Hydroelectric generating set state evaluation method based on multi-index fusion

Abstract

The invention discloses a hydroelectric generating set state evaluation method based on multi-index fusion, which comprises the following steps of: acquiring multi-index parameters of a hydroelectric generating set through a collector to obtain a set of index parameters, and dividing the acquired set of index parameters into four item layers of vibration, swing, pulse and temperature; then, through an analytic hierarchy process and a decision and laboratory evaluation method, respectively calculating subjective and objective weights of each index, establishing an evaluation fuzzy matrix of the indexes, comprehensively calculating an index fuzzy comprehensive matrix and corresponding weights thereof to obtain a fuzzy evaluation matrix of the project targets, and then carrying out weight calculation on each project target of the project layer to obtain a fuzzy evaluation matrix of the project targets; and finally, carrying out weighted calculation on the fuzzy evaluation matrix of the project target to obtain a comprehensive evaluation state of the hydroelectric generating set of the target layer. The technical effects of performing safety early warning on the hydroelectric generating set and reducing economic loss and casualties are achieved.

Description

Technical Field

[0001] The invention relates to the technical field of hydropower unit state assessment methods, and in particular to a hydropower unit state assessment method based on multi-index fusion. Background Art

[0002] Hydropower units are important equipment for converting water energy into electrical energy, and their operating conditions directly affect the safe and stable operation of local or even the entire power system. Equipment failures of hydropower units, such as flooded units, generator bore sweeps, generator wire rod burnout, turbine blade breakage, transformer explosion, etc., may lead to forced and unplanned shutdowns of units, causing power system shocks, and seriously affecting the safety and stability of power stations and power grids. Therefore, in order to ensure the safe and stable operation of hydropower units and power grids, improve equipment utilization, and avoid major economic losses and casualties, it is necessary to reasonably monitor and evaluate the operating status of hydropower units. At the same time, the operating status of hydropower units is affected by many factors. We need to consider multiple index factors, fuse data of different indicators, and use a combination of subjective and objective weights to accurately evaluate the operating status of hydropower units. Summary of the invention

[0003] The purpose of the present invention is to overcome the above-mentioned shortcomings and provide a hydropower unit status assessment method based on multi-indicator fusion, so as to solve the technical problems that the existing hydropower unit assessment methods have the disadvantages of not being accurate enough in indicator weights and not considering the mutual influence between indicators in the same target layer, resulting in the deviation of the assessed status from the actual situation.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: a method for evaluating the status of a hydropower unit based on multi-index fusion, which comprises the following steps:

[0005] Step 1: According to the real-time operating status of the hydropower unit and the real-time data collected by the data sensor, the corresponding dynamic evaluation index is constructed, and the initial sample set including the operating data set and the dynamic safety index is constructed;

[0006] Step 2: For the initial sample set, the degradation degree is introduced to represent the quantitative index, and the initial sample set is processed to achieve the purpose of data compression and generate an efficient sample set;

[0007] Step 3: Use the fuzzy comprehensive evaluation method to construct an evaluation index system for the comprehensive status evaluation of the hydropower unit. The multiple indicators contained therein are layered according to their attributes to form a multi-level system. The corresponding membership and evaluation levels are constructed for all the targets in the system to obtain the fuzzy evaluation matrix of each indicator.

[0008] Step 4: Based on the generated efficient sample set, use the hierarchical analysis method to calculate the subjective weight of each indicator, use the decision-making and laboratory evaluation method to calculate the objective weight of each indicator, and comprehensively consider the subjective weight and objective weight of each indicator to obtain the actual weighted set of indicators;

[0009] Step 5: Perform comprehensive weighted calculation on the fuzzy evaluation matrix of each indicator to obtain the fuzzy evaluation matrix of the project goal in the project layer;

[0010] Step 6: Same as step 4, weight calculation is performed on each target in the project layer, and then weighted calculation is performed on the fuzzy evaluation matrix of the project target, and finally the comprehensive status evaluation matrix of the hydropower unit in the target layer is obtained, and then the status of the hydropower unit is obtained according to the maximum membership principle.

[0011] Furthermore, in step 2, for the initial sample set, the degradation degree is introduced to represent the quantitative index, and the initial sample set is processed to achieve the purpose of data compression, as shown in formula (1):

[0012]

[0013] Where: C is the value of a certain operating variable after standard normalization; C i is the original value of the running variable; C min is the ideal value of the indicator; C max are the limiting values ​​of the indicators; in this way, the values ​​of all variables vary between 0 and 1.

[0014] Furthermore, in step 3, an evaluation index system is constructed for the comprehensive status evaluation of the hydropower unit, and the multiple indicators contained therein are layered according to their attributes to form a multi-level system, including:

[0015] Target layer: comprehensive status assessment of hydropower units;

[0016] Project level: vibration, swing, pulse, temperature;

[0017] Index layer: Vibration includes upper cover vibration (X, Y, Z) and shaft system vibration (A, B, C), swing index includes water-conductor pendulum X and Y, pressure pulsation index includes volute pressure pulsation and exhaust pipe pressure pulsation, temperature index includes water-conductor bearing temperature and water-conductor oil temperature.

[0018] Furthermore, in step 3, the fuzzy evaluation matrix of each indicator is obtained as shown in formulas (2) and (3):

[0019] x jk =d jk / d (2)

[0020] Where: d represents the total number of experts in the indicator set, djk Representative indicator set C i The number of experts who make the k-th level comments on the j-th evaluation index, x jk is the membership degree of the jth indicator to the kth level comment;

[0021]

[0022] Where: X nr Represents the membership degree of the nth evaluation indicator in the indicator set Ci to the rth level comment, R i is the fuzzy evaluation matrix of indicators in the same layer.

[0023] Furthermore, in step 4, the specific steps of using the hierarchical analysis method to calculate the subjective weights of each indicator are as follows:

[0024] 4.1. Build a comprehensive model of hydropower units and construct a multi-level indicator system with hydropower units as the target;

[0025] 4.2. According to the comparison of the importance of different indicators, a judgment matrix is ​​constructed, as shown in formula (4):

[0026]

[0027] Where: v i represents the selected i-th index, v j represents the jth index selected, C ij Represents the importance relationship between the i-th indicator and the j-th indicator;

[0028] 4.3. According to the judgment matrix C obtained above, as shown in formula (5):

[0029] C=(C ij ) n×n (5)

[0030] Where: C ij >0, C ii =1;

[0031] 4.4. Calculate the maximum eigenvalue and the corresponding eigenvector of the judgment matrix, and define the consistency index CI according to the eigenvalue, as shown in formula (6):

[0032]

[0033] Where: max is the maximum eigenvalue of the judgment matrix, and n is the number of corresponding eigenvectors;

[0034] If CI = 0, then there is complete consistency; if CI is close to 0, then there is good consistency; if CI is larger, then the consistency is worse;

[0035] 4.5. According to the randomness index RI corresponding to the matrix order and the consistency index CI of the matrix, the consistency ratio is defined as shown in formula (7):

[0036]

[0037] Where: CR is the consistency ratio;

[0038] 4.6. When the matrix meets the consistency requirements, the eigenvector corresponding to the maximum eigenvalue of the judgment matrix C is normalized to obtain the corresponding weight set (w1, w2, ..., w n ), where Ci is as shown in formula (8):

[0039]

[0040] Where: P i is the eigenvector corresponding to the judgment matrix.

[0041] Furthermore, in step 4, the specific steps of using the decision-making and laboratory evaluation method to calculate the objective weights of each indicator are as follows:

[0042] 4-1. According to the triangular fuzzy function, the influence relationship between indicators at the same level is converted into a triangular fuzzy judgment set according to the corresponding table;

[0043] 4-2. Use the DEMATEL method to reflect the mutual influence of each indicator in the indicator system, and use the CFCS method to defuzzify and calculate the objective weight;

[0044] 4-3. Establish the initial direct impact matrix, collect expert opinions and convert them into triangular fuzzy numbers (l ij ,m ij ,u ij ), and obtain the initial direct influence matrix given by the kth expert As shown in formula (9):

[0045]

[0046] 4-4. Calculate the normalized triangular fuzzy number, as shown in formula (10):

[0047]

[0048] Where: Indicates the difference between the right and left values ​​of a triangular fuzzy number is the standard triangular fuzzy value;

[0049] 4-5. According to the left and right standard values Calculate the normalized total As shown in formula (11):

[0050]

[0051] 4-6. Calculate the impact of the i-th factor on the j-th factor to obtain the direct impact matrix D, as shown in formula (12):

[0052]

[0053] Where: d ij represents the mean of K experts’ judgments, and D is the direct influence matrix formed by the mean of experts’ judgments;

[0054] 4-7. Standardize the processing matrix D and calculate the comprehensive impact matrix T, as shown in formula (13):

[0055]

[0056] Where: Represents the maximum value of the sum of elements in each row of matrix D;

[0057] 4-8. Superimpose the elements in the matrix T according to rows and columns, and calculate the influence degree e, the influence degree f, the centrality m and the cause degree h, as shown in formula (14):

[0058]

[0059] Where: t ij is the impact factor in the comprehensive impact matrix T;

[0060] 4-9. Calculate objective weight As shown in formula (15):

[0061]

[0062] Furthermore, in step 4, the subjective weight and objective weight of each indicator are comprehensively considered to obtain the actual weighted set of indicators as shown in formula (16):

[0063]

[0064] Where: is the subjective weight of the indicator, is the objective weight of the indicator.

[0065] Furthermore, in step 5, the fuzzy evaluation matrix of the project objectives in the project layer is obtained as shown in formula (17):

[0066]

[0067] Where: It represents the different membership values ​​of a certain project target B in the project layer belonging to the 4 status evaluation levels, R is the indicator fuzzy evaluation weight matrix, and W is the weight matrix corresponding to the indicator.

[0068] Beneficial effects of the present invention:

[0069] 1. The present invention solves the technical problems that the existing hydropower unit evaluation method has the problem that the indicator weights are not accurate enough and the mutual influence between indicators in the same target layer is not considered, resulting in a deviation between the evaluation status and the actual situation.

[0070] 2. The present invention realizes dynamic real-time monitoring of the evolution process of the hydropower unit from a normal state to a fault state, thereby achieving a technical effect of safety early warning of the hydropower unit and reducing economic losses and casualties.

[0071] 3. The present invention reduces the energy loss that may be caused by failure of the hydropower unit, improves the power generation efficiency of the hydropower unit, and helps optimize the performance of the hydropower unit.

[0072] 4. The present invention utilizes fuzzy mathematics to handle the uncertainties that may occur in the evaluation of hydropower units, thereby improving the flexibility and adaptability of the evaluation method. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 is a flow chart of the method proposed by the present invention;

[0074] Figure 2 It is a flowchart of a multi-index subjective and objective weight algorithm proposed by the present invention;

[0075] Figure 3 It is a schematic diagram of a comprehensive evaluation model of a hydropower unit involved in the present invention. DETAILED DESCRIPTION

[0076] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0077] Example 1: Figure 1 As shown, this embodiment provides a method for evaluating the status of a hydropower unit based on multi-index fusion, the method comprising:

[0078] Step 1: According to the real-time operating status of the hydropower unit and the real-time data collected by the data sensor, the corresponding dynamic evaluation index is constructed, and the initial sample set including the operating data set and the dynamic safety index is constructed;

[0079] Step 2: For the initial sample set, the degradation degree is introduced to represent the quantitative index, and the initial sample set is processed to achieve the purpose of data compression and generate an efficient sample set.

[0080] Step 3: Use a fuzzy comprehensive evaluation method to construct an evaluation index system for the comprehensive status assessment of the hydropower unit. The multiple indicators contained therein are layered according to their attributes to form a multi-level system, and the corresponding membership degrees and evaluation levels are constructed for all the targets in the system to obtain the fuzzy evaluation matrix of each indicator.

[0081] Step 4: Based on the generated efficient sample set, use the hierarchical analysis method to calculate the subjective weight of each indicator, use the decision-making and laboratory evaluation method to calculate the objective weight of each indicator, and comprehensively consider the subjective weight and objective weight of each indicator to obtain the actual weighted set of indicators (such as Figure 2 shown).

[0082] Step 5: Perform comprehensive weighted calculation on the fuzzy evaluation matrix of each indicator to obtain the fuzzy evaluation matrix of the project goal at the project level.

[0083] Step 6: Same as step 4, weight calculation is performed on each target in the project layer, and then weighted calculation is performed on the fuzzy evaluation matrix of the project target, and finally the comprehensive status evaluation matrix of the hydropower unit in the target layer is obtained, and then the status of the hydropower unit is obtained according to the maximum membership principle.

[0084] In step 2, the initial sample set is constructed based on the indicator data set obtained in real time. Since the unit categories of the evaluation indicators are different and their state quantities are not in the same order of magnitude, in order to facilitate subsequent processing and calculation, this paper uses relative degradation to normalize the evaluation indicator values, quantify the indicators, avoid the impact of the dimensions and order of magnitude of different state evaluation indicators, and thus obtain an efficient sample set.

[0085] For negative indicators, the smaller the better, as shown in formula (1):

[0086]

[0087] Where: C is the value of a certain operating variable after standard normalization; C i is the original value of the running variable; C min is the ideal value of the indicator; C max is the limit value of the indicator; in this way, the values ​​of all variables vary between 0 and 1;

[0088] In step 3, the status system of the hydropower unit is divided into three layers using fuzzy comprehensive evaluation: target layer, project layer, and indicator layer. The evaluation level is divided into five levels: excellent, good, medium, attention, and deterioration. At the same time, the membership degree of each indicator is calculated, as shown in formula (2):

[0089] x jk＝ d jk / d (2)

[0090] Where: d represents the total number of experts in the indicator set. jk Representative indicator set C i The number of experts who make the k-th level comments on the j-th evaluation index, x jk is the membership degree of the jth indicator to the kth level comment;

[0091] In step 3), C i Each indicator C in ij Make a judgment, give the degree to which each indicator belongs to each level of comment, and calculate its corresponding membership degree to obtain the fuzzy evaluation matrix Ri of the indicator. As shown in formula (3):

[0092]

[0093] Where: X nr Represents the membership degree of the nth evaluation indicator in the indicator set Ci to the rth level comment, R i is the fuzzy evaluation matrix of indicators in the same layer;

[0094] In step 4, the analytic hierarchy process is used to calculate the subjective weight of each indicator, and the steps include:

[0095] S1: Multiple indicators included in the object to be evaluated are orderly layered according to different attributes. First, the highest level is the comprehensive evaluation status of the hydropower unit. The first level is the project level, which includes swing, vibration, pulse and temperature. The second level is the indicator level, that is, the indicators of the first level are layered again. Vibration includes upper cover vibration (X, Y, Z) and shaft vibration (A, B, C). The swing index includes hydropower conduction swing X and Y. The pressure pulsation index includes volute pressure pulsation and exhaust pipe pressure pulsation. The temperature index includes water guide shoe temperature and water guide oil temperature.

[0096] S2: Construct a judgment matrix. Assume that this layer has n indicators, Vi…Vn, and let experts judge the importance of two indicators. ij It indicates the importance of Vi compared to Vj. Its judgment matrix is ​​shown in formula (4):

[0097]

[0098] Where: vi represents the selected i-th index, v j represents the jth index selected, C ij Represents the importance relationship between the i-th indicator and the j-th indicator;

[0099] S3: According to the judgment matrix C obtained above, as shown in formula (5):

[0100] C=(C ij ) n×n (5)

[0101] Where: C ij >0, C ii =1.

[0102] S4: Calculate the maximum eigenvalue and the corresponding eigenvector of the judgment matrix, and define the consistency index CI according to the eigenvalue, as shown in formula (6):

[0103]

[0104] Where: max is the maximum eigenvalue of the judgment matrix, and n is the number of corresponding eigenvectors;

[0105] If CI = 0, then there is complete consistency; if CI is close to 0, then there is good consistency; the larger the CI, the worse the consistency.

[0106] S5: Define the consistency ratio according to the randomness index RI corresponding to the matrix order and the consistency index CI of the matrix, as shown in formula (7):

[0107]

[0108] Where: CR is the consistency ratio;

[0109] S6: When the matrix meets the consistency requirements, the eigenvector corresponding to the maximum eigenvalue of the judgment matrix C is normalized to obtain the corresponding weight set (w1, w2, ..., w n ), where w i As shown in formula (8):

[0110]

[0111] Where: P i is the eigenvector corresponding to the judgment matrix;

[0112] In step 4, the objective weights of each indicator are calculated using the decision and laboratory evaluation method, which includes:

[0113] S1 converts the influence relationship between indicators in the same layer into a triangular fuzzy judgment set according to the corresponding table based on the triangular fuzzy function. As shown in Table 1:

[0114] Table 1 Corresponding relations of triangular fuzzy numbers

[0115] Meaning (degree of mutual influence) Corresponding triangular fuzzy judgment No (0，0.1，0.3) slight (0.1，0.3，0.5) Smaller (0.3，0.5，0.7) Larger (0.5，0.7，0.9) Very large (0.7，0.9，1)

[0116] S2 uses the DEMATEL method to reflect the mutual influence of each indicator in the indicator system, and uses the CFCS method to defuzzify and calculate the objective weight.

[0117] S3 establishes the initial direct impact matrix, collects expert opinions and converts them into triangular fuzzy numbers according to the impact relationship (l ij ,m ij ,u ij ), and obtain the initial direct influence matrix given by the kth expert As shown in formula (9):

[0118]

[0119] S4 calculates the normalized triangular fuzzy function, as shown in formula (10):

[0120]

[0121] Where: Indicates the difference between the right and left values ​​of the triangular fuzzy number. is the standard triangular fuzzy value;

[0122] S5 according to the standard value of left and right Calculate the normalized total As shown in formula (11):

[0123]

[0124] S6 calculates the impact of the i-th factor on the j-th factor to obtain the direct impact matrix D, as shown in formula (12):

[0125]

[0126] Where: d ij represents the mean judgment of K experts, and D is the direct influence matrix formed by the mean judgment of experts.

[0127] S7 normalizes the processing matrix D and calculates the comprehensive impact matrix T, as shown in formula (13):

[0128]

[0129] Where: Represents the maximum value among the sum of elements in each row of matrix D.

[0130] S8 superimposes the elements in the matrix T according to rows and columns, and obtains the influence degree e, the influence degree f, the centrality m and the cause degree h, as shown in formula (14):

[0131]

[0132] Where: t ij is the impact factor in the comprehensive impact matrix T;

[0133] S9 Calculate objective weight As shown in formula (15):

[0134]

[0135] In step 4, the comprehensive weight is calculated based on the subjective and objective weights, as shown in formula (16):

[0136]

[0137] Where: is the subjective weight of the indicator, is the objective weight of the indicator;

[0138] In step five, the weighted fuzzy evaluation matrix is ​​calculated, as shown in formula (17):

[0139]

[0140] Where: It indicates that a certain project target B in the project layer belongs to different membership values ​​of the 4 status evaluation levels, R is the indicator fuzzy evaluation weight matrix, and W is the weight matrix corresponding to the indicator;

[0141] In step six, by repeating the above operations with the project goals as indicators, the comprehensive membership evaluation matrix of the target layer hydropower units can be obtained, and the operating status of the hydropower units can be obtained according to the maximum membership principle.

[0142] Embodiment 2:

[0143] The invention example uses the relevant data collected during the normal operation of a hydropower unit. The monitoring quantities include vibration, swing, pressure pulsation and temperature indicators, which can fully reflect the overall status of the turbine system. The monitoring quantities include data at four time points, which can fully reflect the real-time operating status of the hydropower unit.

[0144] like Figure 3As shown in the figure, a hierarchical system is established with the hydropower unit as the target layer, and the following layers are project layer and index layer. The project layer is divided into vibration index, swing index, pressure pulse index and temperature index. The vibration index is divided into upper cover vibration and shaft vibration, the swing index is divided into hydropower conduction X and Y, the pressure pulsation index is divided into volute pressure pulsation and exhaust pipe pressure pulsation, and the temperature index is divided into water conduction shoe temperature and water conduction oil temperature.

[0145] The monitoring data of the four time periods are shown in Table 2 below:

[0146] Table 2 Monitoring data of indicators of hydropower units in different time periods

[0147]

[0148] There are six vibration indices for vibration index weight calculation, including the vibration of the top cover and the vibration of the shaft system. It is generally believed that each index is equally important to the state stability of the turbine system, so the subjective weight is 1 / 6. The objective weight of each index is calculated using formula (15), and finally the subjective and objective weights are substituted into formula (16). Then the comprehensive weight vector of the vibration index is:

[0149] ω A =(0.1858,0.1699,0.1760,0.1328,0.1675,0.1679) T

[0150] The pendulum index includes the X-direction and Y-direction indicators of the water-guided pendulum. Subjectively, these two indicators are considered equally important, so the subjective weight is 1 / 2. The comprehensive weight vector of the pendulum index is:

[0151] ω B =(0.4927,0.5073) T

[0152] The pressure pulsation index includes the volute pressure pulsation and the exhaust pipe pressure pulsation. Subjectively, the two are considered equally important, and the subjective weight is 1 / 2. Then the comprehensive weight vector of the pressure pulsation index is:

[0153] ω C =(0.3447,0.6553) T

[0154] The temperature index includes four indicators: water guide shoe temperature and water guide oil temperature. The subjective weight of each indicator is 1 / 4, so the comprehensive weight vector of the temperature index is:

[0155] ω D =(0.2333,0.2436,0.2925,0.2306) T .

[0156] Project level weight calculation, the project level includes four major indicators: vibration, swing, pressure pulsation, and temperature. The hierarchical analysis method is used to determine the weight of each indicator. Among them, vibration, swing, pressure pulsation and other indicators are fast-changing characteristic quantities and are more sensitive to the status of the unit. Therefore, in terms of importance, vibration index = swing index = pressure pulsation index > temperature index. The judgment matrix for determining the project level is:

[0157]

[0158] After the consistency test of formulas (6) and (7) is passed, the judgment matrix is ​​substituted into (8), and the weight of the project level is:

[0159] ω=(0.2857,0.2857,0.2857,0.1429) T

[0160] After the weight calculation is completed, the monitoring quantity is substituted into formula (1) to obtain the degree of degradation of each indicator. Then, based on expert experience and expert scoring, formula (2) is used to obtain the membership of each indicator in the grade classification and obtain the evaluation matrix Ri. Ri is substituted into formula (17) to obtain the evaluation matrix of each target in the project layer. The evaluation matrix of the project layer is then substituted into formula (17) for weighting to obtain the evaluation matrix of the hydropower unit in the target layer. Finally, the evaluation status of the hydropower unit is obtained according to the maximum membership principle. As shown in Table 3 below:

[0161] Table 3 Corresponding levels of degradation

[0162] Status Level Degradation AExcellent [0-0.15) BGood [0.15-0.375) C Medium [0.375-0.6) D Note [0.6-0.85) E deterioration [0.85-1)

[0163] Table 4 Evaluation level of hydropower units

[0164]

[0165] From the evaluation grades of hydropower units in Table 4, we finally get the grade evaluation of hydropower units in four time periods: A: good B: good C: medium D: attention.

[0166] From the changes in each time period, it can be known that the hydropower unit may have failed and needs timely maintenance.

[0167] The above embodiments are only preferred technical solutions of the present invention and should not be regarded as limiting the present invention. The protection scope of the present invention shall be the technical solutions recorded in the claims, including equivalent replacement solutions of the technical features in the technical solutions recorded in the claims. That is, equivalent replacement improvements within this scope are also within the protection scope of the present invention.

Claims

1. A method for evaluating the status of a hydropower unit based on multi-index fusion, characterized in that: It includes the following steps: Step 1: According to the real-time operating status of the hydropower unit and the real-time data collected by the data sensor, the corresponding dynamic evaluation index is constructed, and the initial sample set including the operating data set and the dynamic safety index is constructed; Step 2: For the initial sample set, the degradation degree is introduced to represent the quantitative index, and the initial sample set is processed to achieve the purpose of data compression and generate an efficient sample set; Step 3: Use the fuzzy comprehensive evaluation method to construct an evaluation index system for the comprehensive status evaluation of the hydropower unit. The multiple indicators contained therein are layered according to their attributes to form a multi-level system. The corresponding membership and evaluation levels are constructed for all the targets in the system to obtain the fuzzy evaluation matrix of each indicator. Step 4: Based on the generated efficient sample set, use the hierarchical analysis method to calculate the subjective weight of each indicator, use the decision-making and laboratory evaluation method to calculate the objective weight of each indicator, and comprehensively consider the subjective weight and objective weight of each indicator to obtain the actual weighted set of indicators; Step 5: Perform comprehensive weighted calculation on the fuzzy evaluation matrix of each indicator to obtain the fuzzy evaluation matrix of the project goal in the project layer; Step 6: Same as step 4, weight calculation is performed on each target in the project layer, and then weighted calculation is performed on the fuzzy evaluation matrix of the project target, and finally the comprehensive status evaluation matrix of the hydropower unit in the target layer is obtained, and then the status of the hydropower unit is obtained according to the maximum membership principle.

2. A method for evaluating the status of a hydropower unit based on multi-index fusion according to claim 1, characterized in that: In step 2, for the initial sample set, the degradation degree is introduced to represent the quantitative index, and the initial sample set is processed to achieve the purpose of data compression, as shown in formula (1): Where: C is the value of a certain operating variable after standard normalization; C i is the original value of the running variable; C min is the ideal value of the indicator; C max are the limiting values ​​of the indicators; in this way, the values ​​of all variables vary between 0 and 1.

3. A method for evaluating the status of a hydropower unit based on multi-index fusion according to claim 1, characterized in that: In step 3, an evaluation index system is constructed for the comprehensive status assessment of the hydropower unit. The multiple indicators contained therein are layered according to their attributes to form a multi-level system, including: Target layer: comprehensive status assessment of hydropower units; Project level: vibration, swing, pulse, temperature; Index layer: Vibration includes upper cover vibration (X, Y, Z) and shaft system vibration (A, B, C), swing index includes water-conductor pendulum X and Y, pressure pulsation index includes volute pressure pulsation and exhaust pipe pressure pulsation, temperature index includes water-conductor bearing temperature and water-conductor oil temperature.

4. A method for evaluating the status of a hydropower unit based on multi-index fusion according to claim 1, characterized in that: In step 3, the fuzzy evaluation matrix of each indicator is obtained as shown in formulas (2) and (3): x jk =d jk / d (2) Where: d represents the total number of experts in the indicator set, d jk Representative indicator set C i The number of experts who make the k-th level comments on the j-th evaluation index, x jk is the membership degree of the jth indicator to the kth level comment; Where: X nr Represents the membership degree of the nth evaluation indicator in the indicator set Ci to the rth level comment, R i is the fuzzy evaluation matrix of indicators in the same layer.

5. The method for evaluating the status of a hydropower unit based on multi-index fusion according to claim 1 is characterized in that: In step 4, the specific steps of using the analytic hierarchy process to calculate the subjective weights of each indicator are as follows: 4.

1. Build a comprehensive model of hydropower units and construct a multi-level indicator system with hydropower units as the target; 4.

2. According to the comparison of the importance of different indicators, a judgment matrix is ​​constructed, as shown in formula (4): v i With v j compared to Corresponding Where: v i represents the selected i-th index, v j represents the jth index selected, C ij Represents the importance relationship between the i-th indicator and the j-th indicator; 4.

3. According to the judgment matrix C obtained above, as shown in formula (5): C=(C ij ) n×n (5) Where: C ij >0, C ii =1; 4.

4. Calculate the maximum eigenvalue and the corresponding eigenvector of the judgment matrix, and define the consistency index CI according to the eigenvalue, as shown in formula (6): Where: max is the maximum eigenvalue of the judgment matrix, and n is the number of corresponding eigenvectors; If CI = 0, then there is complete consistency; if CI is close to 0, then there is good consistency; if CI is larger, then the consistency is worse; 4.

5. According to the randomness index RI corresponding to the matrix order and the consistency index CI of the matrix, the consistency ratio is defined as shown in formula (7): Where: CR is the consistency ratio; 4.

6. When the matrix meets the consistency requirements, the eigenvector corresponding to the maximum eigenvalue of the judgment matrix C is normalized to obtain the corresponding weight set (w1, w2, ..., w n ), where Ci is as shown in formula (8): Where: P i is the eigenvector corresponding to the judgment matrix.

6. A method for evaluating the status of a hydropower unit based on multi-index fusion according to claim 1, characterized in that: In step 4, the specific steps for using the decision and laboratory evaluation method to calculate the objective weights of each indicator are as follows: 4-1. According to the triangular fuzzy function, the influence relationship between indicators at the same level is converted into a triangular fuzzy judgment set according to the corresponding table; 4-2. Use the DEMATEL method to reflect the mutual influence of each indicator in the indicator system, and use the CFCS method to defuzzify and calculate the objective weight; 4-3. Establish the initial direct impact matrix, collect expert opinions and convert them into triangular fuzzy numbers (l ij ,m ij ,u ij ), and obtain the initial direct influence matrix given by the kth expert As shown in formula (9): 4-4. Calculate the normalized triangular fuzzy number, as shown in formula (10): Where: Indicates the difference between the right and left values ​​of a triangular fuzzy number is the standard triangular fuzzy value; 4-5. According to the left and right standard values Calculate the normalized total As shown in formula (11): 4-6. Calculate the impact of the i-th factor on the j-th factor to obtain the direct impact matrix D, as shown in formula (12): Where: d ij represents the mean of K experts’ judgments, and D is the direct influence matrix formed by the mean of experts’ judgments; 4-7. Standardize the processing matrix D and calculate the comprehensive impact matrix T, as shown in formula (13): Where: Represents the maximum value of the sum of elements in each row of matrix D; 4-8. Superimpose the elements in the matrix T according to rows and columns, and calculate the influence degree e, the influence degree f, the centrality m and the cause degree h, as shown in formula (14): Where: t ij is the impact factor in the comprehensive impact matrix T; 4-9. Calculate objective weight As shown in formula (15):

7. The method for evaluating the status of a hydropower unit based on multi-index fusion according to claim 1 is characterized by: In step 4, the subjective weight and objective weight of each indicator are comprehensively considered to obtain the actual weighted set of indicators as shown in formula (16): Where: is the subjective weight of the indicator, is the objective weight of the indicator.

8. The method for evaluating the status of a hydropower unit based on multi-index fusion according to claim 1 is characterized by: In step 5, the fuzzy evaluation matrix of the project objectives in the project layer is obtained as shown in formula (17): Where: It represents the different membership values ​​of a certain project target B in the project layer belonging to the 4 status evaluation levels, R is the indicator fuzzy evaluation weight matrix, and W is the weight matrix corresponding to the indicator.

Images