Method and device for testing and evaluating industrial park integrated management system

Abstract

The invention discloses a test evaluation method and device for an industrial park integrated management system. The method comprises the following steps: acquiring a performance index data set of the industrial park integrated management system; the performance index data set comprises a performance index test data subset of each subsystem; the performance index test data subset comprises a test data sequence of each performance index; pre-processing the performance index data set to obtain a to-be-evaluated data set; and performing test evaluation processing on the to-be-evaluated data set to obtain a performance evaluation result value of the industrial park integrated management system.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of industrial data processing, performance test evaluation and strategy optimization technology, in particular to a test evaluation method and device of an industrial park comprehensive management system. BACKGROUND

[0002] The industrial park comprehensive management system is a core tool for efficient operation of modern industrial parks, and its performance directly affects the management efficiency, resource utilization and production benefit of the park. However, the existing test evaluation method of the industrial park comprehensive management system has many shortcomings. On the one hand, the traditional test method mainly focuses on the performance test of a single functional module, lacks comprehensive performance evaluation of the whole system, and is difficult to reflect the overall performance of the system in the actual complex operating environment. On the other hand, the existing method often ignores the integrity and credibility of data in the data processing stage, and is easily disturbed by abnormal data or noise, resulting in distorted evaluation results. In addition, for the comprehensive management system with multiple subsystems and multiple performance indicators, there is a lack of effective data synchronization and classification processing mechanism, making the evaluation process complex and inefficient. Therefore, how to design a method that can comprehensively, accurately and efficiently evaluate the performance of the industrial park comprehensive management system is a technical problem to be solved at present. SUMMARY

[0003] The present application mainly solves the problem of how to design a method that can comprehensively, accurately and efficiently evaluate the performance of the industrial park comprehensive management system, and discloses a test evaluation method and device of an industrial park comprehensive management system.

[0004] In a first aspect, the present application discloses a test evaluation method of an industrial park comprehensive management system, comprising:

[0005] S1, collecting performance indicator data sets of the industrial park comprehensive management system; the performance indicator data set includes a performance indicator test data sub-set of each subsystem; the performance indicator test data sub-set includes a test data sequence of each performance indicator;

[0006] S2, pre-processing the performance indicator data set to obtain a to-be-evaluated data set;

[0007] S3, performing test evaluation processing on the to-be-evaluated data set to obtain a performance evaluation result value of the industrial park comprehensive management system.

[0008] The pre-processing of the performance indicator data set to obtain the to-be-evaluated data set comprises:

[0009] S21, performing data cleaning processing on the performance indicator data set to obtain a first data set;

[0010] S22, performing time alignment processing on the first data set to obtain a second data set;

[0011] S23, performing category checking processing on the second data set to obtain a third data set;

[0012] S24, performing credibility discrimination processing on the third data set to obtain a to-be-evaluated data set.

[0013] The test evaluation processing on the to-be-evaluated data set obtains a performance evaluation result value of the industrial park comprehensive management system, including:

[0014] S31, performing statistical feature analysis on the to-be-evaluated data set to obtain a sampling feature value;

[0015] S32, based on the sampling feature value, uniformly dividing the to-be-evaluated data set to obtain a plurality of time period to-be-evaluated data sub-sets;

[0016] S33, performing test evaluation on each time period to-be-evaluated data sub-set to obtain a sub-evaluation value of each time period;

[0017] S34, performing fusion evaluation on the sub-evaluation values of all time periods to obtain a performance evaluation result value of the industrial park comprehensive management system.

[0018] The statistical feature analysis on the to-be-evaluated data set obtains a sampling feature value, including:

[0019] S311, using a test data sequence of each performance index of the to-be-evaluated data set as a row vector to construct a test matrix;

[0020] S312, calculating a rank value and a norm value of the test matrix;

[0021] S313, performing Demon transformation on each row vector of the test matrix to obtain a corresponding transformed vector; using all the transformed vectors to construct a transformed test matrix;

[0022] S314, performing feature dimension calculation on the transformed test matrix and the test matrix to obtain a feature dimension;

[0023] S315, determining the greatest common divisor of the feature dimension and the column dimension of the test matrix as the sampling feature value.

[0024] The expression of the feature dimension calculation is:

[0025]

[0026] Wherein, ω1 and ω2 are preset weighting factors, M and N are respectively the row dimension and column dimension of the transformation test matrix, μ and γ are respectively the rank value and norm value of the test matrix, D i represents the i-th dimension factor, D is the feature dimension, A ij and B ij are respectively the elements of the i-th row and j-th column of the transformation test matrix and test matrix, represents the floor of min(D i ).

[0027] The test evaluation on each time period of the to-be-evaluated data subset is performed to obtain a sub-evaluation value of each time period, and the method comprises the following steps of:

[0028] S331, for each time period, based on each performance index test data subset in the corresponding to-be-evaluated data subset, performing a sub-item performance evaluation process to obtain an evaluation value and a weight value of each sub-system;

[0029] S332, using the weight value of each sub-system, performing a weighted summation on the evaluation value of each sub-system to obtain a sub-evaluation value of each time period.

[0030] The sub-item performance evaluation process based on each performance index test data subset in the to-be-evaluated data subset is performed to obtain an evaluation value and a weight value of each sub-system, and the method comprises the following steps of:

[0031] S3311, for each sub-system corresponding performance index test data subset in the to-be-evaluated data subset, obtaining a standard value of each performance index of the performance index test data subset;

[0032] S3312, using a test data sequence of each performance index of the performance index test data subset, respectively subtracting a standard value of the corresponding performance index to obtain a corresponding difference sequence;

[0033] S3313, performing a feature matrix transformation on each difference sequence of the performance index test data subset respectively to obtain a corresponding feature matrix;

[0034] S3314, performing an evaluation calculation on all feature matrices of the performance index test data subset to obtain an evaluation value and a weight value of the corresponding sub-system.

[0035] The second aspect of the present application discloses a test evaluation device of an industrial park comprehensive management system, and the device comprises:

[0036] A memory storing executable program codes;

[0037] A processor coupled with the memory;

[0038] The processor invokes the executable program code stored in the memory to execute the test evaluation method of the industrial park integrated management system.

[0039] The present application discloses a computer storage medium, which stores computer instructions.

[0040] The present application discloses an information data processing terminal for implementing the test evaluation method of the industrial park integrated management system.

[0041] The present application has the following advantages:

[0042] The present application provides a test evaluation method of an industrial park integrated management system, which effectively solves the problems in the prior art through systematic data preprocessing and refined test evaluation process.

[0043] The present application adopts statistical feature analysis and uniform division method, which can dynamically adjust the evaluation granularity according to the actual operation of the system, so that the evaluation result is more consistent with the actual performance of the industrial park integrated management system. BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 The present application discloses a computer storage medium, which stores computer instructions. DETAILED DESCRIPTION

[0045] In order to better understand the content of the present application, an embodiment is given.

[0046] Figure 1 The present application discloses a computer storage medium, which stores computer instructions.

[0047] The present application discloses a computer storage medium, which stores computer instructions.

[0048] S1, a performance index data set of the industrial park comprehensive management system is collected; the performance index data set includes a performance index test data sub-set of each sub-system; the performance index test data sub-set includes a test data sequence of each performance index;

[0049] S2, the performance index data set is pre-processed to obtain a to-be-evaluated data set;

[0050] S3, the to-be-evaluated data set is tested and evaluated to obtain a performance evaluation result value of the industrial park comprehensive management system;

[0051] The pre-processing of the performance index data set to obtain the to-be-evaluated data set comprises:

[0052] S21, the performance index data set is subjected to data cleaning processing to obtain a first data set;

[0053] S22, the first data set is subjected to time alignment processing to obtain a second data set;

[0054] S23, the second data set is subjected to category checking processing to obtain a third data set;

[0055] S24, the third data set is subjected to credibility discrimination processing to obtain the to-be-evaluated data set.

[0056] The testing and evaluation of the to-be-evaluated data set to obtain the performance evaluation result value of the industrial park comprehensive management system comprises:

[0057] S31, statistical feature analysis is performed on the to-be-evaluated data set to obtain a sampling feature value;

[0058] S32, based on the sampling feature value, the to-be-evaluated data set is uniformly divided to obtain to-be-evaluated data sub-sets of a plurality of time periods;

[0059] The uniform division of the to-be-evaluated data set based on the sampling feature value to obtain to-be-evaluated data sub-sets of a plurality of time periods is that the test data sequence of each performance index of the to-be-evaluated data set is uniformly divided into a data sequence with a number of elements equal to the sampling feature value, and the data sequences of all performance indexes of the same time period are used to construct the to-be-evaluated data sub-set of the time period;

[0060] S33, the to-be-evaluated data sub-set of each time period is tested and evaluated to obtain a sub-evaluation value of each time period;

[0061] S34, the sub-evaluation values of all time periods are fused and evaluated to obtain the performance evaluation result value of the industrial park comprehensive management system.

[0062] The fusion evaluation is weighted summation of the sub-evaluation values of each time period by using preset weighting factors to obtain the performance evaluation result value of the industrial park comprehensive management system. The weighting factors can be obtained by taking the inverse of the average time of each time period.

[0063] The statistical feature analysis on the to-be-evaluated data set obtains a sampling feature value, including:

[0064] S311, using the test data sequence of each performance indicator of the to-be-evaluated data set as a row vector, a test matrix is constructed;

[0065] S312, the rank value and the norm value of the test matrix are calculated;

[0066] S313, performing Demon transformation on each row vector of the test matrix to obtain a corresponding transformed vector; using all the transformed vectors, a transformed test matrix is constructed;

[0067] S314, performing feature dimension calculation on the transformed test matrix and the test matrix to obtain a feature dimension;

[0068] S315, determining the greatest common divisor of the feature dimension and the column dimension of the test matrix as the sampling feature value.

[0069] The expression of the feature dimension calculation is:

[0070]

[0071] Wherein, ω1 and ω2 are preset weighting factors, M and N are the row dimension and column dimension of the transformed test matrix respectively, μ and γ are the rank value and norm value of the test matrix respectively, D i represents the i-th dimension factor, D is the feature dimension, A ij and B ij are the elements of the i-th row and j-th column of the transformed test matrix and test matrix respectively, represents the down rounding of min(D i ).

[0072] The expression of the feature dimension calculation comprehensively considers multiple factors such as the rank value, the norm value of the test matrix, and the relationship between the corresponding elements of the transformed test matrix and the test matrix. The tan(μ / γ) reflects the interaction of the rank value and the norm value, the arcsin(A ij / B ij embodies the proportional relationship of the matrix elements before and after transformation, and the exp(-|R ij -T ijThe difference degree between elements is considered, so that the characteristics of data are fully captured, and the calculated characteristic dimension can more accurately reflect the internal structure of data. i The final characteristic dimension D is obtained by rounding down min(D

[0073] The test evaluation on each time period of the to-be-evaluated data subset is performed to obtain a sub-evaluation value of each time period, and the test evaluation on each time period of the to-be-evaluated data subset includes:

[0074] S331, for each time period, based on each performance index test data subset in the corresponding to-be-evaluated data subset, performing itemized performance evaluation processing to obtain an evaluation value and a weight value of each sub-system;

[0075] S332, using the weight value of each sub-system, performing weighted summation on the evaluation value of each sub-system to obtain a sub-evaluation value of each time period.

[0076] The test evaluation on each time period of the to-be-evaluated data subset is performed to obtain a sub-evaluation value of each time period, and the test evaluation on each time period of the to-be-evaluated data subset includes:

[0077] S3311, for each sub-system corresponding performance index test data subset in the to-be-evaluated data subset, obtaining a standard value of each performance index of the performance index test data subset;

[0078] S3312, using the test data sequence of each performance index of the performance index test data subset, respectively subtracting the standard value of the corresponding performance index to obtain a corresponding difference sequence;

[0079] S3313, respectively performing feature matrix transformation on each difference sequence of the performance index test data subset to obtain a corresponding feature matrix;

[0080] S3314, performing evaluation calculation on all feature matrices of the performance index test data subset to obtain an evaluation value and a weight value of the corresponding sub-system;

[0081] The expression of the feature matrix transformation is:

[0082]

[0083] Wherein, s(k) is the kth element of the difference sequence, NS is the length of the difference sequence, t(a, b) is the element of the a row and b column of the feature matrix, u() is the transform function, u(kT1-zT1) is the value of u() at kT1-zT1, T1 and F1 are the time domain transform length and the frequency domain transform length respectively;

[0084] The expression of the feature matrix transform can comprehensively capture the characteristics of the data in the time domain and the frequency domain by complex transform on the difference sequence. s(k) is the element of the difference sequence, and u(kT1-aT1) is the transform function, the value of which at different positions can mine the local characteristics of the data in the time domain, The frequency domain information is introduced, so that the transformed feature matrix can reflect the time domain and frequency domain characteristics of the data at the same time, providing more abundant information for subsequent evaluation calculation. The length NS of the difference sequence, and the time domain transform length and the frequency domain transform length are considered in the expression, which can adapt to the transform of difference sequences of different lengths. This makes the method have universality in processing test data of different performance indicators, and can effectively extract features regardless of the change of data length.

[0085] The transform function can be a Gaussian function.

[0086] The evaluation calculation on all the feature matrices of the performance indicator test data set is to obtain the evaluation value and the weight value of the corresponding sub-system, comprising:

[0087] For each feature matrix, the corresponding trace number and the mean of the variances of all row vectors are calculated;

[0088] The evaluation value and the weight value of the corresponding sub-system are obtained by calculating and processing all the feature matrices;

[0089] The calculation expression of the evaluation value and the weight value is:

[0090]

[0091] Wherein, L2() is the second order Legendre function, D i And The mean of the variances of all row vectors and the trace number of the ith feature matrix are respectively, M1 is the total number of the feature matrix corresponding to the sub-system, qz and fp are the weight value and the evaluation value of the corresponding sub-system respectively.

[0092] The mean of the variances of all row vectors is obtained by averaging the variances of all row vectors of each feature matrix.

[0093] The industrial park comprehensive management system comprises a personnel access management subsystem, a park tool management subsystem, an oil-electricity-water operation monitoring and storage consumption supply management subsystem and a central control software subsystem.

[0094] The personnel access management subsystem, the park tool management subsystem and the oil-electricity-water operation monitoring and storage consumption supply management subsystem each comprise a sensor and an upper computer; a corresponding management program runs in the upper computer;

[0095] The personnel access management subsystem, the park tool management subsystem and the oil-electricity-water operation monitoring and storage consumption supply management subsystem are connected with the central control software subsystem;

[0096] The central control software subsystem connection comprises a server and a control software running on the server.

[0097] The data cleaning processing comprises filling missing values, smoothing noise data, smoothing or deleting outlier points; the smoothing noise data is first obtained by identifying noise data, and then the noise data is smoothed according to the data before and after the noise data; the noise data is a value less than the detection sensitivity of the sensor of the observation data or greater than the measurement upper limit of the sensor of the observation data. The outlier point can be identified by using the Kalman filter method. For the determination of the filling value of the missing value, the measurement values in a certain sampling interval before and after the missing value can be averaged.

[0098] The time alignment processing can be realized by using a time registration processing algorithm; the time registration processing is to unify different types of data to the same time reference; the time registration processing can use the interpolation method, the Lagrange three-point interpolation method, etc.

[0099] The category inspection processing is to check whether each data in the data set is consistent with the preset data type, and to delete the inconsistent data from the data set.

[0100] The credibility discrimination processing of the third data set to obtain the to-be-evaluated data set comprises:

[0101] S241, for each data attribute of the third data set, the data acquisition time of the data is taken as the independent variable, and the data value of the data is taken as the dependent variable, and an autoregressive-moving average modeling is performed to obtain a first approximation model of the data attribute;

[0102] S242, using all information sequences of the information sequence set of each data attribute as a row vector, an information matrix of the data attribute is constructed;

[0103] S243, singular value calculation processing is carried out on the information matrix, and a singular value sequence is obtained;

[0104] S244, the element value of the singular value sequence is taken as a known dependent variable, and the element sequence number of the singular value sequence is taken as a known independent variable, and a to-be-approximated curve is constructed by using the known independent variable and the known dependent variable; the to-be-approximated curve is subjected to polynomial fitting, and a second approximation model of the data attribute is obtained.

[0105] S245, the second approximation model and the first approximation model are multiplied to obtain a fusion test model of the data attribute;

[0106] S246, the data acquisition time of the data of each data attribute is calculated by using the fusion test model of the data attribute, and an approximate dependent variable is obtained.

[0107] S247, whether the absolute value of the difference between the approximate dependent variable and the corresponding data is greater than a first regression discrimination threshold value is discriminated; if greater than the first regression discrimination threshold value, the data is deleted from the third data set, and if less than or equal to the first regression discrimination threshold value, the data is not processed.

[0108] S248, the data after S246 to S247 of the third data set is fused to obtain a to-be-evaluated data set.

[0109] The second aspect of the present application discloses a test evaluation device of an industrial park comprehensive management system, the device comprises:

[0110] A memory storing executable program codes;

[0111] A processor coupled with the memory;

[0112] The processor calls the executable program codes stored in the memory to execute the test evaluation method of the industrial park comprehensive management system.

[0113] The third aspect of the present application discloses a computer storage medium, the computer storage medium stores computer instructions, and the computer instructions are used to execute the test evaluation method of the industrial park comprehensive management system when called by a computer.

[0114] The fourth aspect of the present application discloses an information data processing terminal, which is used to realize the test evaluation method of the industrial park comprehensive management system.

[0115] The foregoing is merely an embodiment of the present invention and is not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A test and evaluation method for an industrial park integrated management system, characterized in that: include: S1, collects the performance indicator data set of the industrial park integrated management system; The performance indicator data set includes a performance indicator test data subset for each subsystem; The performance indicator test data subset includes a test data sequence for each performance indicator; S2, pre-processing the performance indicator data set to obtain a data set to be evaluated; S3, performing test evaluation on the data set to be evaluated to obtain a performance evaluation result value of the industrial park integrated management system.

2. The test and evaluation method for the industrial park integrated management system according to claim 1, characterized in that: The pre-processing of the performance indicator data set to obtain the data set to be evaluated includes: S21, performing data cleaning processing on the performance indicator data set to obtain a first data set; S22, performing time alignment processing on the first data set to obtain a second data set; S23, performing category checking processing on the second data set to obtain a third data set; S24: Perform credibility determination processing on the third data set to obtain a data set to be evaluated.

3. The test and evaluation method for the industrial park integrated management system according to claim 1, characterized in that: The test and evaluation process is performed on the data set to be evaluated to obtain a performance evaluation result value of the industrial park integrated management system, including: S31, performing statistical feature analysis on the data set to be evaluated to obtain sampling feature values; S32, evenly dividing the data set to be evaluated based on the sampled characteristic values ​​to obtain subsets of the data to be evaluated in several time periods; S33, performing test evaluation on the subset of data to be evaluated in each time period to obtain a sub-evaluation value for each time period; S34, performing integrated evaluation on the sub-evaluation values ​​of all time periods to obtain a performance evaluation result value of the industrial park comprehensive management system.

4. The test and evaluation method for the industrial park integrated management system according to claim 3, characterized in that: The performing statistical feature analysis on the data set to be evaluated to obtain sampling feature values ​​includes: S311, constructing a test matrix using the test data sequence of each performance indicator of the data set to be evaluated as a row vector; S312, calculating and obtaining the rank value and norm value of the test matrix; S313, performing a Demon transformation on each row vector of the test matrix to obtain a corresponding transformation vector; and constructing a transformation test matrix using all the transformation vectors; S314, performing characteristic dimension calculation on the transformed test matrix and the test matrix to obtain characteristic dimension; S315 , determining the greatest common divisor of the feature dimension and the column dimension of the test matrix as the sampling eigenvalue.

5. The test and evaluation method for the industrial park integrated management system according to claim 4, characterized in that: The expression for calculating the feature dimension is: Wherein, ω1 and ω2 are preset weighting factors, M and N are the row dimension and column dimension of the transformation test matrix respectively, μ and γ are the rank value and norm value of the test matrix respectively, D i represents the i-th dimension factor, D is the feature dimension, A ij and B ij are the elements of the i-th row and j-th column of the transformation test matrix and the test matrix, respectively, Indicates min(D i ) is rounded down.

6. The test and evaluation method for the industrial park integrated management system according to claim 3, characterized in that: The test evaluation of the subset of data to be evaluated in each time period to obtain the sub-evaluation value of each time period includes: S331, for each time period, based on each performance indicator test data subset in the corresponding data subset to be evaluated, perform sub-item performance evaluation processing to obtain the evaluation value and weight value of each subsystem; S332: Using the weight value of each subsystem, perform weighted summation on the evaluation value of each subsystem to obtain a sub-evaluation value for each time period.

7. The test and evaluation method for the industrial park integrated management system according to claim 6, characterized in that: The method of performing item-by-item performance evaluation based on each performance indicator test data subset in the data subset to be evaluated to obtain an evaluation value and a weight value for each subsystem includes: S3311, obtaining a standard value of each performance indicator of a performance indicator test data subset corresponding to each subsystem in the data subset to be evaluated; S3312, using the test data sequence of each performance indicator in the performance indicator test data diversity set, respectively subtracting the standard value of the corresponding performance indicator to obtain a corresponding difference sequence; S3313, performing a characteristic matrix transformation on each difference sequence of the performance index test data diversity set to obtain a corresponding characteristic matrix; S3314: Evaluate and calculate all characteristic matrices of the performance index test data diversity set to obtain evaluation values ​​and weight values ​​of corresponding subsystems.

8. A test and evaluation device for an industrial park integrated management system, characterized in that: The device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the test and evaluation method for the industrial park integrated management system according to any one of claims 1 to 7.

9. A computer storable medium, characterized in that The computer storable medium stores computer instructions, and when the computer instructions are called by a computer, they are used to execute the test and evaluation method for the industrial park integrated management system according to any one of claims 1 to 7.

10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the test and evaluation method of the industrial park integrated management system as described in any one of claims 1 to 7.

Images