based on consideration of factors such as calculation amount, it is obviously unrealistic to apply all the operating parameters to evaluate the health state of the equipment, and the influence of different operating parameters on the health state of the whole equipment is not completely the same.

Specifically, the embodiment of the invention weights the characteristic quantity of each operating parameter through the predetermined comprehensive weighting coefficient, and can obtain a multidimensional space for representing the health state of the whole equipment.

103. And calculating the distance between the evaluation feature and a sample feature which is called from a running sample library of the equipment and is used for representing that the equipment is in a full health state.

Specifically, the sample characteristics of the characterization device in the complete health state stored in the running sample library should be in one-to-one correspondence with the evaluation characteristics, that is, in the multidimensional space, the distance between the evaluation characteristics of the current health state of the characterization device and the sample characteristics of the characterization device in the complete health state can be calculated, and then the health degree of the device is judged according to the distance.

More specifically, the distance may be a mahalanobis distance, a euclidean distance, a manhattan distance, a chebyshev distance, or the like, and is not particularly limited herein.

104. Determining a health status of the device based on a comparison of the distance to different distance threshold intervals in the running sample library.

Specifically, sample characteristics representing that the equipment is in a complete health state in the operation sample library can be obtained by extraction based on batch historical operation data of the equipment group, and meanwhile, the health state of the equipment is represented by using different distance threshold intervals in the operation sample library, so that the problems that fault data under different health states are scarce and difficult to define are effectively solved.

As an embodiment of the present invention, the preset comprehensive weighting coefficient is obtained based on fusing a subjective weighting coefficient and an objective weighting coefficient;

the subjective weighting coefficient is determined based on a scoring result obtained by scoring each operation parameter sample according to a preset rule;

the objective weighting coefficients are determined based on the data-inherent relevance of each of the operational parameter samples.

Specifically, the preset rule for determining the subjective weighting factor may be set to be a scoring item such as a difficulty level of component maintenance and an influence level on the whole machine operation by combining expert knowledge, and then the subjective weighting factor of each operation parameter sample is determined by a method such as an analytic hierarchy process according to the preset rule for each operation parameter sample.

More specifically, the data intrinsic correlation of the operation parameter samples can be obtained by normalizing each operation parameter sample and then using a method such as an entropy method.

It should be noted that the operation parameter samples of the equipment are weighted by integrating subjective and objective factors, so that the setting of the weighting coefficient by integrating the subjective use factors and the influence of the objective data relevance is realized, and the obtained multidimensional space can more accurately represent the health state of the equipment.

As an embodiment of the present invention, the acquiring operation parameters of the device and calculating to obtain feature quantities of the operation parameters includes:

acquiring preset specific operation parameters of the equipment; calculating to obtain the characteristic quantity of each preset specific operation parameter;

specifically, the specific operation parameter is a predetermined operation parameter which has a main influence on the health state of the equipment;

the method for determining the preset specific operation parameter comprises the following steps:

obtaining each operation parameter sample of the equipment in a first time window width, and calculating to obtain the characteristic quantity of each operation parameter sample;

weighting the characteristic quantity of each operation parameter sample based on the preset comprehensive weighting coefficient to obtain the evaluation sample characteristic of the equipment;

and performing dimension reduction processing on the evaluation sample characteristics, and determining the preset specific operation parameters.

Specifically, in consideration of the large data processing amount of the evaluation of the health state of the device by using all the operation parameters of the device during operation, in the embodiment of the present invention, the health state of the device is evaluated based on the predetermined specific operation parameters that mainly affect the health state of the device.

More specifically, in the embodiment of the present invention, firstly, based on a set first time window width, each operation parameter sample of the device is obtained from historical operation data of the device, and then a feature quantity of each operation parameter sample is obtained through calculation; then weighting the characteristic quantity of each operation parameter sample based on a preset comprehensive weighting coefficient to obtain a weighted characteristic table A1 of batch historical operation data, further realizing the treatment on the influence of subjective use demand factors and objective data relevance of each operation parameter sample comprehensive device, enabling the characteristic selection for health evaluation to be optimized more pertinently, obtaining original input data (primary evaluation sample characteristics) for characteristic dimension reduction, then utilizing PCA (principal component analysis) to reduce the dimension of the primary evaluation sample characteristics, further orthogonalizing all the characteristics, then selecting the operation parameters corresponding to the characteristic quantity of the first n operation parameter samples as preset specific operation parameters for evaluating the health state of the whole machine of the device, thereby realizing the selection of the operation parameters, and simultaneously, decoupling the selected health evaluation characteristics through dimension reduction treatment, and effectively realizes the data dimension reduction and reduces the space-time complexity of the health evaluation algorithm operation.

As an embodiment of the present invention, the acquiring preset specific operating parameters of a device, and calculating and obtaining feature quantities of each preset specific operating parameter includes:

acquiring preset specific operation parameters of the equipment in each second time window width based on a preset step length; the second time window width is at least greater than a set multiple of the first time window width;

and calculating and obtaining the characteristic quantity of each preset specific operation parameter based on the proportional relation between the second time window width and the first time window width.

Specifically, assuming that an operation parameter sample of the equipment is extracted from historical operation data of the equipment, a first time window width on which a feature quantity of the operation parameter sample depends is calculated as w1, a preset specific operation parameter of the equipment is obtained in real time, a second time window width on which the feature quantity of the preset specific operation parameter depends is calculated as w2, a preset step length, namely a window moving step length is p1, and meanwhile, since one feature quantity of one operation parameter can be obtained from each w1, by limiting w2> b w1, wherein b is a set multiple (b is an integer and is greater than a set threshold), so that the feature quantities of c w2/w1 operation parameters can be obtained for each operation parameter in each w2, namely, the number of the obtained feature quantities of the preset specific operation parameter is matched with the ratio number c of the second time window width and the first time window width, namely, is equal to the multidimensional space for obtaining the health state of the c-group representation equipment, and then the distance between the c groups of multidimensional spaces and the sample characteristics representing the health state of the equipment is calculated, so that the accuracy of the health state evaluation of the equipment can be effectively improved.

In the embodiment of the invention, aiming at equipment running in real time, a fixed-length time window is taken to calculate a weighted health evaluation feature list cluster in the window, the distance from each health evaluation feature in the cluster to a standard health evaluation feature list of a health state is respectively calculated, the health state of the equipment is judged by combining distance thresholds of different health states, the noise influence of sensor data can be effectively smoothed by presetting step length, the fluctuation of the health evaluation result of the equipment is further avoided, and the accuracy of the whole health state evaluation of the equipment is further improved.

As an embodiment of the present invention, the determining the health status of the device based on the comparison of the distance with different distance threshold intervals in the running sample library includes:

determining a health status of the device based on a proportion of the distances falling within different distance threshold intervals in the running sample library.

Specifically, it is assumed that H0, H1, H2, H3, and … respectively represent the health states of the entire devices corresponding to different distance threshold intervals stored in the running sample library, and in the last w2, the health state of the estimated entire device is H0, the first time window width is w1, and the second time window width is w2 are taken as examples, then c distance values of the health evaluation characteristics to the complete health state can be obtained by calculation, so if the distance values exceeding a certain proportion in one time window width w2 all fall within the health state H1 interval, the health state of the entire device of the time window width is determined to be H1, otherwise, the health state of the entire device within the time window width is still H0.

As an embodiment of the present invention, the running of different distance threshold intervals in the sample library includes:

the distance interval between the sample characteristics representing the equipment in different health states and the sample characteristics representing the equipment in a complete health state;

the acquisition method for characterizing the sample characteristics of the equipment in different health states comprises the following steps:

operating parameter samples of the equipment in different health states are called by the operating sample library;

and obtaining sample characteristics characterizing the equipment in different health states based on the operation parameter samples of the equipment in different health states.

Specifically, before the running sample library is actually applied, the running parameter samples can be obtained by analyzing based on a large amount of historical running data of the equipment, so that the problem of sparse running parameter data of the characterization equipment in each health state is effectively solved, meanwhile, the closer the sample characteristics of the characterization equipment in the complete health state are, the better the complete machine health state of the equipment is, and therefore, based on different distance intervals, the health state of the complete machine of the equipment can be flexibly divided into multiple types according to needs, for example: critical failure, malfunction, sub-health, healthy, very healthy, etc.

As an embodiment of the present invention, the operation parameter samples of the equipment in different health states called from the operation sample library are operation parameter samples obtained by deleting and/or modifying operation parameter samples that do not satisfy the aging rules based on preset aging rules; and

based on a data amplification method, when the number of any one of the operation parameter samples is less than the corresponding set sample standard quantity, performing sample quantity amplification on the operation parameter samples of which the number is less than the corresponding set sample standard quantity; wherein the sample size of the amplified running parameter sample does not exceed a set number threshold.

Specifically, continuous deletion and/or modification of the operation parameter samples in the sample library can be realized by reasonably setting an aging rule, wherein the deletion of the operation parameter samples is to remove the samples judged to be invalid, and the modification is to modify the sample data.

More specifically, taking the example of deleting the operation parameter samples, the aging rule may be set to limit the use duration of the samples, that is, the aging samples are removed according to the use duration of the samples; taking the example of modifying the operation parameter sample, the aging rule can be set as the reference equipment key technical modification, namely modifying the sample after the equipment key technical modification; likewise, the aging rules may also be set to limit the length of time the sample is used and to reference device critical technology, thereby enabling continuous pruning and modification of the sample. The result of the health evaluation can be guaranteed to have timeliness through the preset aging rule, and each distance threshold can be updated in real time.

Furthermore, the number of the operation parameter samples in the operation sample library can be checked based on a preset time period or in real time, and sample amplification is performed appropriately, for example, when the sample amount described by the health states of serious failure, sub-health, very health and the like is insufficient, the sample amount amplification is performed by a data amplification method such as a Synthetic Minority Oversampling method (SMOTE) and the like, so that the problem of inaccurate evaluation result caused by the insufficient sample amount can be further overcome, and meanwhile, the accuracy of the samples can be ensured and the balance of the sample amount in the operation sample library can be ensured by limiting the sample amount passing through the sample amplification not to exceed a number threshold, for example, not to exceed a certain percentage of the total sample amount.

As an embodiment of the present invention, the operation parameter samples of the equipment in different health states called from the operation sample library are operation parameters extracted from operation parameter big data of the equipment based on the obtained maintenance service feedback information and the customer feedback information of the equipment.

Specifically, the equipment should be in a normal operation state in most of the time, so that the operation parameter sample amount for the equipment in a complete health state is quite abundant, and relatively, the operation parameter samples for the equipment in different health states are sparse, considering that the maintenance service feedback information generally records the operation parameters of the equipment in a certain time period according to the abnormal condition of the equipment, and the customer generally feeds back the information when the equipment is abnormally operated, so that the operation parameters of the equipment in an abnormal operation state generally exist when the maintenance service feedback information and the customer feedback information exist in the equipment.

More specifically, the current equipment operation is based on the fact that the operation parameter of the equipment is in a real-time recorded state, and then big data of the operation parameter of the equipment is formed, so that by accessing the maintenance service feedback information and the customer feedback information (considering the difference of the understanding degree of the customer on the equipment, the customer feedback information is preferably verified customer feedback information), the operation parameter which characterizes the equipment in an incomplete health state can be extracted from the big data of the operation parameter of the equipment according to the maintenance service feedback information and the equipment operation time period corresponding to the customer feedback information, and the parameters are taken as operation parameter samples in the operation sample library, so as to supplement the operation parameter samples which characterize the equipment in different health states in the operation sample library, and then the real-time update of the operation parameter samples is realized, and the problem that the operation parameter samples representing the equipment in different health states are sparse in the operation parameter sample library is further solved, so that the accuracy of evaluating the health state of the whole equipment by applying the method provided by the embodiment of the invention is further improved.

The overall process of the equipment health assessment method according to the above embodiment of the present invention, which includes the steps of constructing the early-stage operation sample library, updating the samples in the operation sample library in real time, and assessing the overall health status of the equipment in real time by using the operation sample library, is shown in fig. 2, and includes:

201. acquiring equipment operation parameters from equipment operation historical data;

202. determining subjective weighting coefficients of the operating parameters;

203. determining objective weighting coefficients of the operating parameters;

204. determining a comprehensive weighting coefficient of the operation parameter;

205. weighting the characteristic quantity of each operation parameter;

206. performing data dimension reduction on the weighted characteristic quantity of each operating parameter to select a specific operating parameter;

207. dynamically deleting and/or modifying the operation parameter samples in the operation sample library according to a preset aging rule, and amplifying the operation parameter samples based on a data amplification method;

208. extracting operation parameters from operation parameter big data of equipment as operation parameter samples based on the maintenance service feedback information and the client feedback information;

209. calculating the distance value between the running parameter sample representing each health state and the running parameter sample representing the complete health state;

210. determining distance threshold value intervals representing all health states of the equipment based on the distance values obtained through calculation;

211. acquiring specific operation parameters of the equipment in real time according to the second time window width to acquire characteristic quantities of the specific operation parameters;

212. calculating the distance between the characteristic quantity of the specific operation parameter and the sample characteristic quantity representing that the equipment is in a complete health state;

213. and obtaining the health state of the whole equipment in the second time window width based on the proportion of the distance values falling into the distance threshold intervals.

The equipment health assessment method is an engineering machinery health assessment method based on the distance similarity criterion of the operation sample library, can be used for weighting the operation parameters of the engineering machinery by integrating subjective and objective factors, effectively reflects the subjective use requirements of equipment and the objective relevance of operation parameter data, and can be used for optimizing the feature selection for health assessment in a more targeted manner; after the operation parameters and the comprehensive weighting coefficients thereof are determined, the data dimension reduction is used for reducing the dimension of the characteristics, all the characteristics can be further orthogonalized, the selected health evaluation characteristics are decoupled, and the data dimension reduction is effectively realized and the space-time complexity of the operation of the health evaluation algorithm is reduced; meanwhile, by providing an effective dynamic adding and deleting mechanism framework of the sample library, the timeliness of the health evaluation result can be ensured; the sliding time window is selected for the real-time operation equipment, the health state of the equipment is determined according to the proportion of the Mahalanobis distance in the time window, and sudden change of the health state caused by sudden change of the distance due to data fluctuation of the sensor can be effectively avoided.

In the following, a device health assessment system provided by the present invention is described, and a device health assessment system described below and a device health assessment method described above may be referred to in correspondence.

As shown in fig. 3, the device health assessment system provided by the present invention includes a data acquisition module 310, a feature calculation module 320, a distance calculation module 330, and a status assessment module 340; wherein the content of the first and second substances,

the data obtaining module 310 is configured to obtain an operating parameter of a device;

the characteristic calculation module 320 is configured to calculate a characteristic quantity of the operating parameter, and weight each of the operating parameters based on a preset comprehensive weighting coefficient of each of the operating parameters to obtain an evaluation characteristic of the device;

the distance calculation module 330 is configured to calculate a distance between the evaluation feature and a sample feature called from a running sample library of the device and characterizing that the device is in a full health state;

the status evaluation module 340 is configured to determine the health status of the device based on a comparison of the distance to different distance threshold intervals in the running sample library.

It should be noted that, in the equipment health assessment system provided by the invention, firstly, the collected operation parameters of the equipment are weighted based on the predetermined comprehensive weighting coefficients corresponding to the operation parameters, so as to obtain the evaluation characteristics capable of reflecting the health state of the whole equipment; then calculating the distance between the evaluation characteristics and the characteristics of the samples representing the equipment in a complete health state in the running sample library; finally, the overall health state of the equipment can be accurately evaluated based on the comparison of the distance between the evaluation characteristics of the equipment and the sample characteristics of the equipment in the complete health state and different distance threshold intervals stored in a running sample library.

In a preferred scheme, the preset comprehensive weighting coefficient is obtained based on a fusion subjective weighting coefficient and an objective weighting coefficient;

the subjective weighting coefficient is determined based on a scoring result obtained by scoring each operation parameter sample according to a preset rule;

the objective weighting coefficients are determined based on the data-inherent relevance of each of the operational parameter samples.

In a preferred embodiment, the data acquisition module acquires preset specific operating parameters of the equipment; the preset specific operation parameters are predetermined operation parameters which mainly affect the health state of the equipment;

the equipment health evaluation system also comprises a second data acquisition module, a second characteristic acquisition module and a preset specific operation parameter determination module; wherein the content of the first and second substances,

the second data acquisition module is used for acquiring each operation parameter sample of the equipment in a first time window width and calculating and acquiring the characteristic quantity of each operation parameter sample;

the second characteristic acquisition module is used for weighting the characteristic quantity of each operation parameter sample based on the preset comprehensive weighting coefficient to obtain the evaluation sample characteristic of the equipment;

the preset specific operation parameter determining module is used for performing dimension reduction processing on the evaluation sample characteristics and determining the preset specific operation parameters.

In a preferred embodiment, the data acquisition module is further configured to acquire a preset specific operating parameter of the device within each second time window width based on a preset step length; the second time window width is at least greater than a set multiple of the first time window width; and calculating and obtaining the characteristic quantity of the preset specific operation parameter based on the proportional relation between the second time window width and the first time window width.

In a preferred embodiment, the state evaluation module is specifically configured to determine the health state of the device based on a proportion of the distances falling into different distance threshold intervals in the running sample library.

In a preferred embodiment, the running sample library includes different distance threshold intervals, including:

the distance interval between the sample characteristics representing the equipment in different health states and the sample characteristics representing the equipment in a complete health state;

the equipment health evaluation system also comprises a data retrieval module; the data calling module is used for calling running parameter samples of the equipment in different health states from the running sample library; and obtaining sample characteristics characterizing the equipment in different health states based on the operation parameter samples of the equipment in different health states.

In a preferred embodiment, the equipment health assessment system further comprises a data updating module and a data amplification module; wherein the content of the first and second substances,

the data updating module is used for deleting and/or modifying the operation parameter samples which do not meet the aging rules in the operation sample library based on a preset aging rule;

the data amplification module is used for carrying out sample size amplification on the operation parameter samples of which the number is less than the corresponding set sample standard quantity based on a data amplification method when the number of any operation parameter sample is less than the corresponding set sample standard quantity, and the sample size of the amplified operation parameter samples does not exceed a set number threshold.

In a preferred embodiment, the data updating module is further configured to extract the operation parameters from the operation parameter big data of the equipment based on the maintenance service feedback information and the customer feedback information of the equipment.

The equipment health assessment system of the invention is used for the equipment health assessment method of the foregoing embodiments. Therefore, the descriptions and definitions in the device health assessment method in the foregoing embodiments can be used for understanding the execution modules in the embodiments of the present invention.

The invention also provides equipment comprising the equipment health assessment system.

It should be noted that the device provided by the present invention is a device including the device health assessment system, and therefore, all advantages and technical effects of the device health assessment system are provided, and no further description is provided herein.

Fig. 4 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 4: a processor (processor)410, a communication Interface 420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. Processor 410 may invoke logic instructions in memory 430 to perform a method of device health assessment, the method comprising: acquiring operation parameters of equipment, and calculating to obtain characteristic quantities of the operation parameters; weighting the characteristic quantity of each operation parameter based on a preset comprehensive weighting coefficient of each operation parameter to obtain the evaluation characteristic of the equipment; calculating the distance between the evaluation feature and a sample feature which is called from a running sample library of the equipment and is used for representing that the equipment is in a full health state; determining a health status of the device based on a comparison of the distance to different distance threshold intervals in the running sample library.

In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform a method for device health assessment provided by the above methods, the method comprising: acquiring operation parameters of equipment, and calculating to obtain characteristic quantities of the operation parameters; weighting the characteristic quantity of each operation parameter based on a preset comprehensive weighting coefficient of each operation parameter to obtain the evaluation characteristic of the equipment; calculating the distance between the evaluation feature and a sample feature which is called from a running sample library of the equipment and is used for representing that the equipment is in a full health state; determining a health status of the device based on a comparison of the distance to different distance threshold intervals in the running sample library.

In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of device health assessment, the method comprising: acquiring operation parameters of equipment, and calculating to obtain characteristic quantities of the operation parameters; weighting the characteristic quantity of each operation parameter based on a preset comprehensive weighting coefficient of each operation parameter to obtain the evaluation characteristic of the equipment; calculating the distance between the evaluation feature and a sample feature which is called from a running sample library of the equipment and is used for representing that the equipment is in a full health state; determining a health status of the device based on a comparison of the distance to different distance threshold intervals in the running sample library.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A device health assessment method, comprising:

acquiring operation parameters of equipment, and calculating to obtain characteristic quantities of the operation parameters;

weighting the characteristic quantity of each operation parameter based on a preset comprehensive weighting coefficient of each operation parameter to obtain the evaluation characteristic of the equipment;

calculating the distance between the evaluation feature and a sample feature which is called from a running sample library of the equipment and is used for representing that the equipment is in a full health state;

determining a health status of the device based on a comparison of the distance to different distance threshold intervals in the running sample library.

2. The equipment health assessment method according to claim 1, wherein said preset integrated weighting coefficients are obtained based on fusing subjective weighting coefficients and objective weighting coefficients;

the subjective weighting coefficient is determined based on a scoring result obtained by scoring each operation parameter sample according to a preset rule;

the objective weighting coefficients are determined based on the data-inherent relevance of each of the operational parameter samples.

3. The equipment health assessment method according to claim 2, wherein the acquiring of the operating parameters of the equipment and the calculating of the feature quantity of each of the operating parameters comprises:

acquiring preset specific operating parameters of the equipment, and calculating to obtain characteristic quantities of the preset specific operating parameters;

the method for determining the preset specific operation parameter comprises the following steps:

obtaining each operation parameter sample of the equipment in a first time window width, and calculating to obtain the characteristic quantity of each operation parameter sample;

weighting the characteristic quantity of each operation parameter sample based on the preset comprehensive weighting coefficient to obtain the evaluation sample characteristic of the equipment;

and performing dimension reduction processing on the evaluation sample characteristics, and determining the preset specific operation parameters.

4. The equipment health assessment method according to claim 3, wherein the acquiring of the preset specific operating parameters of the equipment and the calculating of the feature quantity of each preset specific operating parameter comprises:

acquiring preset specific operation parameters of the equipment in each second time window width based on a preset step length; the second time window width is at least greater than a set multiple of the first time window width;

and calculating and obtaining the characteristic quantity of each preset specific operation parameter based on the proportional relation between the second time window width and the first time window width.

5. The device health assessment method of claim 4, wherein said determining the health status of the device based on the comparison of the distance to different distance threshold intervals in the running sample library comprises:

determining a health status of the device based on a proportion of the distances falling within different distance threshold intervals in the running sample library.

6. The device health assessment method of claim 3, wherein the running of different distance threshold intervals in the sample library comprises:

the distance interval between the sample characteristics representing the equipment in different health states and the sample characteristics representing the equipment in a complete health state;

the acquisition method for characterizing the sample characteristics of the equipment in different health states comprises the following steps:

calling running parameter samples of the equipment in different health states by the running sample library;

and obtaining sample characteristics characterizing the equipment in different health states based on the operation parameter samples of the equipment in different health states.

7. The equipment health assessment method according to claim 6, wherein the operation parameter samples of the equipment called by the operation sample library under different health states are operation parameter samples obtained by deleting and/or modifying operation parameter samples which do not meet the aging rules based on preset aging rules; and

based on a data amplification method, when the number of any one of the operation parameter samples is less than the corresponding set sample standard quantity, carrying out sample quantity amplification on the operation parameter samples with the number less than the corresponding set sample standard quantity; wherein the sample size of the amplified running parameter sample does not exceed a set number threshold.

8. The equipment health assessment method according to claim 6, wherein the operation parameter samples of the equipment under different health states called by the operation sample library are operation parameters extracted from operation parameter big data of the equipment based on the maintenance service feedback information and the customer feedback information of the equipment.

9. An equipment health assessment system, comprising:

the data acquisition module is used for acquiring the operating parameters of the equipment;

the characteristic calculation module is used for calculating the characteristic quantity of the operation parameters, and weighting the characteristic quantity of each operation parameter based on the preset comprehensive weighting coefficient of each operation parameter to obtain the evaluation characteristic of the equipment;

the distance calculation module is used for calculating the distance between the evaluation feature and a sample feature which is called from a running sample library of the equipment and is used for representing that the equipment is in a complete health state;

a state evaluation module to determine a health state of the device based on a comparison of the distance to different distance threshold intervals in the running sample library.

10. A device comprising the device health assessment system of claim 9.

Images