A method for identifying a reciprocating compressor valve failure

Abstract

This application belongs to the field of compressor technology, specifically relating to a method for identifying valve faults in reciprocating compressors. As a crucial component of reciprocating compressors, valves have a relatively high failure rate, especially in ultra-high pressure reciprocating compressors, where valve failures are even more prominent. Existing fault diagnosis methods are mostly limited to process parameters and sound analysis, which are complex and require a high level of professional experience from testing personnel, thus limiting their widespread application in engineering practice. This application provides a method for detecting valve faults in reciprocating compressors. It obtains the temperature of the valve cover on the same side of the cylinder and processes the data based on its distribution and trend characteristics. Evaluation indicators are constructed using the similarity of the temperatures of each valve cover, and valve faults are identified using the characteristic distribution patterns of normal valve temperature data. This provides an easily applicable reference method for early and rapid identification of valve faults in reciprocating compressors.

Description

Technical Field

[0001] This invention relates to the field of valve fault diagnosis technology for reciprocating compressors, and in particular to a method for identifying valve faults in reciprocating compressors. Background Technology

[0002] Reciprocating compressors are widely used power equipment in the industrial field. Their core component, the valve, is responsible for the periodic control of gas intake and discharge, which directly affects the efficiency, energy consumption, and operational stability of the compressor. At present, valve fault diagnosis is mainly based on signal monitoring and state parameter analysis. Common methods include (1) Vibration signal analysis: collecting valve vibration signals through acceleration sensors, analyzing the characteristics of impact force changes, and identifying valve plate breakage or spring failure; (2) Pressure indicator diagram method: measuring the pressure change curve inside the cylinder. If the intake valve leaks, the expansion process curve will shift downward, and the exhaust valve fault manifests as abnormal compression process; (3) Temperature and pressure monitoring: real-time monitoring of interstage pressure, exhaust temperature, and valve cover temperature. Leakage faults are often accompanied by abnormal temperature rise and pressure fluctuation; (4) Lubricating oil analysis: detecting the metal particle composition in the lubricating oil to indirectly determine the degree of valve wear; (5) Acoustic and displacement detection: using noise signals or displacement sensors to capture the deviation of valve plate movement trajectory and evaluate the real-time status of valve operation.

[0003] Despite the abundance of existing technologies, the following problems still exist in practical applications: theoretical research is based on ideal conditions, while actual field conditions are complex. For example, vibration signals are easily affected by noise from other mechanical components, and the complexity of high-precision sensor installation and signal processing algorithms limits field applications. These factors make it difficult for the commonly used methods mentioned above to guarantee diagnostic accuracy. Summary of the Invention

[0004] To overcome the shortcomings of existing technologies where valve fault accuracy is affected by complex conditions and difficult to guarantee, this invention proposes a method for detecting abnormal valve temperature data in reciprocating compressors. Based on the analysis of valve cover temperature monitoring data of reciprocating compressor valves, a comprehensive evaluation index for early valve fault identification is constructed. This invention is based on existing valve monitoring equipment, explores its distribution regularity, and realizes an efficient and non-invasive valve fault identification method, which is of great significance for improving compressor operation reliability and reducing maintenance costs.

[0005] The present invention proposes a method for identifying valve failures in a reciprocating compressor, comprising the following steps:

[0006] St1. Synchronously collect the temperature data of the valve cover of the same cylinder on the same side of the reciprocating compressor and perform time alignment to construct the temperature time sequence data of each valve.

[0007] Step 2: Build temperature time series data for each valve, and calculate the similarity index and consistency index of the temperature time series data for each pair of valves.

[0008] St3. For each pair of valves, calculate the combined weight of the similarity index and the consistency index as the comprehensive evaluation index s(p,q);

[0009] St4. If all comprehensive evaluation indicators s(p,q) corresponding to valve p are less than the set threshold, then valve p is judged to be in a fault state.

[0010] Preferred:

[0011]

[0012] Where w represents the weighting coefficient; d(p,q) represents the similarity index between air valve p and air valve q; and ρ(p,q) represents the consistency index between air valve p and air valve q.

[0013] Preferably, the consistency index is the correlation coefficient;

[0014]

[0015] Among them, Tp n Tq represents the valve cover temperature of valve p at time n. n The valve cover temperature of valve q at time n is represented by N, and N represents the time series length of the temperature time series data. Let T(p) be the mean of the temperature time series data. This represents the mean of the temperature time series data T(q).

[0016] Preferably, the weighting coefficient w takes values ​​in the interval [0.3, 0.5].

[0017] Preferably, the similarity index d(p,q) is the Fréchet distance.

[0018] Preferred:

[0019] Let D[i][j] = max(d(Tp) i ,Tq j ),min(D[i-1][j],D[i][j-1],D[i-1][j-1]))

[0020] d(Tp i ,Tq j )=|Tp i -Tq j |

[0021] D[0][0]=0

[0022] D[i][0]=∞

[0023] D[0][j]=∞

[0024] i and j represent time points, 1≤i≤N, 1≤j≤N, and N represents the length of the temperature time series data; Tp i Let Tq be the valve cover temperature of valve p at time i. j The valve cover temperature of valve q at time j; d(Tp) i ,Tq j ) represents Tp i and Tq j The distance between them;

[0025] The Fréchet distance between valves p and q is D[N][N].

[0026] Preferably, in step St1, the temperature data of the valve cover of the same cylinder on the same side of the reciprocating compressor is first collected and outlier processing is performed; then the temperature data of each valve cover are aligned at time points and the temperature time series data of the valve is constructed.

[0027] The present invention proposes a reciprocating compressor valve fault identification device, which includes a data receiving module, a data preprocessing module, a time alignment module, and a comprehensive evaluation module;

[0028] The data receiving module is used to receive the valve cover temperature of the same cylinder and the same side valve of the reciprocating compressor collected by the monitoring equipment;

[0029] The data preprocessing module is used to preprocess the valve cover temperature time series data of each gas valve, including outlier removal and missing value interpolation.

[0030] The time alignment module is used to perform time-aligned sampling of the temperature time series data of the valve cover after different preprocessing of the air valve;

[0031] The comprehensive evaluation module is used to calculate the correlation and consistency indices of temperature time series data between different gas valves, and to calculate the comprehensive evaluation index.

[0032] The present invention proposes a reciprocating compressor valve fault identification system, comprising a memory and a processor. The memory stores a computer program, and the processor is connected to the memory. The processor is used to execute the computer program to implement the reciprocating compressor valve fault identification method.

[0033] The present invention proposes a storage medium storing a computer program, which, when executed, is used to implement the method for identifying faults in the reciprocating compressor valve.

[0034] The advantages of this invention are:

[0035] (1) Compared with the temperature distribution characteristics of the intake valve cover under normal operating conditions, the temperature data distribution of the valve cover under abnormal conditions is significantly different. This invention analyzes the similarity and consistency of the temperature distribution data of the valves on the same side of a single cylinder, identifies abnormal valve cover temperatures based on the differences in the identified data distribution trends, and thus determines valve failures. This makes the monitoring and diagnosis of reciprocating compressor valve failures more real-time and robust, providing a method that is easy to implement in engineering practice for valve failure identification.

[0036] (2) Discrete Fréchet distance primarily measures the similarity of temperature data distribution trends, considering the shape and order of temperature changes, reflecting the differences in data trends. The smaller the distance, the more similar the curve shapes of the two data sets. Pearson correlation coefficient mainly evaluates the sensitivity of temperature data changes, reflecting the consistency of temperature data in rising or falling trends. The closer the correlation coefficient is to 1 or -1, the stronger the monotonic correlation between the two data sets. Combining discrete Fréchet distance and Pearson correlation coefficient to construct a comprehensive evaluation index more comprehensively reflects the similarity of two temperature data sets, making full use of the advantages of both methods, considering both the overall shape change of the data and the monotonic correlation of the data. The comprehensive evaluation index of this invention is the sum of the weights of the Fréchet distance and the Pearson correlation coefficient. By combining Fréchet distance and Pearson correlation coefficient to construct a comprehensive evaluation index, and setting thresholds based on historical data or domain knowledge, it assists in the identification and diagnosis of valve malfunctions. By combining discrete Fréchet distance and Pearson correlation coefficient, the similarity between two temperature data sets can be comprehensively evaluated from different perspectives. This can better capture the similarity of temperature curve shapes and trends, and better measure the consistency of temperature data in monotonic trends.

[0037] (3) The present invention also provides a simple and fast method for calculating discrete Fréchet distance, which greatly improves the calculation efficiency while ensuring the accuracy of the calculation results.

[0038] (4) In this invention, the larger the comprehensive evaluation index value, the more similar the distribution of valve cover temperature; the closer the comprehensive evaluation index is to 1, the stronger the correlation between the two sets of temperature data. It considers both the shape and trend similarity of the data curves (through discrete Fréchet distance) and the monotonic correlation of the data (through Pearson correlation coefficient), and can more comprehensively evaluate the correlation of temperature data. Attached Figure Description

[0039] Figure 1 This is a flowchart of the method of the present invention;

[0040] Figure 2This is a temperature distribution diagram of the intake valve cover of a certain reciprocating unit A100 over 24 hours.

[0041] Figure 3(a) shows the Fréchet distance matrix of valve cover temperature for unit A100;

[0042] Figure 3(b) shows the Pearson coefficient matrix for valve cover temperature of unit A100;

[0043] Figure 3(c) shows the comprehensive evaluation index matrix of valve cover temperature for unit A100;

[0044] Figure 4 This is a temperature distribution diagram of the intake valve cover during time B100 of the reciprocating unit;

[0045] Figure 5(a) shows the Fréchet distance matrix of valve cover temperature for unit A100;

[0046] Figure 5(b) shows the Pearson coefficient matrix for valve cover temperature of unit A100;

[0047] Figure 5(c) shows the comprehensive evaluation index matrix of valve cover temperature for unit A100. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] like Figure 1 As shown, the present invention proposes a method for identifying valve failures in a reciprocating compressor, which includes the following steps.

[0050] St1. Synchronously collect the temperature data of the valve cover on the same side of the same cylinder of the reciprocating compressor and perform time alignment to construct the temperature time sequence data of each valve.

[0051] In practice, the temperature data of the valve cover on the same side of the same cylinder of the reciprocating compressor is first collected, and outlier values ​​are deleted and missing values ​​are interpolated.

[0052] Valve cover temperature data is obtained from relevant monitoring equipment or data recording systems. The data should include the temperature measurement value and the corresponding timestamp information to facilitate time alignment.

[0053] Then, the valve cover temperature data of the same cylinder and the same side valve of the reciprocating compressor are aligned at time points, and the temperature time series data of the valve is constructed.

[0054] Because the temperature measurement times of different valve covers may vary, it is necessary to align the temperature data of all valve covers in chronological order. Interpolation is used to ensure that each valve cover has a corresponding temperature value at the same point in time.

[0055] Suppose that a reciprocating compressor has two valves on the same side of the same cylinder, denoted as valve p and valve q respectively. The temperature time series data corresponding to valve p is denoted as T(p), and the temperature time series data corresponding to valve q is denoted as T(q).

[0056] T(p) = [Tp1, Tp2, ..., Tp n ,…,Tp N ]

[0057] T(q) = [Tq1, Tq2, ..., Tq n ,…,Tq N ]

[0058] Among them, Tp n and Tq n Tp1, Tp2, and Tp3 represent the valve cover temperatures of valves p and q at time n, respectively, where 1 ≤ n ≤ N, and N represents the time sequence length; N Tq1, Tq2, and Tq represent the valve cover temperatures of valve p at times 1, 2, and N, respectively. N These represent the valve cover temperatures of the air valve q at times 1, 2, and N, respectively.

[0059] St2, calculate the Fréchet distance d(T(p),T(q)) and correlation coefficient ρ(p,q) for the temperature time series data of each pair of valves.

[0060] That is, in this embodiment, the Fréchet distance d(T(p),T(q)) of the temperature time series data of valve p and valve q is used as the similarity index d(p,q), and the correlation coefficient is used as the consistency index ρ(p,q).

[0061] The Fréchet distance between the temperature time series data of valve p and valve q is used to measure the similarity of the valve cover temperature data.

[0062] Construct the link sequence L of temperature data sequences T(p) and T(q):

[0063]

[0064] Where a1=b1=1, a m =b m =N; m is the length of the link sequence L, 1≤k≤m, 1≤a k ≤N, 1≤b k ≤N; a1≤a2≤a3≤…≤ak ≤…≤a m b1≤b2≤b3≤…≤b k ≤…≤b m ; and a k+1 =a k or a k +1, b k+1 =b k or b k +1, k+1≤m;

[0065] Right now

[0066]

[0067] Thus, the series L simultaneously follows the order of the endpoints in T(p) and T(q).

[0068] The essence of Fréchet distance is to find the minimum link sequence length among all the rule-compliant link sequences formed by the endpoints; the link sequence length is the maximum distance value of the data pairs it contains, that is, to calculate the distance value of each data pair in the link sequence and select the maximum value as the link sequence length.

[0069] Define length ||L|| as the length of the longest connection in sequence L, that is:

[0070]

[0071] The discrete Fréchet distance between these two temperature data sets T(p) and T(q) is defined as follows:

[0072] d(T(p),T(q))=min{||L|||L is the link sequence between T(p) and T(q)}.

[0073] Therefore, when calculating the Fréchet distance d(T(p),T(q)), it is first necessary to list all the sequences L, then calculate the length of each sequence, and then select the minimum value as the Fréchet distance.

[0074] For example, T(p) = [1,2,3] and T(q) = [5,3,6]:

[0075] Let the indices of T(p) in the sequence be a1 = 1, a2 = 2, a3 = 3, satisfying a2 = a1 + 1, a3 = a2 + 1, which are strictly increasing and satisfy the non-decreasing rule;

[0076] The subscripts corresponding to T(q) in the sequence are b1=1, b2=2, b3=3, satisfying b2=b1+1, b3=b2+1, which are strictly increasing and satisfy the non-decreasing rule;

[0077] We obtain the following linked sequence: (1,5), (2,3), (3,6), with a sequence length of:

[0078] ||L||=max{|1-5|,|2-3|,|3-6|}=max{4,1,3}=4.

[0079] Let the indices of T(p) in the sequence be a1 = 1, a2 = 1, a3 = 2, a4 = 2, a5 = 3; then a2 = a1, a3 = a2 + 1, a4 = a3, a5 = a4 + 1, satisfying a i+1 =a i or a i+1 =a i +1;

[0080] In the sequence, the indices corresponding to T(q) are b1 = 1, b2 = 2, b3 = 2, b4 = 3, b5 = 3; at this time, b2 = b1 + 1, b3 = b2, b4 = b3 + 1, b5 = b4, satisfying b i+1 =b i or b i +1=b i+1 ;

[0081] The second connected sequence is (1,5), (1,3), (2,3), (2,6), (3,6), with a sequence length of:

[0082] ||L||=max{|1-5|,|1-3|,|2-3|,|2-6|,|3-6|}=max{4,2,1,4,3}=4.

[0083] Let the indices of the sequence corresponding to T(p) be a1 = 1, a2 = 2, a3 = 3, a4 = 3, a5 = 3, satisfying a i+1 =a i or a i+1 =a i +1;

[0084] The indices corresponding to T(q) in the sequence are b1=1, b2=2, b3=3, b4=3, b5=3, satisfying b i+1 =b i or b i +1=b i+1 ;

[0085] The third connection sequence is obtained as (1,5), (1,3), (1,6), (2,6), (3,6), with a sequence length of:

[0086] ||L||=max{|1-5|,|1-3|,|1-6|,|2-6|,|3-6|}=max{4,2,5,4,3}=5.

[0087] According to the construction rules of the link sequence L, T(p) and T(q) of length N can be used to construct 4 N-1 Four link sequences were constructed in this embodiment. 2 Among the linked sequences, the minimum value in ||L|| is found to be 4. Therefore, the discrete Fréchet distance is 4.

[0088] Clearly, using the algorithms listed above involves an enormous amount of work. To improve computational efficiency, this implementation proposes a simpler calculation method for calculating the Fréchet distance.

[0089] First, set the matrix boundaries: D[0][0] = 0, D[i][0] = ∞, D[0][j] = ∞, i and j represent time points, 1 ≤ i ≤ N, 1 ≤ j ≤ N;

[0090] Recursively calculate the distance parameter D[i][j]:

[0091] D[i][j]=max{d(Tp i ,Tq j ),min(D[i-1][j],D[i][j-1],D[i-1][j-1])}

[0092] d(Tp i ,Tq j )=|Tp i -Tq j |

[0093] Where D[i-1][j-1], D[i-1][j], and D[i][j-1] are all distance parameters, and Tp i Let Tq be the valve cover temperature of valve p at time i. j The valve cover temperature of valve q at time j; d(Tp) i ,Tq j ) represents Tp i and Tq j The distance between them;

[0094] The calculated result D[N][N] of D[i][j] is used as the Fréchet distance between valve p and valve q.

[0095] In the above examples where T(p) = [1,2,3] and T(q) = [5,3,6], the recursive formula D[i][j] is used for calculation, and the results are as follows:

[0096] D[3][3]=max{d(Tp3,Tq3),min(D[2][3],D[3][2],D[2][2])}

[0097] d(Tp3,Tq3) = |3 - 6| = 3

[0098] D[2][3] = max{d(Tp2,Tq3), min(D[1][3], D[2][1], D[1][2])}

[0099] D[1][3] = max{d(Tp1,Tq3), min(D[0][3], D[1][2], D[0][1])} = max{5, min(∞, D[1][2], ∞)}

[0100] D[2][1] = max{d(Tp2,Tq1), min(D[1][1], D[2][0], D[1][0])} = max{3, min(D[1][1], ∞, ∞)}

[0101] D[1][2] = max{d(Tp1,Tq2), min(D[0][2], D[1][1], D[0][1])} = max{2, min(∞, D[1][1], ∞)} [[ID=第十五]]

[0102] D[1][1] = max{d(Tp1,Tq1), min(D[0][1], D[1][0], D[0][0])} = max{4, min(∞, ∞, 0)} = 4

[0103] Reverse calculation: D[1][2] = 4, D[2][1] = 4, D[1][3] = 5, D[2][3] = max{4, min(5, 4, 4)} = 4; D[3][2] = max{d(Tp3,Tq2), min(D[2][2], D[3][1], D[2][1])}

[0104] D[2][2] = max{d(Tp2,Tq2), min(D[1][2], D[2][1], D[1][1])} = max{1, min(4, 4, 4)} = 4

[0105] D[3][1] = max{d(Tp3,Tq1), min(D[2][1], D[3][0], D[2][0])} = max{2, min(4, ∞, ∞)} = 4

[0106] D[2][2] = max{d(Tp2,Tq2), min(D[1][2], D[2][1], D[1][1])} = max{1, min(4, 4, 4)} = 4

[0107] Reverse calculation: D[3][2] = max{0, min(4, 4, 4)} = 4

[0108] D[3][3]=max{3,min(4,4,4}=4; that is, the Fréchet distance between the temperature data sequences T(p)=[1,2,3] and T(q)=[5,3,6] calculated by the first method is 4.

[0109] As can be seen, the recursive calculation results are consistent with the calculation results of the chain segment sequence listing, proving the effectiveness of the simplified calculation provided by the present invention.

[0110] The correlation coefficient ρ(p,q) of the temperature time series data of valves p and q is used to evaluate the consistency of temperature data changes, and its calculation process is as follows:

[0111]

[0112] in, Let T(p) be the mean of the temperature time series data. This represents the mean of the temperature time series data T(q).

[0113] St3, calculate the comprehensive evaluation index s(p,q) for each pair of valves based on Fréchet distance and correlation coefficient;

[0114]

[0115] Where w represents the weighting coefficient; d(p,q) represents the Fréchet distance between valve p and valve q; and ρ(p,q) represents the correlation coefficient between valve p and valve q.

[0116] The larger the comprehensive evaluation index s(p,q) value, the more similar the temperature time series data T(p) and T(q) are. The weighting coefficient w ranges from [0,1] and is used to adjust the weights of the discrete Fréchet distance and Pearson correlation coefficient in the comprehensive evaluation index. The weighting coefficient is usually determined based on the characteristics of the valve cover temperature of the specific compressor model and domain knowledge. It is usually considered that the shape of the valve temperature distribution is more important for identifying the valve condition, so it can be taken in the interval [0.3, 0.5].

[0117] St4. If all comprehensive evaluation indicators s(p,q) corresponding to valve p are less than the set threshold, then valve p is judged to be in a fault state.

[0118] According to the judgment criteria of this embodiment, the comprehensive evaluation index value of each air valve is compared with the set threshold. If the comprehensive evaluation index value of a certain air valve and the other multiple air valves are all less than the threshold, it indicates that the valve cover temperature distribution of the air valve is significantly different from that of the other air valves. Therefore, it is judged that the air valve may have a fault or abnormality, which is theoretically valid.

[0119] Thresholds are set based on historical data or domain knowledge to aid in the identification and diagnosis of valve malfunctions. For example, when a reciprocating compressor is operating normally, valve cover temperature data for the same valve on the same side of the same cylinder is collected. Then, steps St1-St3 above are used to calculate the comprehensive evaluation index between each pair of valves as a health indicator. In this case, the threshold must be set lower than the health indicator. Alternatively, historical data of a reciprocating compressor with multiple valves on the same side of the same stage can be selected. The valve cover temperature data of each valve when one valve malfunctions can be obtained from the historical data. Then, steps St1-St3 above are used to calculate the comprehensive evaluation index between each pair of valves. A threshold is set to separate the comprehensive evaluation index of the malfunctioning valve from other comprehensive evaluation indicators.

[0120] The following specific embodiments verify the above-mentioned method for identifying valve faults in reciprocating compressors.

[0121] In the following examples, temperature time-series data with a step size of 1 hour and a data volume of 24 are constructed.

[0122] Example 1

[0123] Taking a reciprocating unit A100 as an example, it contains 4 intake valves, labeled 1#-4#.

[0124] In this embodiment, the unit monitoring equipment acquires relevant data, such as the temperature data of the valve covers of intake valves #1 to #4 on the same side of the first-stage cylinder within a specified time (e.g., 24 hours), including the temperature measurement values ​​of each valve at different times and the corresponding timestamp information. Since the temperature measurement times of different valve covers may deviate, an interpolation method is used to perform time alignment preprocessing on the data, so that each valve has a corresponding temperature value at the same time point, ensuring the accuracy of subsequent calculations.

[0125] This embodiment selects data during the time period of intake valve #2 failure.

[0126] In this embodiment, a temperature value is extracted from the preprocessed discrete ordered sequence dataset at 1-hour intervals, thereby obtaining 24 temperature values ​​that constitute the temperature time-series data of each intake valve, such as... Figure 2 As shown. Thus, the temperature data matrix of the four intake valves of the reciprocating unit A100 is represented as follows:

[0127]

[0128] That is, p,q∈[1,2,3,4], i,j∈[1,2,……,24]; Tp# i This indicates the valve cover temperature of the intake valve p at time i;

[0129] The Fréchet distance d(1#,2#) between intake valve 1# and intake valve 2# is calculated as follows:

[0130] Let: D[0][0]=0, D[i][0]=∞, D[0][j]=∞; i,j∈[1, 2,...,24];

[0131] D[1][0]=D[0][1]=∞

[0132] D[1][1]=max{d(T1#1,T2#1),(D[0][0]; D[0][1]; D[1][0])}

[0133] D[1][2]=max{d(T1#1,T2#2),(D[0][1]; D[0][2]; D[1][1])}

[0134] ...

[0135] D

[24]

[24] =max{d(T1# 24 T2# 24 ),(D

[23]

[23] ; D

[23]

[24] ; D

[24]

[24] )}

[0136] In this embodiment, after actual measurement and sorting, T1#1 = 53.43 and T2#1 = 50.43 are obtained. The recursive calculation yields D

[24]

[24] = 13.82, that is: d(1#,2#) = 13.82.

[0137] Following the same method, the discrete Fréchet distances between each pair of intake valves 1# and 3#, 4#, and 2#, 3#, 4# are calculated, ultimately yielding... Figure 4 The Fréchet distance matrix of the valve cover temperature of valve A of the reciprocating unit is shown in Figure 3(a).

[0138] The Pearson correlation coefficient formula for the temperature sequence of intake valve 1# and intake valve 2#d is calculated as follows:

[0139]

[0140] Among them, T1# n This indicates the valve cover temperature of intake valve #1 at time n; This represents the average temperature of intake valve #1 over 24 hours; T2# n This indicates the valve cover temperature of intake valve #2 at time n; This indicates the average temperature of intake valve #2 over 24 hours.

[0141] In this embodiment, the Pearson correlation coefficient ρ(1#,2#) for intake valves 1# and 2# was calculated to be 0.45.

[0142] Following the same method, the Pearson correlation coefficients between intake valve 1# and intake valves 3# and 4#, as well as between intake valves 2#, 3# and 4#, were calculated to obtain the Pearson correlation coefficient matrix of reciprocating unit A100 shown in Figure 3(b).

[0143] If the weight of the Fréchet distance component is set to 0.45, then the weight of the Pearson correlation coefficient component is 0.55, and the weight coefficient w is set to 0.45.

[0144] Therefore, the comprehensive evaluation index for the valve covers of intake valve #1 and intake valve #2 is:

[0145]

[0146] Using the same method, calculate the comprehensive evaluation index values ​​between each pair of intake valve 1# and intake valves 3# and 4#, as well as between intake valves 2#, 3# and 4#, to obtain the comprehensive evaluation index matrix of reciprocating unit A100 in Figure 3(c).

[0147] Observe the comprehensive evaluation index matrix of reciprocating unit A100 in Figure 3(c) and compare the comprehensive evaluation index values ​​of each valve with the set threshold of 0.5. In the comprehensive evaluation index matrix, the comprehensive evaluation index value of intake valve 2# and intake valve 1# is 0.28, which is less than 0.5, indicating that the similarity of the valve cover temperature distribution of intake valve 2# and intake valve 1# is low. The comprehensive evaluation index value of intake valve 2# and intake valve 3# is 0.24, and the comprehensive evaluation index value of intake valve 2# and intake valve 4# is 0.29, indicating that intake valve 2# differs significantly from intake valves 1#, 3#, and 4# in terms of temperature distribution similarity. The comprehensive evaluation index values ​​of other intake valves 1#, 3#, and 4# are all greater than 0.5, indicating that the temperature change trend and distribution shape of intake valve 2# are inconsistent with other intake valves. Therefore, it is judged that intake valve 2# may have a fault.

[0148] The judgment result is consistent with the actual situation.

[0149] Example 2

[0150] In this embodiment, taking the recirculation unit B100 as an example, it includes 4 air valves, which are denoted as air valves A, B, C and D respectively.

[0151] In this embodiment, when valve D is in an abnormal state, the valve cover temperature data of valves A, B, C, and D are collected synchronously. Referring to the preprocessing method in Embodiment 1, 24-hour temperature time-series data are obtained as follows: Figure 4 As shown.

[0152] In this embodiment, the Fréchet distance matrix of the reciprocating unit B100 is shown in Figure 5(a), the Pearson correlation coefficient matrix is ​​shown in Figure 5(b), and the comprehensive evaluation index matrix is ​​shown in Figure 5(c).

[0153] In this embodiment, the threshold value is 0.5.

[0154] Based on the comprehensive evaluation index matrix of reciprocating unit B100 in Figure 5(c), and examining the comprehensive evaluation index values ​​of valve D with other valves (valve A, valve B, and valve C), it can be seen that the comprehensive evaluation index value of valve D is less than 0.5, indicating that the temperature distribution of valve D's valve cover differs significantly from that of other valves. This means that valve D differs from other normally functioning valves in terms of temperature change trend and distribution shape, thus suggesting that valve A may be malfunctioning.

[0155] The judgment result is consistent with the actual situation.

[0156] Of course, those skilled in the art will recognize that the present invention is not limited to the details of the exemplary embodiments described above, but also includes the same or similar structures that can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0157] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

[0158] The technologies, shapes, and structures not described in detail in this invention are all known technologies.

Claims

1. A method for identifying valve failures in a reciprocating compressor, characterized in that, Includes the following steps: St1. Synchronously collect the temperature data of the valve cover of the same cylinder on the same side of the reciprocating compressor and perform time alignment to construct the temperature time sequence data of each valve. Step 2: Build temperature time series data for each valve, and calculate the similarity index and consistency index of the temperature time series data for each pair of valves. St3. For each pair of valves, calculate the combined weight of the similarity index and the consistency index as the comprehensive evaluation index s(p,q); St4. If all comprehensive evaluation indicators s(p,q) corresponding to valve p are less than the set threshold, then valve p is judged to be in a fault state. Where w represents the weighting coefficient; d(p,q) represents the similarity index between valve p and valve q. This indicates the consistency index between air valve p and air valve q. The consistency index uses the correlation coefficient; Among them, Tp n Tq represents the valve cover temperature of valve p at time n. n The valve cover temperature of valve q at time n is represented by N, and N represents the time series length of the temperature time series data. Let T(p) be the mean of the temperature time series data. The mean of the temperature time series data T(q); The weighting coefficient w takes values ​​in the interval [0.3, 0.5]. The similarity index d(p,q) uses the Fréchet distance; make d( Tp i , Tq j )=| Tp i - Tq j | D[0][0]=0 D[i][0]=∞ D[0][j]=∞ i and j represent time points, 1≤i≤N, 1≤j≤N, and N represents the length of the temperature time series data; Tp i Let Tq be the valve cover temperature of valve p at time i. j The valve cover temperature of valve q at time j; d( Tp i , Tq j )express Tp i and Tq j The distance between them; The Fréchet distance between valves p and q is D[N][N].

2. The method for identifying valve failures in a reciprocating compressor as described in claim 1, characterized in that, In step St1, the temperature data of the valve cover on the same side of the same cylinder of the reciprocating compressor is first collected and outlier processing is performed; then the temperature data of each valve cover are aligned at time points and the temperature time series data of the valve is constructed.

3. A reciprocating compressor valve fault identification device, used to implement the reciprocating compressor valve fault identification method as described in claim 1 or 2, characterized in that, It includes a data receiving module, a data preprocessing module, a time alignment module, and a comprehensive evaluation module; The data receiving module is used to receive the valve cover temperature of the same cylinder and the same side valve of the reciprocating compressor collected by the monitoring equipment; The data preprocessing module is used to preprocess the valve cover temperature time series data of each gas valve, including outlier removal and missing value interpolation. The time alignment module is used to perform time-aligned sampling of the temperature time series data of the valve cover after different preprocessing of the air valve; The comprehensive evaluation module is used to calculate the similarity and consistency indices of temperature time series data between different gas valves, and to calculate the comprehensive evaluation index.

4. A fault identification system for a reciprocating compressor valve, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, the processor is connected to the memory, and the processor is used to execute the computer program to implement the method for identifying valve failures in a reciprocating compressor as described in any one of claims 1 or 2.

5. A storage medium, characterized in that, The system contains a computer program that, when executed, is used to implement the method for identifying valve failures in a reciprocating compressor as described in any one of claims 1 or 2.

Images