Hydropower station risk grade determination method and system based on big data

Abstract

The invention provides a hydropower station risk level determination method and system based on big data, and the method comprises the steps: collecting a vibration time sequence signal of each piece of hydroelectric generating set equipment in a hydropower station, and determining the time-shifting multi-scale attention entropy of the hydropower station according to the vibration time sequence signal of each piece of hydroelectric generating set equipment in the hydropower station; determining fault component points and fault types of fault hydroelectric generating set equipment in the hydropower station; determining the failure probability and failure consequence data of each fault component point of each fault hydroelectric generating set device; determining the failure probability and failure consequence data of each fault hydroelectric generating set device; and determining the risk level of each fault hydroelectric generating set device in the hydropower station according to the failure probability and the failure consequence data of each fault hydroelectric generating set device. According to the technical scheme provided by the invention, comprehensive risk assessment can be carried out on the hydroelectric generating set equipment, and help is provided for risk decision of management personnel of a hydropower station and maintenance work of maintenance personnel.

Description

Technical Field

[0001] The present application relates to the technical field of risk assessment of hydropower stations, and in particular to a method and system for determining the risk level of a hydropower station based on big data. Background Art

[0002] During operation, hydropower generation systems at hydropower stations are subject to hazardous events that could result in casualties, environmental damage, and loss of property and equipment. These events can be defined as operational risks for hydropower stations. Based on this definition, risk assessment evaluates and ranks the probability of occurrence and potential consequences of identified hazardous events to understand the potential risk to equipment and systems. This is crucial for ensuring the health and safety of hydropower station personnel and the stability of hydropower generation. While risk assessment methods have been widely applied to safety management issues in various fields, risk assessment for hydropower stations is still in its developmental stages.

[0003] As core components of a hydropower station's hydroelectric generation system, the safety and stability of these units are crucial to the efficient operation of the station. However, existing technologies focus on risk analysis of common accidents or localized issues, neglecting fault risk analysis of hydropower equipment. This makes it difficult to conduct comprehensive and accurate risk assessments of hydropower units. Therefore, a comprehensive and accurate solution for determining the risk level of a hydropower station is urgently needed. Summary of the Invention

[0004] The present application provides a method and system for determining the risk level of a hydropower station based on big data, so as to at least solve the technical problem that the existing technology focuses on the risk analysis of certain common accidents or local problems, ignores the failure risk analysis of hydropower unit equipment, and cannot conduct a comprehensive and accurate risk assessment of the hydropower units in the hydropower station.

[0005] The first embodiment of the present application proposes a method for determining the risk level of a hydropower station based on big data, the method comprising:

[0006] collecting vibration time series signals of each hydropower unit equipment in the hydropower station, and determining the time-shifted multi-scale attention entropy of the hydropower station according to the vibration time series signals of each hydropower unit equipment in the hydropower station;

[0007] Determine the fault component points and fault categories of each faulty hydropower unit equipment in the hydropower station according to the time-shifted multi-scale attention entropy of the hydropower station;

[0008] Determine the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment;

[0009] Determining the failure probability and failure consequence data of each faulty hydropower unit equipment according to the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment;

[0010] The risk level of each faulty hydroelectric generating unit equipment in the hydropower station is determined according to the failure probability and failure consequence data of each faulty hydroelectric generating unit equipment.

[0011] Preferably, determining the time-shifted multi-scale attention entropy of the hydropower station based on the vibration time series signals of each hydropower unit equipment in the hydropower station includes:

[0012] Divide the vibration time series signal of each hydropower unit into k vibration signal subsequences;

[0013] Determine the attention entropy mean value of each hydropower unit device according to the k vibration signal subsequences of each hydropower unit device;

[0014] The time-shifted multi-scale attention entropy of the hydropower station is formed based on the mean of the attention entropy of each hydropower unit equipment.

[0015] Furthermore, determining the fault component points and fault categories of each faulty hydropower unit equipment in the hydropower station according to the time-shifted multi-scale attention entropy of the hydropower station includes:

[0016] The time-shifted multi-scale attention entropy of the hydropower station is used as a feature vector, and a principal component analysis method is used to perform data dimensionality reduction processing on the feature vector to obtain a feature vector after data dimensionality reduction;

[0017] Inputting the feature vector after the data dimension reduction into a pre-trained fault identification model to obtain the fault component points and fault categories of each faulty hydropower unit equipment;

[0018] The fault identification model is obtained by training a random forest classifier based on the time-shifted multi-scale attention entropy after dimensionality reduction of data in the historical period of the hydropower station and the fault component points and fault types corresponding to the time-shifted multi-scale attention entropy.

[0019] Furthermore, the determination of the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment includes:

[0020] Determining an expert evaluation language for each faulty component point of each faulty hydropower unit device based on a relationship between a preset expert evaluation language, the faulty component point, and the fault category, and determining a fuzzy number for each faulty component point of each faulty hydropower unit device based on the expert evaluation language for each faulty component point of each faulty hydropower unit device;

[0021] The trapezoidal fuzzy membership function is used to determine the membership value corresponding to the fuzzy number of each faulty component point of each faulty hydropower unit equipment;

[0022] Determine the failure probability of each fault component point of each faulty hydropower unit equipment according to the membership value corresponding to the fuzzy number of each fault component point of each faulty hydropower unit equipment and the fuzzy number;

[0023] Obtaining relative loss values ​​corresponding to each faulty component point of each faulty hydropower unit equipment, and determining loss rates of each faulty component point of each faulty hydropower unit equipment based on the relative loss values ​​corresponding to each faulty component point of each faulty hydropower unit equipment;

[0024] Obtaining the failure probability of each faulty component point of each faulty hydropower unit equipment and the risk probability borne by workers every day, and determining the fatal accident rate of each faulty component point of each faulty hydropower unit equipment based on the failure probability of each faulty component point of each faulty hydropower unit equipment and the risk probability borne by workers every day;

[0025] The failure consequence data include loss rate and fatal accident rate.

[0026] Furthermore, the determining of the failure probability and failure consequence data of each faulty hydropower unit equipment according to the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment includes:

[0027] Determine the sum of failure probabilities of each faulty component point of the e-th faulty hydropower unit equipment, and use the sum of the failure probabilities as the failure probability of the e-th faulty hydropower unit equipment;

[0028] Determine the sum of the loss rates of the faulty component points of the e-th faulty hydropower unit equipment, and use the sum of the loss rates as the loss rate of the e-th faulty hydropower unit equipment;

[0029] Determine the sum of fatal accident rates of each faulty component point of the e-th faulty hydropower unit equipment, and use the sum of the fatal accident rates as the fatal accident rate of the e-th faulty hydropower unit equipment;

[0030] Among them, e∈[1~E], E is the total number of faulty hydropower units.

[0031] Furthermore, determining the risk level of each faulty hydropower generating unit equipment in the hydropower station based on the failure probability and failure consequence data of each faulty hydropower generating unit equipment includes:

[0032] Determine the risk pre-control assessment value of each faulty hydropower unit equipment according to the failure probability and failure consequence data of each faulty hydropower unit equipment;

[0033] Obtain a preset assessment level range, determine the assessment level range to which the risk pre-control assessment value of each faulty hydropower unit equipment belongs, and use the assessment level corresponding to the assessment level range to which the risk pre-control assessment value belongs as the risk level of the faulty hydropower unit equipment.

[0034] Furthermore, the method further comprises:

[0035] Obtain the preset failure probability level table, economic consequence level table and social consequence level table;

[0036] The failure probability level, economic consequence level, and social consequence level of each faulty hydropower unit equipment are determined based on the failure probability and failure consequence data of each faulty hydropower unit equipment.

[0037] Furthermore, the method further comprises:

[0038] The risk level, failure probability level, economic consequence level, and social consequence level of each faulty hydropower unit equipment are displayed.

[0039] The second embodiment of the present application proposes a hydropower station risk level determination system based on big data, including:

[0040] an acquisition module, configured to acquire vibration time series signals of each hydropower unit in the hydropower station, and determine the time-shifted multi-scale attention entropy of the hydropower station based on the vibration time series signals of each hydropower unit in the hydropower station;

[0041] A first determination module is configured to determine the fault component points and fault categories of each faulty hydropower unit equipment in the hydropower station according to the time-shifted multi-scale attention entropy of the hydropower station;

[0042] The second determination module is used to determine the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment;

[0043] A third determination module is used to determine the failure probability and failure consequence data of each faulty hydropower unit equipment according to the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment;

[0044] The fourth determination module is used to determine the risk level of each faulty hydropower unit equipment in the hydropower station according to the failure probability and failure consequence data of each faulty hydropower unit equipment.

[0045] A third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect of the present application.

[0046] The technical solutions provided by the embodiments of this application bring at least the following beneficial effects:

[0047] This application proposes a method and system for determining the risk level of a hydropower station based on big data. The method includes: collecting vibration time series signals of each hydropower unit equipment in the hydropower station, determining the time-shifted multi-scale attention entropy of the hydropower station based on the vibration time series signals of each hydropower unit equipment in the hydropower station; determining the fault component points and fault categories of each faulty hydropower unit equipment in the hydropower station based on the time-shifted multi-scale attention entropy of the hydropower station; determining the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment; determining the failure probability and failure consequence data of each faulty hydropower unit equipment based on the failure probability and failure consequence data of each faulty hydropower unit equipment; and determining the risk level of each faulty hydropower unit equipment in the hydropower station based on the failure probability and failure consequence data of each faulty hydropower unit equipment. The technical solution proposed in this application can conduct a comprehensive risk assessment of hydropower unit equipment, providing assistance to risk decision-making of hydropower station managers and maintenance work of maintenance personnel.

[0048] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0050] Figure 1 This is a flow chart of a method for determining the risk level of a hydropower station based on big data according to one embodiment of the present application;

[0051] Figure 2 A schematic diagram of a fuzzy membership function provided according to one embodiment of the present application;

[0052] Figure 3 A schematic diagram of a maximum and minimum setting method provided according to an embodiment of the present application;

[0053] Figure 4 This is a first structural diagram of a hydropower station risk level determination system based on big data provided according to one embodiment of the present application;

[0054] Figure 5 This is a second structural diagram of a hydropower station risk level determination system based on big data provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0056] The present application proposes a method and system for determining the risk level of a hydropower station based on big data. The method includes: collecting vibration time series signals of each hydropower unit equipment in the hydropower station, determining the time-shifted multi-scale attention entropy of the hydropower station based on the vibration time series signals of each hydropower unit equipment in the hydropower station; determining the fault component points and fault categories of each faulty hydropower unit equipment in the hydropower station based on the time-shifted multi-scale attention entropy of the hydropower station; determining the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment; determining the failure probability and failure consequence data of each faulty hydropower unit equipment based on the failure probability and failure consequence data of each faulty hydropower unit equipment; and determining the risk level of each faulty hydropower unit equipment in the hydropower station based on the failure probability and failure consequence data of each faulty hydropower unit equipment. The technical solution proposed in the present application can conduct a comprehensive risk assessment of hydropower unit equipment, providing assistance to hydropower station managers in risk decision-making and maintenance personnel in maintenance work.

[0057] The following describes a method and system for determining the risk level of a hydropower station based on big data in an embodiment of the present application with reference to the accompanying drawings.

[0058] Example 1

[0059] Figure 1 This is a flow chart of a method for determining the risk level of a hydropower station based on big data according to an embodiment of the present application. Figure 1 As shown, the method includes:

[0060] Step 1: Collect vibration time series signals of each hydropower unit equipment in the hydropower station, and determine the time-shifted multi-scale attention entropy of the hydropower station according to the vibration time series signals of each hydropower unit equipment in the hydropower station.

[0061] In the embodiment of the present disclosure, determining the time-shifted multi-scale attention entropy of the hydropower station based on the vibration time series signals of each hydropower unit equipment in the hydropower station includes:

[0062] Divide the vibration time series signal of each hydropower unit into k vibration signal subsequences;

[0063] Determine the attention entropy mean value of each hydropower unit device according to the k vibration signal subsequences of each hydropower unit device;

[0064] The time-shifted multi-scale attention entropy of the hydropower station is formed based on the mean of the attention entropy of each hydropower unit equipment.

[0065] For example, (1) the vibration time series signal of length N of each hydropower unit equipment in the hydropower station is collected, and the vibration time series signal is divided into k subsequences, and the formula is:

[0066]

[0067] Where, is the βth subsequence of the ath hydropower unit equipment in the hydropower station, x β,a is the sample point of the vibration time series signal of the a-th hydropower unit in the hydropower station, and k is the number of segmented subsequences.

[0068] (2) Calculate the mean attention entropy of each hydropower unit equipment

[0069]

[0070] Where TSMA(k,a) is the mean attention entropy of the a-th hydropower unit equipment in the hydropower station, for 's attention entropy;

[0071] (3) The set consisting of the mean values ​​of the attention entropy of each hydropower unit equipment in the hydropower station is used as the time-shifted multi-scale attention entropy TSMATE of the hydropower station.

[0072] Step 2: Determine the fault component points and fault categories of each faulty hydropower unit equipment in the hydropower station according to the time-shifted multi-scale attention entropy of the hydropower station.

[0073] In the embodiment of the present disclosure, step 2 specifically includes:

[0074] 2.1 The time-shifted multi-scale attention entropy of the hydropower station is used as a feature vector, and the principal component analysis method is used to perform data dimensionality reduction on the feature vector to obtain a feature vector after data dimensionality reduction;

[0075] It should be noted that the time-shifted multi-scale attention entropy TSMATE of the hydropower station is used as the feature vector, and the principal component analysis PCA dimensionality reduction is used to overcome the TSMATE feature redundancy problem. By converting highly correlated feature variables into independent low-dimensional variables, the complexity of the data is reduced and the training efficiency of the model is improved.

[0076] 2.2 Input the feature vector after the data dimension reduction into the pre-trained fault identification model to obtain the fault component points and fault categories of each faulty hydropower unit equipment;

[0077] The fault identification model is obtained by training a random forest classifier based on the time-shifted multi-scale attention entropy after dimensionality reduction of data in the historical period of the hydropower station and the fault component points and fault types corresponding to the time-shifted multi-scale attention entropy.

[0078] It should be noted that the feature vector after dimension reduction is input into a classifier based on random forest RF for fault identification and fault classification, so as to obtain the fault component point and fault category of the hydropower unit.

[0079] The dimensionality reduction features are input into the classifier, and the classifier is used to effectively distinguish different fault signals. RF is a multi-classifier containing multiple decision trees, and its output category is determined by the mode of the categories output by the decision tree.

[0080] Bootstrap sampling is a sampling method with replacement, which allows you to obtain samples with the same size as the sampled samples. Assuming the sample size is infinite, approximately 36.8% of the out-of-bag samples will not be drawn. This data is often used to test the generalization ability of the model. The Bagging algorithm is an ensemble learning algorithm that uses the bootstrap sampling method to perform multiple samplings to form multiple sample sets. Each sample set is trained as a weak learner. Each weak learner independently processes the data and votes on it. The one with the most votes is the algorithm's result.

[0081] RF uses an improved Bagging algorithm and a CART decision tree as a weak learner. Therefore, each decision tree is independent of each other and can only retain some of the data features of the original sample. The construction of RF consists of the following three parts:

[0082] (1) In each round of RF training, a sampling method with replacement is used to extract P samples from the sample data, and P decision trees are constructed based on them;

[0083] (2) Randomly select training data for the decision tree. Assuming that the sample has M feature attributes, randomly select l feature attributes from the M feature attributes as the training attributes of the decision tree;

[0084] (3) The generated P decision trees form a RF, and each decision tree jointly determines the classification result.

[0085] It should be noted that the method further includes:

[0086] The names of the faulty components and the fault categories of the faulty hydropower generating unit equipment are recorded to form a statistical table.

[0087] Obtain the fault component point of the faulty device and construct a component fault table of the hydropower unit; wherein the component fault table includes the faulty device and its corresponding fault component point, and one faulty device corresponds to one or more fault component points.

[0088] Step 3: Determine the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment.

[0089] In the embodiment of the present disclosure, step 3 specifically includes:

[0090] Determining an expert evaluation language for each faulty component point of each faulty hydropower unit device based on a relationship between a preset expert evaluation language, the faulty component point, and the fault category, and determining a fuzzy number for each faulty component point of each faulty hydropower unit device based on the expert evaluation language for each faulty component point of each faulty hydropower unit device;

[0091] The trapezoidal fuzzy membership function is used to determine the membership value corresponding to the fuzzy number of each faulty component point of each faulty hydropower unit equipment;

[0092] Determine the failure probability of each fault component point of each faulty hydropower unit equipment according to the membership value corresponding to the fuzzy number of each fault component point of each faulty hydropower unit equipment and the fuzzy number;

[0093] Obtaining relative loss values ​​corresponding to each faulty component point of each faulty hydropower unit equipment, and determining loss rates of each faulty component point of each faulty hydropower unit equipment based on the relative loss values ​​corresponding to each faulty component point of each faulty hydropower unit equipment;

[0094] Obtaining the failure probability of each faulty component point of each faulty hydropower unit equipment and the risk probability borne by workers every day, and determining the fatal accident rate of each faulty component point of each faulty hydropower unit equipment based on the failure probability of each faulty component point of each faulty hydropower unit equipment and the risk probability borne by workers every day;

[0095] The failure consequence data include loss rate and fatal accident rate.

[0096] It should be noted that the expert evaluation language includes very high: “very high (VH)”, “high (H)”, “higher (RH)”, “medium (M)”, “lower (RL)”, “low (L)”, “very low (VL)”;

[0097] Fuzzy number conversion: The conversion of natural language into mathematical language requires the use of fuzzy membership functions. Trapezoidal fuzzy membership functions are used to define the mapping relationship between expert language and fuzzy functions. Figure 2 As shown, the fuzzy membership functions corresponding to 7 languages ​​are given, and the corresponding expressions are given as follows:

[0098]

[0099] Where u(x) is the membership degree of the fuzzy number x, such as Figure 2 As shown, on the interval [a, b], the function value rises linearly from 0 to 1; on the interval [b, c], the function value is always 1; on the interval [c, d], the function value drops linearly from 1 to 0;

[0100] The analytic hierarchy process (AHP) is used for weighted processing, and the weighted results are:

[0101]

[0102] Among them, u z (x) is the membership function after the fuzzy number x is weighted; ω j is the weight of expert j, u ij is the membership degree corresponding to the i-th fuzzy language given by the j-th expert;

[0103] The maximum and minimum setting method is used to obtain the fuzzy probability, and the maximum and minimum fuzzy sets are defined as:

[0104]

[0105] Where u max (x) is the maximum fuzzy set corresponding to the fuzzy number x, u min (x) is the minimum fuzzy set corresponding to the fuzzy number x. Figure 3 The maximum and minimum setting methods shown are used to obtain the left and right valid scores:

[0106] P R (Z)=sup[u z (x)∩u max (x)]

[0107] P L (Z)=sup[u z (x)∩u min (x)]

[0108] Where, P R (Z) is the right effective fraction, P L (Z) is the left valid fraction;

[0109] Calculate the fuzzy probability as: P M =(P R +1-P L ) / 2, and the failure probability is converted using the Onisawa formula:

[0110]

[0111] Where P is the failure probability of the faulty component point.

[0112] It should be noted that the method for calculating the consequences of failure is:

[0113] Define relative loss L i As an economic consequence, the ratio of total losses to total capital is:

[0114]

[0115] In the formula, L i is the relative loss, T i is the total capital, T is the total loss, and the relative loss L i When it is greater than 1, the relative loss is 1;

[0116] At the same time, in order to clarify the size of the loss rate, the logarithmic loss is defined: C = 5 + logT i ;

[0117] Taking IRPA as the social consequence, assuming that the staff's inspection time is T hours per day, the probability of the staff bearing the risk every day is P r =T / 24, and the probability of equipment failure is P s , the weights of death, serious injury and minor injury caused by failure are 0.63, 0.33 and 0.04 respectively, then the IRPA value of the worker who may die within one year, that is, the fatal accident rate is: S i =0.63×P r ×P s .

[0118] Step 4: Determine the failure probability and failure consequence data of each faulty hydropower unit equipment according to the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment.

[0119] In the embodiment of the present disclosure, step 4 specifically includes:

[0120] Determine the sum of failure probabilities of each faulty component point of the e-th faulty hydropower unit equipment, and use the sum of the failure probabilities as the failure probability of the e-th faulty hydropower unit equipment;

[0121] Determine the sum of the loss rates of the faulty component points of the e-th faulty hydropower unit equipment, and use the sum of the loss rates as the loss rate of the e-th faulty hydropower unit equipment;

[0122] Determine the sum of fatal accident rates of each faulty component point of the e-th faulty hydropower unit equipment, and use the sum of the fatal accident rates as the fatal accident rate of the e-th faulty hydropower unit equipment;

[0123] Among them, e∈[1~E], E is the total number of faulty hydropower units.

[0124] It should be noted that if a device includes four faulty component points A, B, C, and D, then the failure probability of the faulty device is the sum of the failure probabilities of the four faulty component points A, B, C, and D, and the failure consequence of the faulty device is the sum of the failure consequences of the four faulty component points A, B, C, and D.

[0125] Step 5: Determine the risk level of each faulty hydropower generating unit equipment in the hydropower station based on the failure probability and failure consequence data of each faulty hydropower generating unit equipment.

[0126] In the embodiment of the present disclosure, step 5 specifically includes:

[0127] Determine the risk pre-control assessment value of each faulty hydropower unit equipment according to the failure probability and failure consequence data of each faulty hydropower unit equipment;

[0128] Obtain a preset assessment level range, determine the assessment level range to which the risk pre-control assessment value of each faulty hydropower unit equipment belongs, and use the assessment level corresponding to the assessment level range to which the risk pre-control assessment value belongs as the risk level of the faulty hydropower unit equipment.

[0129] It should be noted that the risk assessment results are calculated based on the failure probability and failure consequences of the faulty equipment, and the risk level of each faulty equipment is assessed according to a preset risk level table. Risk assessment result = failure probability × failure consequences. Based on the calculated risk assessment results, a five-level risk level is established: Level 1: No monitoring required; Level 2: Regular monitoring and maintenance required; Level 3: Risk mitigation measures required; Level 4: Real-time maintenance required to prevent accidents; Level 5: Accident has already occurred and emergency repairs should be carried out as soon as possible.

[0130] It should be noted that the method further includes:

[0131] Obtain the preset failure probability level table, economic consequence level table and social consequence level table;

[0132] The failure probability level, economic consequence level, and social consequence level of each faulty hydropower unit equipment are determined based on the failure probability and failure consequence data of each faulty hydropower unit equipment.

[0133] The failure probability levels are shown in Table 1:

[0134] Table 1

[0135] Qualitative description Failure probability Assessment level Very low risk ＜0.0003 1 Low risk 0.0003～0.003 2 Medium risk 0.003～0.03 3 High risk 0.03～0.3 4 Extremely high risk 0.3～1 5

[0136] The economic consequence levels are shown in Table 2:

[0137] Table 2

[0138] describe Loss Rate Logarithmic loss grade Very low loss <![CDATA[<10 -4 ]]> ＜1 1 Low loss <![CDATA[10 -4 ~10 -3 ]]> 1～2 2 Moderate losses <![CDATA[10 -3 ~10 -2 ]]> 2～3 3 High losses <![CDATA[10 -2 ~10 -1 ]]> 3～4 4 Extremely high losses <![CDATA[10 -1 ~1]]> 4～5 5

[0139] The social consequence levels are shown in Table 3:

[0140] Table 3

[0141] describe Fatal accident rate grade Very low consequence <![CDATA[<10 -6 ]]> 1 Low consequence <![CDATA[10 -6 ~10 -5 ]]> 2 Moderate consequences <![CDATA[10 -5 ~10 -4 ]]> 3 High Consequences <![CDATA[10 -4 ~10 -3 ]]> 4 Very high consequences <![CDATA[10 -3 ]]> 5

[0142] It should be noted that the method further includes:

[0143] The risk level, failure probability level, economic consequence level, and social consequence level of each faulty hydropower unit equipment are displayed.

[0144] Among them, a graphical risk model can be constructed, including device nodes, failure probability nodes and failure consequence nodes; the device nodes are used to display the name and risk level of the faulty device, the failure probability nodes are used to connect to corresponding device nodes and display the failure probability value and failure probability rating of the corresponding faulty device, and the failure consequence nodes are used to connect to corresponding device nodes and display the failure consequence value and failure consequence rating of the corresponding faulty device.

[0145] In summary, the method for determining the risk level of a hydropower station based on big data proposed in this embodiment can conduct a comprehensive risk assessment of hydropower unit equipment, thereby assisting hydropower station managers in risk decision-making and maintenance personnel in their maintenance work.

[0146] Example 2

[0147] Figure 4 This is a structural diagram of a hydropower station risk level determination system based on big data according to an embodiment of the present application. Figure 4 As shown, the system includes:

[0148] The acquisition module 100 is used to collect the vibration time series signals of each hydropower unit equipment in the hydropower station, and determine the time-shifted multi-scale attention entropy of the hydropower station based on the vibration time series signals of each hydropower unit equipment in the hydropower station;

[0149] A first determination module 200 is configured to determine the faulty component points and fault types of each faulty hydropower unit equipment in the hydropower station according to the time-shifted multi-scale attention entropy of the hydropower station;

[0150] The second determination module 300 is used to determine the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment;

[0151] The third determining module 400 is used to determine the failure probability and failure consequence data of each faulty hydropower unit device according to the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit device;

[0152] The fourth determination module 500 is configured to determine the risk level of each faulty hydropower generating unit equipment in the hydropower station according to the failure probability and failure consequence data of each faulty hydropower generating unit equipment.

[0153] In the embodiment of the present disclosure, the acquisition module 100 is further configured to:

[0154] Divide the vibration time series signal of each hydropower unit into k vibration signal subsequences;

[0155] Determine the attention entropy mean value of each hydropower unit device according to the k vibration signal subsequences of each hydropower unit device;

[0156] The time-shifted multi-scale attention entropy of the hydropower station is formed based on the mean of the attention entropy of each hydropower unit equipment.

[0157] In the embodiment of the present disclosure, the first determining module 200 is further configured to:

[0158] The time-shifted multi-scale attention entropy of the hydropower station is used as a feature vector, and a principal component analysis method is used to perform data dimensionality reduction processing on the feature vector to obtain a feature vector after data dimensionality reduction;

[0159] Inputting the feature vector after the data dimension reduction into a pre-trained fault identification model to obtain the fault component points and fault categories of each faulty hydropower unit equipment;

[0160] The fault identification model is obtained by training a random forest classifier based on the time-shifted multi-scale attention entropy after dimensionality reduction of data in the historical period of the hydropower station and the fault component points and fault types corresponding to the time-shifted multi-scale attention entropy.

[0161] In the embodiment of the present disclosure, the second determining module 300 is further configured to:

[0162] Determining an expert evaluation language for each faulty component point of each faulty hydropower unit device based on a relationship between a preset expert evaluation language, the faulty component point, and the fault category, and determining a fuzzy number for each faulty component point of each faulty hydropower unit device based on the expert evaluation language for each faulty component point of each faulty hydropower unit device;

[0163] The trapezoidal fuzzy membership function is used to determine the membership value corresponding to the fuzzy number of each faulty component point of each faulty hydropower unit equipment;

[0164] Determine the failure probability of each fault component point of each faulty hydropower unit equipment according to the membership value corresponding to the fuzzy number of each fault component point of each faulty hydropower unit equipment and the fuzzy number;

[0165] Obtaining relative loss values ​​corresponding to each faulty component point of each faulty hydropower unit equipment, and determining loss rates of each faulty component point of each faulty hydropower unit equipment based on the relative loss values ​​corresponding to each faulty component point of each faulty hydropower unit equipment;

[0166] Obtaining the failure probability of each faulty component point of each faulty hydropower unit equipment and the risk probability borne by workers every day, and determining the fatal accident rate of each faulty component point of each faulty hydropower unit equipment based on the failure probability of each faulty component point of each faulty hydropower unit equipment and the risk probability borne by workers every day;

[0167] The failure consequence data include loss rate and fatal accident rate.

[0168] In the embodiment of the present disclosure, the third determining module 400 is further configured to:

[0169] Determine the sum of failure probabilities of each faulty component point of the e-th faulty hydropower unit equipment, and use the sum of the failure probabilities as the failure probability of the e-th faulty hydropower unit equipment;

[0170] Determine the sum of the loss rates of the faulty component points of the e-th faulty hydropower unit equipment, and use the sum of the loss rates as the loss rate of the e-th faulty hydropower unit equipment;

[0171] Determine the sum of fatal accident rates of each faulty component point of the e-th faulty hydropower unit equipment, and use the sum of the fatal accident rates as the fatal accident rate of the e-th faulty hydropower unit equipment;

[0172] Among them, e∈[1~E], E is the total number of faulty hydropower units.

[0173] In the embodiment of the present disclosure, the fourth determining module 500 is further configured to:

[0174] Determine the risk pre-control assessment value of each faulty hydropower unit equipment according to the failure probability and failure consequence data of each faulty hydropower unit equipment;

[0175] Obtain a preset assessment level range, determine the assessment level range to which the risk pre-control assessment value of each faulty hydropower unit equipment belongs, and use the assessment level corresponding to the assessment level range to which the risk pre-control assessment value belongs as the risk level of the faulty hydropower unit equipment.

[0176] In the embodiment of the present disclosure, Figure 5 As shown, the system further includes: a determination module 600;

[0177] The determination module 600 is configured to:

[0178] Obtain the preset failure probability level table, economic consequence level table and social consequence level table;

[0179] The failure probability level, economic consequence level, and social consequence level of each faulty hydropower unit equipment are determined based on the failure probability and failure consequence data of each faulty hydropower unit equipment.

[0180] In the embodiment of the present disclosure, Figure 5 As shown, the system further includes: a display module 700;

[0181] The display module 700 is used to:

[0182] The risk level, failure probability level, economic consequence level, and social consequence level of each faulty hydropower unit equipment are displayed.

[0183] In summary, the big data-based hydropower station risk level determination system proposed in this embodiment can perform comprehensive risk assessments on hydropower unit equipment, providing assistance to hydropower station managers in risk decision-making and maintenance personnel in their maintenance work.

[0184] Example 3

[0185] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in the first embodiment is implemented.

[0186] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0187] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0188] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for determining the risk level of a hydropower station based on big data, characterized in that: The method comprises: collecting vibration time series signals of each hydropower unit equipment in the hydropower station, and determining the time-shifted multi-scale attention entropy of the hydropower station according to the vibration time series signals of each hydropower unit equipment in the hydropower station; Determine the fault component points and fault categories of each faulty hydropower unit equipment in the hydropower station according to the time-shifted multi-scale attention entropy of the hydropower station; Determine the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment; Determining the failure probability and failure consequence data of each faulty hydropower unit equipment according to the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment; The risk level of each faulty hydroelectric generating unit equipment in the hydropower station is determined according to the failure probability and failure consequence data of each faulty hydroelectric generating unit equipment.

2. The method according to claim 1, wherein The step of determining the time-shifted multi-scale attention entropy of the hydropower station according to the vibration time series signals of each hydropower unit equipment in the hydropower station includes: Divide the vibration time series signal of each hydropower unit into k vibration signal subsequences; Determine the attention entropy mean value of each hydropower unit device according to the k vibration signal subsequences of each hydropower unit device; The time-shifted multi-scale attention entropy of the hydropower station is formed based on the mean of the attention entropy of each hydropower unit equipment.

3. The method according to claim 2, wherein The determining of each fault component point and fault category of each faulty hydropower generating unit equipment in the hydropower station according to the time-shifted multi-scale attention entropy of the hydropower station includes: The time-shifted multi-scale attention entropy of the hydropower station is used as a feature vector, and a principal component analysis method is used to perform data dimensionality reduction processing on the feature vector to obtain a feature vector after data dimensionality reduction; Inputting the feature vector after the data dimension reduction into a pre-trained fault identification model to obtain the fault component points and fault categories of each faulty hydropower unit equipment; The fault identification model is obtained by training a random forest classifier based on the time-shifted multi-scale attention entropy after dimensionality reduction of data in the historical period of the hydropower station and the fault component points and fault types corresponding to the time-shifted multi-scale attention entropy.

4. The method according to claim 3, wherein The determination of the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment includes: Determining an expert evaluation language for each faulty component point of each faulty hydropower unit device based on a relationship between a preset expert evaluation language, the faulty component point, and the fault category, and determining a fuzzy number for each faulty component point of each faulty hydropower unit device based on the expert evaluation language for each faulty component point of each faulty hydropower unit device; The trapezoidal fuzzy membership function is used to determine the membership value corresponding to the fuzzy number of each faulty component point of each faulty hydropower unit equipment; Determine the failure probability of each fault component point of each faulty hydropower unit equipment according to the membership value corresponding to the fuzzy number of each fault component point of each faulty hydropower unit equipment and the fuzzy number; Obtaining relative loss values ​​corresponding to each faulty component point of each faulty hydropower unit equipment, and determining loss rates of each faulty component point of each faulty hydropower unit equipment based on the relative loss values ​​corresponding to each faulty component point of each faulty hydropower unit equipment; Obtaining the failure probability of each faulty component point of each faulty hydropower unit equipment and the risk probability borne by workers every day, and determining the fatal accident rate of each faulty component point of each faulty hydropower unit equipment based on the failure probability of each faulty component point of each faulty hydropower unit equipment and the risk probability borne by workers every day; The failure consequence data include loss rate and fatal accident rate.

5. The method according to claim 4, wherein The determining of the failure probability and failure consequence data of each faulty hydropower unit equipment according to the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment comprises: Determine the sum of failure probabilities of each faulty component point of the e-th faulty hydropower unit equipment, and use the sum of the failure probabilities as the failure probability of the e-th faulty hydropower unit equipment; Determine the sum of the loss rates of the faulty component points of the e-th faulty hydropower unit equipment, and use the sum of the loss rates as the loss rate of the e-th faulty hydropower unit equipment; Determine the sum of fatal accident rates of each faulty component point of the e-th faulty hydropower unit equipment, and use the sum of the fatal accident rates as the fatal accident rate of the e-th faulty hydropower unit equipment; Among them, e∈[1~E], E is the total number of faulty hydropower units.

6. The method according to claim 5, wherein Determining the risk level of each faulty hydropower generating unit equipment in the hydropower station based on the failure probability and failure consequence data of each faulty hydropower generating unit equipment includes: Determine the risk pre-control assessment value of each faulty hydropower unit equipment according to the failure probability and failure consequence data of each faulty hydropower unit equipment; Obtain a preset assessment level range, determine the assessment level range to which the risk pre-control assessment value of each faulty hydropower unit equipment belongs, and use the assessment level corresponding to the assessment level range to which the risk pre-control assessment value belongs as the risk level of the faulty hydropower unit equipment.

7. The method according to claim 6, wherein The method further comprises: Obtain the preset failure probability level table, economic consequence level table and social consequence level table; The failure probability level, economic consequence level, and social consequence level of each faulty hydropower unit equipment are determined based on the failure probability and failure consequence data of each faulty hydropower unit equipment.

8. The method according to claim 7, wherein The method further comprises: The risk level, failure probability level, economic consequence level, and social consequence level of each faulty hydropower unit equipment are displayed.

9. A hydropower station risk level determination system based on big data, characterized in that: The system comprises: an acquisition module, configured to acquire vibration time series signals of each hydropower unit in the hydropower station, and determine the time-shifted multi-scale attention entropy of the hydropower station based on the vibration time series signals of each hydropower unit in the hydropower station; A first determination module is configured to determine the fault component points and fault categories of each faulty hydropower unit equipment in the hydropower station according to the time-shifted multi-scale attention entropy of the hydropower station; The second determination module is used to determine the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment; A third determination module is used to determine the failure probability and failure consequence data of each faulty hydropower unit equipment according to the failure probability and failure consequence data of each faulty component point of each faulty hydropower unit equipment; The fourth determination module is used to determine the risk level of each faulty hydropower unit equipment in the hydropower station according to the failure probability and failure consequence data of each faulty hydropower unit equipment.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images