Rail transit signal equipment state evaluation method and device, medium and electronic equipment

Abstract

The invention discloses a rail transit signal equipment state assessment method and device, a medium and electronic equipment, and the method comprises the steps: obtaining the equipment failure time corresponding to a to-be-assessed equipment class, and determining the failure rate type of the to-be-assessed equipment class based on the equipment failure time; determining a state evaluation index for the to-be-evaluated equipment class based on the failure rate type, and determining an evaluation index weight corresponding to the state evaluation index; and performing state evaluation on the to-be-evaluated equipment class by adopting the evaluation index weight and the state evaluation index. According to the technical scheme, the evaluation accuracy of the equipment operation state can be improved, and the operation stability of the rail transit system is improved.

Description

Technical Field

[0001] This application relates to the technical field of rail transit safety. Specifically, this application relates to a method, device, medium, and electronic device for evaluating the state of rail transit signal equipment. Background Art

[0002] During the operation of rail transit signal equipment, accurately grasping the change in the failure rate of rail transit signal equipment is crucial for comprehensively understanding the equipment operation status and ensuring the stable operation of the rail transit system.

[0003] In related technologies, the analysis of the failure rate of rail transit signal equipment mostly relies on general models or simple statistical data, such as the common bathtub curve model. However, in some complex industrial production environments, rail transit signal equipment may be affected by multiple factors in a cross - influence manner, and its failure rate curve does not present a typical bathtub shape. This makes it impossible to accurately evaluate the equipment operation status based on the bathtub curve model, thereby affecting the stable operation of the rail transit system. Summary of the Invention

[0004] This application provides a method, device, medium, and electronic device for evaluating the state of rail transit signal equipment, which can realize the quantitative evaluation of the equipment operation status, and can achieve the purpose of improving the evaluation accuracy of the equipment operation status and the stability of the rail transit system operation.

[0005] According to the first aspect of this application, a method for evaluating the state of rail transit signal equipment is provided. The method includes:

[0006] Obtain the equipment failure time corresponding to the equipment class to be evaluated, and determine the failure rate type of the equipment class to be evaluated based on the equipment failure time;

[0007] Based on the failure rate type, determine the state evaluation index for the equipment class to be evaluated, and determine the evaluation index weight corresponding to the state evaluation index;

[0008] Use the evaluation index weight and the state evaluation index to evaluate the state of the equipment class to be evaluated.

[0009] According to the second aspect of this application, a device for evaluating the state of rail transit signal equipment is provided. The device includes:

[0010] A failure rate type determination module, configured to obtain the equipment failure time corresponding to the equipment class to be evaluated, and determine the failure rate type of the equipment class to be evaluated based on the equipment failure time;

[0011] An index weight determination module, configured to determine state evaluation indexes for the device class to be evaluated based on the failure rate type, and determine the evaluation index weights corresponding to the state evaluation indexes;

[0012] A state evaluation module, configured to perform state evaluation on the device class to be evaluated by using the evaluation index weights and the state evaluation indexes.

[0013] According to the third aspect of the present invention, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the rail transit signal device state evaluation method as described in the embodiment of the present application.

[0014] According to the fourth aspect of the present invention, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the rail transit signal device state evaluation method as described in the embodiment of the present application.

[0015] According to the fifth aspect of the present application, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the rail transit signal device state evaluation method as described in the embodiment of the present application.

[0016] The technical solution of the present application takes the device failure time of the device class to be evaluated as the entry point, analyzes the device failure characteristics of the device class to be evaluated, and obtains the failure rate type of the device class to be evaluated. By using state evaluation indexes adapted to the failure rate type and combining evaluation index weights, it effectively realizes the scientific quantitative evaluation of the operation state of rail transit signal devices. Compared with using a general model such as the bathtub curve model to analyze the failure rate of rail transit signal devices based on statistical assumptions, the embodiment of the present application is based on the actual failure time of the device class to be evaluated, fully considers the complexity and differences of the industrial production environments where different rail transit signal devices are located, realizes the customized analysis of the device class to be evaluated, realizes the quantitative evaluation of the device operation state, improves the evaluation accuracy of the device operation state, and is beneficial to improving the operation stability of the rail transit system.

[0017] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. Description of the Drawings

[0018] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0019] Figure 1 It is a flowchart of the method for evaluating the status of rail transit signal equipment provided in Embodiment 1;

[0020] Figure 2 It is a flowchart of the method for evaluating the status of rail transit signal equipment provided in Embodiment 2;

[0021] Figure 3 It is a schematic structural diagram of the device for evaluating the status of rail transit signal equipment provided in Embodiment 3 of the present application;

[0022] Figure 4 It is a schematic structural diagram of an electronic device provided in Embodiment 4 of the present application. Detailed implementation manners

[0023] In order to enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0024] It should be noted that the terms "first", "second", "target", and "candidate" in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0025] Embodiment 1

[0026] Figure 1It is a flowchart of a method for evaluating the state of rail transit signal equipment provided in Embodiment 1. This embodiment is applicable to the situation of evaluating the state of rail transit signal equipment in a rail transit system. This method can be executed by a rail transit signal equipment state evaluation device, which is implemented in the form of hardware and / or software and can be integrated into an electronic device operating this system.

[0027] As Figure 1 shown, the method includes:

[0028] S110. Obtain the equipment failure time corresponding to the equipment class to be evaluated, and determine the failure rate type of the equipment class to be evaluated based on the equipment failure time.

[0029] S120. Determine state evaluation indicators for the equipment class to be evaluated based on the failure rate type, and determine the evaluation index weights corresponding to the state evaluation indicators.

[0030] S130. Perform a state evaluation on the equipment class to be evaluated by using the evaluation index weights and the state evaluation indicators.

[0031] Among them, the equipment class to be evaluated refers to a certain type of rail transit signal equipment that needs to be evaluated for its state. The equipment failure time refers to the specific time point when the safety and effectiveness of the rail transit signal equipment belonging to the equipment class to be evaluated can no longer be guaranteed after reaching the end of its service life.

[0032] Optionally, the equipment failure time corresponding to the equipment class to be evaluated can be collected from the operation logs and fault records of the rail transit signal equipment. The original failure data collected from the operation logs and fault records needs to be further cleaned. Exemplarily, after removing duplicate values, handling missing values, correcting error values, and normalizing the data for the original failure data, the equipment failure time of the equipment class to be evaluated is obtained.

[0033] The equipment failure time is used to determine the failure rate type of the equipment class to be evaluated. Optionally, by determining the probability density function of the equipment failure time, a failure rate curve is plotted. The failure rate type of the equipment class to be evaluated is determined according to the increasing and decreasing trends of the probability density function and the failure rate curve.

[0034] Among them, the failure rate type is used to measure the change of the failure rate during the entire life cycle of the device class to be evaluated. Optionally, the failure rate types include increasing type, decreasing type, and balanced type, corresponding to the three failure stages of the bathtub curve model, namely the early failure period, the accidental failure period, and the wear-out failure period. The early failure period is characterized by a relatively high initial failure rate, which rapidly decreases over time, and the curve is of the decreasing type. The accidental failure period is characterized by a stable failure rate at a relatively low level, and the curve is approximately horizontal, belonging to the constant type. The wear-out failure period is characterized by a sharp increase in the failure rate, and the curve is of the increasing type, indicating the end of the product life.

[0035] Among them, the failure rate type is used to determine the status evaluation index of the device class to be evaluated. The status evaluation index is related to the failure rate type of the device class to be evaluated and is used to evaluate the operating status of the device class to be evaluated.

[0036] The failure rate levels corresponding to different failure rate types are different, and there are differences in the status evaluation indexes used for device classes to be evaluated with different failure rate types. Optionally, based on the correspondence between the preset failure rate type and the status evaluation index, the status evaluation index corresponding to the failure rate type is determined.

[0037] The evaluation index weights corresponding to the status evaluation indexes are used to coordinate the relative importance among different indexes to ensure the scientificity and objectivity of the evaluation results. Each status evaluation index has corresponding evaluation index weights.

[0038] Optionally, the evaluation index weights are obtained by combining subjective weighting and objective weighting. Subjective weighting incorporates industry prior knowledge, and objective weighting is completely determined by the degree of data variation. Optionally, the evaluation index weights include expert weights and entropy weights. Expert weights belong to subjective weighting, and entropy weights belong to objective weighting.

[0039] Optionally, the status evaluation indexes are weighted using the evaluation index weights, and the status of the device class to be evaluated is evaluated based on the obtained weighted results.

[0040] The technical solution of this application takes the device failure time of the device class to be evaluated as the entry point, analyzes the device failure characteristics of the device class to be evaluated, and obtains the failure rate type of the device class to be evaluated. By using the status evaluation indexes adapted to the failure rate type and combining the evaluation index weights, it effectively realizes the scientific quantitative evaluation of the operating status of rail transit signal devices. Compared with using a general model such as the bathtub curve model to analyze the failure rate of rail transit signal devices based on statistical assumptions, the embodiments of this application are based on the actual failure time of the device class to be evaluated, fully considering the complexity and differences of the industrial production environments where different rail transit signal devices are located, realizing the customized analysis of the device class to be evaluated, realizing the quantitative evaluation of the device operating status, improving the evaluation accuracy of the device operating status, and being beneficial to improving the stability of the rail transit system operation.

[0041] In an optional embodiment, determining the status evaluation index for the device class to be evaluated based on the failure rate type includes: if the failure rate type is a balanced type, determining the number of failures as the status evaluation index of the device class to be evaluated; if the failure rate type is an increasing type, determining at least two of the wavelet total energy, the last moment failure rate value, the average failure time, the median failure time and the characteristic failure time as the status evaluation index of the device class to be evaluated; if the failure rate type is a decreasing type, determining at least two of the wavelet total energy, the first failure time, the 20,000-hour failure rate value, the average failure time, the median failure time and the characteristic failure time as the status evaluation index of the device class to be evaluated.

[0042] Among them, the balanced type corresponds to the accidental failure period of the bathtub curve model, which is characterized by a stable failure rate at a low level, belonging to the constant type. The number of failures is determined as the status evaluation indicator of the equipment class to be evaluated. Optionally, by counting the number of equipment failure times of the equipment class to be evaluated, the number of equipment failure times is determined as the number of failures. When the failure rate type is balanced, the number of failures is negatively correlated with the equipment operating status. The more failures, the worse the equipment operating status.

[0043] The increasing type corresponds to the wear-out failure period of the bathtub curve model, which is manifested by a sharp increase in the failure rate, marking the end of the product life. This indicates that the equipment type to be evaluated has experienced an accidental failure period, and at least two of the wavelet total energy, last-moment failure rate value, average failure time, median failure time, and characteristic failure time are determined as status evaluation indicators for the equipment type to be evaluated. The decreasing type corresponds to the early failure period of the bathtub curve model, which is manifested by a high initial failure rate that decreases rapidly over time. This indicates that the equipment type to be evaluated has not yet reached the accidental failure period, and at least two of the wavelet total energy, first failure time, 20,000-hour failure rate value, average failure time, median failure time, and characteristic failure time are determined as status evaluation indicators for the equipment type to be evaluated.

[0044] Among them, the total wavelet energy is used to quantify the steepness of the failure rate change. The larger the total wavelet energy, the more drastic the failure rate change and the higher the steepness. Conversely, the smaller the total wavelet energy, the smoother the failure rate change and the lower the steepness. The failure rate curve obtained by fitting the equipment failure time is decomposed by wavelet packets to divide the signal energy by frequency band, and the sum of the energy of each sub-band is the total wavelet energy. The last moment failure rate value refers to the failure rate at the last moment recorded by the equipment failure time. The average failure time is based on the probability density function of the equipment class to be evaluated. Determine, optionally, mean time to failure use Calculated. The average failure time is used to reflect the overall reliability level. The median failure time refers to the time when 50% of the equipment in the equipment class to be evaluated fails. The characteristic failure time refers to the time when 63.2% of the equipment in the equipment class to be evaluated fails, which is used to describe the concentrated failure characteristics of the wear-out failure period.

[0045] The first failure time refers to the time when the equipment to be evaluated fails for the first time after it is put into use. The 20,000-hour failure rate value refers to the failure rate of the equipment to be evaluated at the time corresponding to 20,000 hours after it is put into use.

[0046] When the failure rate type is increasing, the mean failure time, median failure time, and characteristic failure time are positive indicators, that is, the higher the value, the better the equipment operation status. The last moment failure rate value and wavelet total energy are negative indicators, that is, the higher the value, the worse the equipment operation status.

[0047] When the failure rate type is decreasing, the first failure time, mean failure time, median failure time, characteristic failure time and wavelet total energy are positive indicators, that is, the higher the evaluation index value corresponding to the positive indicator, the better the equipment operation status; the 20,000-hour failure rate value is a negative indicator, that is, the higher the evaluation index value corresponding to the negative indicator, the worse the equipment operation status. For the decreasing failure rate type, the larger the wavelet total energy, the more drastic the change in failure rate and the higher the steepness, indicating that the equipment to be evaluated can reach the accidental failure period faster; conversely, the smaller the wavelet total energy, the more gradual the change in failure rate and the lower the steepness, indicating that the equipment to be evaluated will reach the accidental failure period more slowly.

[0048] The above technical scheme provides a practical scheme for determining status evaluation indicators, which is used to adapt the failure mechanism and reliability characteristics of the failure stage corresponding to the failure rate type, and uses the status evaluation indicators matching the failure rate type to perform status evaluation on the equipment type to be evaluated, thereby realizing a multi-dimensional evaluation of the equipment operating status, avoiding the one-sidedness of single indicator evaluation, realizing a scientific and quantitative evaluation of the operating status of rail transit signal equipment, and improving the evaluation accuracy of the equipment operating status.

[0049] In an optional embodiment, determining the evaluation indicator weight corresponding to the state evaluation indicator includes: obtaining the expert weight of the state evaluation indicator; using the entropy weight method to determine the entropy weight of the state evaluation indicator based on the evaluation indicator value corresponding to the state evaluation indicator; and determining the evaluation indicator weight corresponding to the state evaluation indicator based on the expert weight and the entropy weight.

[0050] Among them, the expert weight belongs to subjective weighting and incorporates prior industry knowledge. The entropy weight belongs to objective weighting and is determined by the degree of data variation. The entropy weight is determined by the entropy weight method and is determined by the evaluation index values corresponding to the state evaluation indicators. The greater the degree of data variation, the higher the information content, and the corresponding greater the entropy weight. Optionally, the expert weight and the entropy weight are used for weighted processing to obtain a weighted processing result, and the weighted processing result is determined as the evaluation index weight corresponding to the state evaluation indicator.

[0051] In the above technical solution, by comprehensively determining the evaluation index weight based on the expert weight and the entropy weight, the evaluation index weight not only retains the expert knowledge and considers the actual business meaning of the index but also reduces the subjective randomness, and has both scientificity and interpretability, solving the problem that the evaluation index weight in the past was fixed and difficult to adapt to the complex and changeable operating environment.

[0052] In some alternative embodiments, the state of the device to be evaluated is evaluated using the evaluation index weight and the state evaluation index, including: querying the score range using the evaluation index value corresponding to the state evaluation index to obtain the target score range corresponding to the evaluation index value; determining the state index score corresponding to the state evaluation index based on the target score range; weighting the state index score using the evaluation index weight to obtain the device state score of the device to be evaluated; and evaluating the state of the device to be evaluated using the device state score.

[0053] Among them, the score range is divided based on a large amount of real data, standards, and expert experience. Querying the score range using the evaluation index value corresponding to the state evaluation index can obtain the target score range. Among them, the target score range is adapted to the evaluation index value.

[0054] The state evaluation index is related to the failure rate type. Optionally, an initial score range is determined for the failure rate type, and then, based on the evaluation index value corresponding to the state evaluation index, the score range is queried to determine the target score range corresponding to the evaluation index value. Exemplarily, the initial score range for the balanced failure rate is set to [80, 100], the initial score range for the decreasing failure rate is set to [70, 80), and the initial score range for the increasing failure rate is set to [60, 70).

[0055] When the target score range is determined, the state index score corresponding to the target score range can be further obtained. In this way, both the state index score corresponding to the state evaluation index and the evaluation index weight are determined. Weighting the state index score using the evaluation index weight, the obtained evaluation weighted result is the device state score of the device to be evaluated.

[0056] Among them, the device status score is used to quantify the operating status of the device class to be evaluated. The device status score is positively correlated with the operating status of the device class to be evaluated. The higher the device status score, the better the operating status of the device class to be evaluated.

[0057] The above technical solution provides a practical device status score determination scheme, which can be used to quantify the operating status of rail transit signal devices, improve the evaluation accuracy of device operating status, and is beneficial to improving the operating stability of rail transit systems.

[0058] Embodiment 2

[0059] Figure 2 is a flowchart of the rail transit signal device status evaluation method provided according to Embodiment 2. This embodiment is further optimized on the basis of the above embodiment.

[0060] As Figure 2 shown, the method includes:

[0061] S210. Obtain the device failure time corresponding to the device class to be evaluated.

[0062] S220. Determine the number of failures of the device class to be evaluated based on the device failure time.

[0063] Optionally, by counting the number of device failure times of the device class to be evaluated, the number of device failure times is determined as the number of failures. The number of failures can be used to determine the failure rate type of the device class to be evaluated.

[0064] S230. Determine the probability density function of the device failure time, and determine the failure rate function of the device class to be evaluated based on the probability density function.

[0065] Among them, the probability density function of the device failure time is the core tool for quantifying the failure time distribution law in reliability engineering. Different distribution types correspond to different failure mechanisms and stage characteristics. The probability density function can be used to determine the failure rate type of the device class to be evaluated. Optionally, determine the probability distribution function based on the probability density function. Determine the failure rate function of the device class to be evaluated based on the probability density function and the probability distribution function.

[0066] Among them, the increasing or decreasing trend of the failure rate function is used to determine the failure rate type of the device class to be evaluated.

[0067] S240. Determine the failure rate type of the device class to be evaluated based on the number of failures, the increasing or decreasing trend of the failure rate function, and the probability density function.

[0068] Among them, the number of failures provides a statistical law, the failure rate function reveals the internal change mechanism, and the probability density function describes the time distribution pattern. The combination of the three can uniquely correspond to different failure stages of the bathtub curve model, and then the failure rate type of the equipment class to be evaluated can be determined.

[0069] S250. Determine the state evaluation index for the equipment class to be evaluated based on the failure rate type, and determine the evaluation index weight corresponding to the state evaluation index.

[0070] S260. Perform a state evaluation on the equipment class to be evaluated by using the evaluation index weight and the state evaluation index.

[0071] The technical solution of this application determines the number of failures of the equipment class to be evaluated according to the equipment failure time, determines the probability density function of the equipment failure time, and determines the failure rate function of the equipment class to be evaluated based on the probability density function. Based on the statistical law provided by the number of failures, the internal change mechanism revealed by the failure rate function, and the time distribution pattern described by the probability density function, the combination of the three can uniquely correspond to different failure stages of the bathtub curve model, and jointly determine the failure rate type of the equipment class to be evaluated. A practical failure rate type determination scheme is provided, which ensures the accuracy of the failure rate type determination. Using the failure rate type to evaluate the operating state of the equipment class to be evaluated is beneficial to improving the accuracy of the equipment operating state evaluation.

[0072] In an optional embodiment, determining the failure rate type of the equipment class to be evaluated based on the number of failures, the increasing and decreasing trend of the failure rate function, and the probability density function includes: if the number of failures is less than or equal to the reliability loss coefficient of the equipment class to be evaluated, then determine the failure rate type of the equipment class to be evaluated as the balanced type; if the number of failures is greater than the reliability loss coefficient of the equipment class to be evaluated and the probability density function is in the form of an exponential function, then determine the failure rate type of the equipment class to be evaluated as the balanced type; if the number of failures is greater than the reliability loss coefficient of the equipment class to be evaluated and the probability density function is in other function forms except the exponential function form, then determine the failure rate type of the equipment class to be evaluated based on the increasing and decreasing trend of the failure rate function.

[0073] Among them, the reliability loss coefficient is used to quantify the degree of equipment performance degradation. Optionally, use to determine the reliability loss coefficient of the equipment class to be evaluated. Among them, is the operating time of the equipment class to be evaluated, is the availability of the equipment class to be evaluated, is the average repair time of the equipment class to be evaluated. Among them, the availability can be obtained by querying the equipment operation manual.

[0074] If the number of failures is less than or equal to the reliability loss coefficient of the device class to be evaluated, it indicates that the device class to be evaluated has not shown abnormal degradation during the statistical period of device failure time and meets the reliability design expectations. Then, the failure rate type of the device class to be evaluated is determined as balanced.

[0075] If the number of failures is greater than the reliability loss coefficient of the device class to be evaluated, it indicates that the device class to be evaluated has shown abnormal degradation during the statistical period of device failure time, and it is necessary to further analyze the failure rate type in combination with the probability density function of the device failure time.

[0076] The probability density function of the exponential distribution strictly corresponds to a constant failure rate, which is the only continuous distribution with the "Memoryless Property". This property indicates that the device failure probability is only related to the current moment and has nothing to do with the historical operation duration, which conforms to the physical essence of random failures. In the bathtub curve model, the exponential distribution corresponds to the accidental failure period. If the probability density function of the device failure time is in the form of an exponential function, then the failure rate type of the device class to be evaluated is determined as balanced.

[0077] If the probability density function is in other functional forms than the exponential function form, it is necessary to further analyze the increasing and decreasing trends of the failure rate function. Optionally, the Mann - Kendall trend test is used to determine whether the failure rate function shows an increasing or decreasing trend.

[0078] The above - mentioned technical solution provides a practical failure rate type determination solution, which comprehensively considers the number of failures, the increasing and decreasing trends of the failure rate function, and the probability density function, providing technical support and data support for determining the failure rate type of the device class to be evaluated.

[0079] In an optional embodiment, determining the failure rate type of the device class to be evaluated based on the increasing and decreasing trends of the failure rate function includes: if the failure rate function shows an increasing trend, then the failure rate type of the device class to be evaluated is determined as increasing; if the failure rate function shows a decreasing trend, then the failure rate type of the device class to be evaluated is determined as decreasing.

[0080] The increasing trend of the failure rate function indicates that the failure rate gradually rises, marking the end of the product life, corresponding to the wear - out failure period of the bathtub curve model. The failure rate type of the device class to be evaluated is determined as increasing. If the failure rate function shows a decreasing trend, it indicates that the failure rate gradually decreases, corresponding to the early failure period of the bathtub curve model. The failure rate type of the device class to be evaluated is determined as decreasing.

[0081] The above - mentioned technical solution determines the failure rate type according to the increasing and decreasing trends of the failure rate curve, providing a practical failure rate type determination solution, and providing technical support and data support for determining the failure rate type.

[0082] In an optional embodiment, determining the probability density function of the device failure time and determining the failure rate function of the device class to be evaluated based on the probability density function includes: fitting the probability distribution of the device failure time using at least two preset probability distributions, and determining whether the target probability distribution that the device failure time conforms to is included in the preset probability distributions; if included, using maximum likelihood estimation to determine the probability density function of the device failure time based on the target probability distribution; otherwise, using kernel density estimation to determine the probability density function of the device failure time; determining the probability distribution function based on the probability density function; and determining the failure rate function of the device class to be evaluated based on the probability density function and the probability distribution function.

[0083] The specific type of the preset probability distribution is not limited here and is specifically determined according to actual business requirements. The preset probability distribution is generally a common probability distribution. Exemplarily, the preset probability distribution may include at least two of exponential distribution, Weibull distribution, normal distribution, lognormal distribution, and gamma distribution.

[0084] Optionally, use the Kolmogorov - Smirnov test to perform a goodness - of - fit test on the preset probability distribution for the device failure time, and then determine the target probability distribution that the device failure time conforms to in the preset probability distributions. Among them, the target probability distribution is the probability distribution that the device failure time conforms to in the preset probability distributions.

[0085] When the target probability distribution is determined, use maximum likelihood estimation to perform parameter estimation on the device failure time to obtain the probability density function of the device failure time. Determine the probability distribution function of the device failure time based on the probability density function. Optionally, based on Determine the failure rate function, where represents the probability density function, represents the probability distribution function, is the likelihood function is the maximum likelihood estimate value of the parameter to be estimated in represents the failure rate function.

[0086] If there is no probability distribution that the device failure time conforms to in the preset probability distributions, use kernel density estimation to determine the probability density function of the device failure time. Specifically, 1) Select a kernel function. Common kernel functions include Gaussian kernel function, Epanechnikov kernel function, etc. 2) Determine the bandwidth. The choice of bandwidth affects the estimation result. Common selection methods include Silverman's rule of thumb, etc. 3) Calculate the kernel density estimate value. For a given device failure time , the probability density function of the kernel density estimate is .

[0087] Probability density function obtained based on kernel density estimation , and calculate the distribution function through integration . Adopt to determine the failure rate function

[0088] For the above technical solution, the method of distribution fitting and non-parametric estimation is adopted to determine the probability density function of the equipment failure time, then determine the probability distribution function based on the probability density function, and further determine the failure rate function. It provides a practical and reliable failure rate function determination scheme, providing data support and technical support for subsequent use of the failure rate function to determine the failure rate type

[0089] In a specific embodiment, the operating states of four types of rail transit signal equipment, namely type A, type B, type C, and type D, are evaluated. Type A, type B, type C, and type D are the equipment types to be evaluated

[0090] Collect the original failure data of type A, type B, type C, and type D from the operation logs and fault records of rail transit signal equipment. After removing duplicate values, handling missing values, correcting error values, and standardizing the data for the original failure data, obtain the equipment failure times of type A, type B, type C, and type D

[0091] Based on the formula respectively determine the reliability loss coefficients of type A, type B, type C, and type D, where is the operating time is the availability is the mean time to repair. For the above four types of equipment, namely type A, type B, type C, and type D, they have been running continuously from 2016 to 2023. Therefore , obtain the availability by querying the equipment user manual , is approximately 14

[0092] Based on the equipment failure times of the four types of equipment, namely type A, type B, type C, and type D, the number of failures of type A, type B, type C, and type D are 12, 59, 28, and 37 respectively. Since the number of failures of type A equipment is less than 14, it can be determined that the failure rate type of type A equipment is balanced. The number of failures of type B, type C, and type D are all greater than 14, and it is necessary to further combine the probability density distribution of the equipment failure time and the failure rate function to determine the failure rate types of these three types of equipment

[0093] First, select a suitable target probability distribution from the preset probability distributions to fit the equipment failure times of types B, C, and D, and use the Kolmogorov - Smirnov test for goodness - of - fit testing. The preset probability distributions include at least two of the exponential distribution, Weibull distribution, normal distribution, log - normal distribution, and gamma distribution. Through distribution fitting, it is determined that type B equipment conforms to the exponential distribution, and the failure rate type of type B equipment is the balanced type.

[0094] Since there is no matching probability distribution in the preset probability distributions for the equipment failure times of types C and D, use Kernel Density Estimation (KDE) to estimate the probability density function from the equipment failure times, and then obtain the failure rate function. Then, use the Mann - Kendall trend test to determine the increasing or decreasing trend of the failure rate function. After determination, the failure rate function of type C is in a decreasing trend, and the failure rate function of type D is in an increasing trend. The failure rate types of types C and D are determined to be the decreasing type and the increasing type, respectively.

[0095] For types A and B with balanced failure rates, the number of failures is determined as the state evaluation index. For type C with a decreasing failure rate, at least two of the total wavelet energy , the first failure time , the failure rate value at 20,000 hours , the mean time to failure , the median time to failure , and the characteristic failure time are determined as the state evaluation indexes of the equipment class to be evaluated. For type D with an increasing failure rate, at least two of the total wavelet energy , the failure rate value at the last moment , the mean time to failure , the median time to failure , and the characteristic failure time are determined as the state evaluation indexes of the equipment class to be evaluated.

[0096] Exemplarily, the state evaluation indexes and the corresponding evaluation index values of the four types of equipment, types A, B, C, and D, are shown in Table 1.

[0097] Table 1

[0098]

[0099] For types C and D, the evaluation index weights corresponding to the state evaluation indexes are shown in Table 2.

[0100] Table 2

[0101]

[0102] Among them, the evaluation index weight is obtained by weighting the expert weight and the entropy weight.

[0103] For the balanced failure rate, the number of failures is the only state evaluation index, and the fewer the number of failures, the higher the score. Exemplarily, the scoring rule can be: 1 failure corresponds to 100 points, 2 failures correspond to 99 points,... 20 failures correspond to 81 points. When the number of failures exceeds 20 and it is determined to be an exponential distribution, it corresponds to 80 points.

[0104] For the decreasing failure rate, among them, the time to first failure , the mean time to failure , the median time to failure , the characteristic time to failure , and the total wavelet energy are positive indicators, and the failure rate value at 20,000 hours is a negative indicator.

[0105] For the failure rate determined to be decreasing, the mean time to failure , the median time to failure , and the characteristic time to failure are positive indicators. The failure rate value at the last moment and the total wavelet energy are negative indicators.

[0106] The state evaluation index is related to the failure rate type. Optionally, an initial scoring interval is determined for the failure rate type, and then, based on the evaluation index value corresponding to the state evaluation index, a scoring interval query is performed to determine the target scoring interval corresponding to the evaluation index value. Exemplarily, the initial scoring interval for the balanced failure rate is set to [80, 100], the initial scoring interval for the decreasing failure rate is [70, 80), and the initial scoring interval for the increasing failure rate is [60, 70). When the target scoring interval is determined, the state index score corresponding to the target scoring interval can be further obtained.

[0107] Specifically, the device state scores of devices A, B, C, and D calculated by weighted average according to the state index scores and evaluation index weights corresponding to each state evaluation index are shown in Table 3 below. The content in the cell corresponding to each state evaluation index column in Table 3 is the state index score corresponding to the evaluation index, and the device state score is obtained by weighting the state index score using the evaluation index weight.

[0108] Table 3

[0109] Example 3

[0110] Figure 3FIG. 0 is a schematic structural diagram of a rail transit signal equipment status evaluation device provided in Embodiment 3 of the present application. This embodiment is applicable to the situation of evaluating the status of rail transit signal equipment in a rail transit system. The device can be implemented by software and / or hardware and can be integrated into electronic devices such as intelligent terminals.

[0111] As Figure 3 shown in FIG. Figure 3 , the rail transit signal equipment status evaluation device 300 may include:

[0112] A failure rate type determination module 310, configured to obtain the equipment failure time corresponding to the equipment class to be evaluated, and determine the failure rate type of the equipment class to be evaluated based on the equipment failure time;

[0113] An index weight determination module 320, configured to determine a status evaluation index for the equipment class to be evaluated based on the failure rate type, and determine the evaluation index weight corresponding to the status evaluation index;

[0114] A status evaluation module 330, configured to perform a status evaluation on the equipment class to be evaluated by using the evaluation index weight and the status evaluation index.

[0115] The technical solution of the present application takes the equipment failure time of the equipment class to be evaluated as the starting point, analyzes the equipment failure characteristics of the equipment class to be evaluated, and obtains the failure rate type of the equipment class to be evaluated. By using status evaluation indexes adapted to the failure rate type and combining with the evaluation index weights, it effectively realizes the scientific quantitative evaluation of the operation status of rail transit signal equipment. Compared with using a general model such as the bathtub curve model to analyze the failure rate of rail transit signal equipment based on statistical assumptions, the embodiment of the present application is based on the actual failure time of the equipment class to be evaluated, fully considers the complexity and differences of the industrial production environments where different rail transit signal equipment is located, realizes the customized analysis of the equipment class to be evaluated, realizes the quantitative evaluation of the equipment operation status, improves the evaluation accuracy of the equipment operation status, and is beneficial to improving the operation stability of the rail transit system.

[0116] Optionally, the failure rate type determination module 310 includes: a failure times determination sub-module, configured to determine the failure times of the equipment class to be evaluated based on the equipment failure time; a failure rate function determination sub-module, configured to determine the probability density function of the equipment failure time, and determine the failure rate function of the equipment class to be evaluated based on the probability density function; a failure rate type determination sub-module, configured to determine the failure rate type of the equipment class to be evaluated based on the failure times, the increasing and decreasing trend of the failure rate function, and the probability density function.

[0117] Optionally, the failure rate type determination sub-module includes: a first type determination unit configured to determine the failure rate type of the device under evaluation as balanced if the number of failures is less than or equal to the reliability loss coefficient of the device under evaluation; a second type determination unit configured to determine the failure rate type of the device under evaluation as balanced if the number of failures is greater than the reliability loss coefficient of the device under evaluation and the probability density function is in the form of an exponential function; and a third type determination unit configured to determine the failure rate type of the device under evaluation based on the increasing or decreasing trend of the failure rate function if the number of failures is greater than the reliability loss coefficient of the device under evaluation and the probability density function is in a form other than the exponential function form.

[0118] Optionally, the third type determination unit includes: an increasing type determination sub-unit configured to determine the failure rate type of the device under evaluation as increasing if the failure rate function is in an increasing trend; and a decreasing type determination sub-unit configured to determine the failure rate type of the device under evaluation as decreasing if the failure rate function is in a decreasing trend.

[0119] Optionally, the failure rate function determination sub-module includes: a probability distribution fitting unit configured to perform probability distribution fitting on the device failure time using at least two preset probability distributions and determine whether the target probability distribution that the device failure time conforms to is included in the preset probability distributions; a first function determination unit configured to, if it is included, determine the probability density function of the device failure time based on the target probability distribution using maximum likelihood estimation; a second function determination unit configured to, otherwise, determine the probability density function of the device failure time using kernel density estimation; a distribution function determination unit configured to determine the probability distribution function based on the probability density function; and a failure rate function determination unit configured to determine the failure rate function of the device under evaluation based on the probability density function and the probability distribution function.

[0120] Optionally, the index weight determination module 320 includes: a first index determination sub-module configured to determine the number of failures as the state evaluation index of the device under evaluation if the failure rate type is balanced; a second index determination sub-module configured to determine at least two of the total wavelet energy, the failure rate value at the last moment, the average failure time, the median failure time, and the characteristic failure time as the state evaluation index of the device under evaluation if the failure rate type is increasing; and a third index determination sub-module configured to determine at least two of the total wavelet energy, the first failure time, the failure rate value at 20,000 hours, the average failure time, the median failure time, and the characteristic failure time as the state evaluation index of the device under evaluation if the failure rate type is decreasing.

[0121] Optionally, the index weight determination module 320 includes: an expert weight acquisition sub-module for acquiring the expert weights of the status evaluation indexes; an entropy weight determination sub-module for determining the entropy weights of the status evaluation indexes based on the evaluation index values corresponding to the status evaluation indexes by using the entropy weight method; and an index weight determination sub-module for determining the evaluation index weights corresponding to the status evaluation indexes based on the expert weights and the entropy weights.

[0122] Optionally, the status evaluation module 330 includes: a score range query sub-module for querying the score range by using the evaluation index values corresponding to the status evaluation indexes to obtain the target score range corresponding to the evaluation index values; an index score determination sub-module for determining the status index score corresponding to the status evaluation indexes based on the target score range; a status score determination sub-module for weighting the status index score by using the evaluation index weights to obtain the device status score of the device class to be evaluated; and a status evaluation sub-module for performing status evaluation on the device class to be evaluated by using the device status score.

[0123] The rail transit signal equipment status evaluation device provided by the invention embodiment can execute the rail transit signal equipment status evaluation method provided by any embodiment of the present application, and has the corresponding performance modules and beneficial effects for executing the rail transit signal equipment status evaluation method.

[0124] Embodiment 4

[0125] According to the embodiments of the present application, the present application also provides an electronic device, a readable storage medium, and a computer program product.

[0126] Figure 4 FIG. shows a schematic structural diagram of an electronic device 410 that can be used to implement the embodiments. The electronic device 410 includes at least one processor 411, and a memory communicatively connected to at least one processor 411, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc. The memory stores a computer program executable by at least one processor. The processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 into the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other through a bus 414. The input / output (I / O) interface 415 is also connected to the bus 414.

[0127] Multiple components in the electronic device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, an optical disc, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0128] The processor 411 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 411 executes the various methods and processes described above, such as the method for evaluating the status of rail transit signal equipment.

[0129] In some embodiments, the method for evaluating the status of rail transit signal equipment can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 418. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the method for evaluating the status of rail transit signal equipment described above can be executed. Alternatively, in other embodiments, the processor 411 can be configured to execute the method for evaluating the status of rail transit signal equipment in any other suitable manner (e.g., by means of firmware).

[0130] The various embodiments of the systems and technologies described above in this article can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs, which can be executed and / or interpreted on a programmable system including at least one programmable processor. The programmable processor can be a special or general programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0131] The computer program for implementing the method of this application can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable rail transit signal device state evaluation devices, such that when the computer programs are executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, executed partially on the machine as an independent software package and partially on a remote machine, or executed entirely on a remote machine or server.

[0132] In the context of this application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include electrical connections based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0133] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0134] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a rail transit signal equipment status evaluation server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with the implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0135] A computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0136] The embodiment of the present application also discloses a computer program product, which includes a computer program that implements the rail transit signal equipment status evaluation method provided in any embodiment of the present application when executed by a processor. This program product and the rail transit signal equipment status evaluation methods disclosed in the embodiments of the present application belong to the same inventive concept, and thus will not be elaborated herein.

[0137] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present application can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present application can be achieved, and no limitation is imposed herein.

[0138] The above specific implementation manners do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present application shall be included within the protection scope of the present application.

Claims

1. A method for evaluating the state of rail transit signal equipment, characterized in that, The method includes: Obtaining the device failure time corresponding to the device class to be evaluated, and determining the failure rate type of the device class to be evaluated based on the device failure time; Determining state evaluation indicators for the device class to be evaluated based on the failure rate type, and determining the evaluation index weights corresponding to the state evaluation indicators; Performing a state evaluation on the device class to be evaluated by using the evaluation index weights and the state evaluation indicators.

2. The method according to claim 1, characterized in that, The determining the failure rate type of the device class to be evaluated based on the device failure time includes: Determining the number of failures of the device class to be evaluated based on the device failure time; Determining the probability density function of the device failure time, and determining the failure rate function of the device class to be evaluated based on the probability density function; Determining the failure rate type of the device class to be evaluated based on the number of failures, the increasing or decreasing trend of the failure rate function, and the probability density function.

3. The method according to claim 2, wherein The determining the failure rate type of the device class to be evaluated based on the number of failures, the increasing or decreasing trend of the failure rate function, and the probability density function includes: If the number of failures is less than or equal to the reliability loss coefficient of the device class to be evaluated, determining the failure rate type of the device class to be evaluated as the balanced type; If the number of failures is greater than the reliability loss coefficient of the device class to be evaluated, and the probability density function is in the form of an exponential function, determining the failure rate type of the device class to be evaluated as the balanced type; If the number of failures is greater than the reliability loss coefficient of the device class to be evaluated, and the probability density function is in a function form other than the exponential function form, determining the failure rate type of the device class to be evaluated based on the increasing or decreasing trend of the failure rate function.

4. The method according to claim 3, wherein The determining the failure rate type of the device class to be evaluated based on the increasing or decreasing trend of the failure rate function includes: If the failure rate function is in an increasing trend, determining the failure rate type of the device class to be evaluated as the increasing type; If the failure rate function is in a decreasing trend, determining the failure rate type of the device class to be evaluated as the decreasing type.

5. The method according to claim 2, wherein The determining the probability density function of the device failure time, and determining the failure rate function of the device class to be evaluated based on the probability density function includes: Performing probability distribution fitting on the device failure time by using at least two preset probability distributions, and determining whether the target probability distribution that the device failure time conforms to is included in the preset probability distributions; If it is included, determining the probability density function of the device failure time by using maximum likelihood estimation based on the target probability distribution; Otherwise, determining the probability density function of the device failure time by using kernel density estimation; Determining the probability distribution function based on the probability density function; Determining the failure rate function of the device class to be evaluated based on the probability density function and the probability distribution function.

6. The method according to claim 1, characterized in that The determining state evaluation indicators for the device class to be evaluated based on the failure rate type includes: If the failure rate type is the balanced type, determining the number of failures as the state evaluation indicator of the device class to be evaluated; If the failure rate type is increasing, at least two of the total wavelet energy, the failure rate value at the last moment, the mean time to failure, the median time to failure, and the characteristic time to failure are determined as the state evaluation indexes of the device class to be evaluated; If the failure rate type is decreasing, at least two of the total wavelet energy, the time to first failure, the failure rate value at 20,000 hours, the mean time to failure, the median time to failure, and the characteristic time to failure are determined as the state evaluation indexes of the device class to be evaluated.

7. The method according to claim 1, wherein The determination of the evaluation index weights corresponding to the state evaluation indexes includes: Obtaining the expert weights of the state evaluation indexes; Using the entropy weight method to determine the entropy weight of the state evaluation indexes based on the evaluation index values corresponding to the state evaluation indexes; Based on the expert weights and the entropy weights, determining the evaluation index weights corresponding to the state evaluation indexes.

8. The method according to claim 1, characterized in that, The use of the evaluation index weights and the state evaluation indexes to perform state evaluation on the device class to be evaluated includes: Performing a query of the score range using the evaluation index values corresponding to the state evaluation indexes to obtain the target score range corresponding to the evaluation index values; Determining the state index score corresponding to the state evaluation index based on the target score range; Weighting the state index scores using the evaluation index weights to obtain the device state score of the device class to be evaluated; Using the device state score to perform state evaluation on the device class to be evaluated.

9. A device for evaluating the state of rail transit signal equipment, characterized in that, The device includes: A failure rate type determination module, configured to obtain the device failure time corresponding to the device class to be evaluated, and determine the failure rate type of the device class to be evaluated based on the device failure time; An index weight determination module, configured to determine state evaluation indexes for the device class to be evaluated based on the failure rate type, and determine the evaluation index weights corresponding to the state evaluation indexes; A state evaluation module, configured to perform state evaluation on the device class to be evaluated using the evaluation index weights and the state evaluation indexes.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the rail transit signal device state evaluation method according to any one of claims 1-8.

11. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the rail transit signal device state evaluation method according to any one of claims 1-8.

Images