Campus equipment operation and maintenance management and control platform based on intelligent control

Abstract

The invention discloses a campus equipment operation and maintenance management and control platform based on intelligent control. The platform comprises a detection module, an abnormity analysis module and a fault positioning processing module. The detection module constructs a risk vector and a cobweb coordinate system, and starts a balanced or centralized detection mode according to the cobweb area and the axial value dispersion; the anomaly analysis module judges abnormal components and marks priorities by constructing a component data matrix, analyzing a time sequence and the like; the fault positioning processing module calculates abnormal component correlation, generates a fault feature cluster, matches fault types and sorts and processes a priority sequence; according to the platform, the problems of missing multi-dimensional risk analysis, extensive fault positioning and the like in traditional operation and maintenance are solved, accurate assessment and grading detection of equipment risks, accurate judgment of abnormal components and topological positioning and scientific scheduling of faults are realized, the accuracy and efficiency of campus equipment operation and maintenance are improved, and safe and efficient operation of equipment is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of campus equipment management, and in particular relates to a campus equipment operation and maintenance management and control platform based on intelligent control. Background Art

[0002] As campus equipment becomes more intelligent, the operation and maintenance of equipment such as air conditioners and elevators face challenges such as the dispersion of multi-parameter monitoring data and the lack of systematic risk assessment. Traditional single-point threshold alarm methods are unable to capture the linkage effects of multi-dimensional risks such as abnormal operation and accumulated load pressure, resulting in delayed fault location and blind allocation of maintenance resources, which cannot meet the needs of safe and efficient equipment operation.

[0003] Existing technologies have three core flaws in campus equipment operation and maintenance:

[0004] Insufficient multi-dimensional risk linkage analysis: The correlation between different risk vectors cannot be quantified, making it difficult to identify potential systemic failures and resulting in a lack of accuracy in comprehensive risk assessments.

[0005] The fault location mechanism is crude: the single parameter threshold judgment is susceptible to noise interference and lacks topological clustering analysis of abnormal components, resulting in insufficient accuracy in locating composite faults.

[0006] Operation and maintenance decisions lack quantitative priorities: A priority system that integrates risk transmission paths and maintenance efficiency has not been established, resulting in blind scheduling of maintenance resources and delayed response to high-risk faults. To this end, we propose a campus equipment operation and maintenance management and control platform based on intelligent control. Summary of the Invention

[0007] The purpose of the present invention is to provide a campus equipment operation and maintenance management platform based on intelligent control to solve the problems raised in the above background technology.

[0008] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a campus equipment operation and maintenance management platform based on intelligent control, comprising: a detection module, an abnormality analysis module and a fault location processing module;

[0009] Detection module: Constructs risk vectors for campus operation and maintenance equipment, sets detection cycles and analyzes risk vector values ​​at each detection moment, constructs a spider web coordinate system to generate an operation and maintenance spider web diagram, and activates corresponding detection modes based on the spider web area and axis value dispersion;

[0010] Anomaly Analysis Module: Monitors each risk vector based on the priority sequence corresponding to the detection mode; obtains the value of each component in the risk vector during the detection period, constructs a component data matrix and calculates the vector component threshold; determines the abnormal difference and the total number of abnormalities by analyzing the component time series and adjacent difference series; calculates the component priority value; and after determining the abnormal component, integrates and labels the priority value;

[0011] Fault location processing module: Calculates the correlation coefficient of any two abnormal components, retains the component pairs whose absolute correlation values ​​meet the threshold and converts them into connecting edges of an undirected graph, and uses a fully connected clustering algorithm to generate fault feature clusters; constructs a mapping table between fault feature clusters and fault types, substitutes the current feature cluster into the mapping table to match the fault type, calculates the processing priority value corresponding to each fault type, sorts them into a priority sequence, and sends them to the operation and maintenance terminal.

[0012] Preferably, the specific process of constructing a spider web coordinate system to generate an operation and maintenance spider web diagram is as follows:

[0013] Obtain equipment on campus that requires operation, maintenance, and control. Build a risk vector for each device. The risk vectors include: operational anomaly risk vector, load pressure accumulation vector, environmental erosion risk vector, maintenance hazard accumulation vector, and lifespan degradation risk vector.

[0014] Each risk vector contains several vector components. A detection period is set to obtain the values ​​of the vector components at each detection moment within the detection period.

[0015] According to the logical relationship between the vector components and the corresponding risk vectors, they are divided into positive correlation components and negative correlation components. After normalizing each vector component, the formula is used: Obtain a risk vector value V; wherein Xi is the number of the positive correlation component; i = 1, 2, ..., m; m is the total number of positive correlation components; yg is the number of the negative correlation component; g = 1, 2, ..., k; k is the total number of negative correlation components; ai and bg are the preset weight coefficients assigned to each positive correlation component and negative correlation component respectively;

[0016] Taking the geometric center of the plane as the origin, five directional axes are evenly distributed along the circumference. Each directional axis corresponds to a risk vector, and a spider web coordinate system is constructed. For each detection moment, the numerical values ​​of the risk vectors corresponding to the detection moment are normalized and mapped to the corresponding directional axis of the spider web coordinate system to obtain the corresponding numerical points. Adjacent data points are connected in sequence in a clockwise direction to obtain the operation and maintenance spider web diagram.

[0017] Preferably, the specific process of starting the corresponding detection mode according to the spider web area and the axis value dispersion is:

[0018] Calculate the area of ​​the operation and maintenance spider web graph at the current detection moment to obtain the spider web area ZS; at the same time, calculate the standard deviation of the five direction axis values ​​in the operation and maintenance spider web graph to obtain the axis value dispersion ZL;

[0019] Set the spider web area threshold SY and the axis value dispersion threshold LY;

[0020] If the detection time ZS ≥ SY and ZL < LY, start the balance detection mode, and perform detections on each direction axis in sequence according to the balance priority sequence;

[0021] The process of constructing the balance priority sequence is as follows:

[0022] For each direction axis in the operation and maintenance spider web diagram, analyze the correlation coefficient between the current direction axis and the other direction axes; and perform mean calculation to obtain the axis average correlation degree XG;

[0023] If the value of the direction axis is greater than or equal to the corresponding threshold, it is recorded as the direction axis being abnormal. Count the number of times the direction axis is abnormal at the monitoring time within the current cycle, and record it as the abnormal detection count; by dividing the abnormal detection count by the total number of detection times up to the current time within the current cycle, obtain the abnormal risk rate FG;

[0024] Obtain the risk vector value V corresponding to each detection time up to the current time within the current detection cycle; use the formula: Obtain the risk growth rate FZ; where s is the label of the detection time, t = 1, 2,..., T; T is the total number of detection times that have occurred within the current detection cycle up to the current time;

[0025] After normalizing the axis average correlation degree XG, abnormal risk rate FG, and risk growth rate FZ, use the formula: P 均衡 = XY × w1 + FG × w2 + FZ × w3 to obtain the balance priority value P 均衡 ; where w1, w2, and w3 are preset weight coefficients;

[0026] Sort the risk vectors corresponding to each direction axis according to the balance priority value to obtain the balance priority sequence.

[0027] Preferably, if the detection time ZS ≥ SY and ZL ≥ LY, start the centralized detection mode; and perform detections on each direction axis according to the centralized priority sequence;

[0028] The process of constructing the centralized priority sequence is as follows:

[0029] For each direction axis in the operation and maintenance spider web diagram, count the number of times the historical direction axis is abnormal and the number of times equipment failures are caused after the direction axis is abnormal; and by dividing the number of times equipment failures are caused after the historical direction axis is abnormal by the number of times the historical direction axis is abnormal, obtain the failure triggering rate GY;

[0030] Calculate the average value of the duration of each fault operation and repair after the direction axis abnormality causes a failure to obtain the average repair duration XF;

[0031] By dividing the current value of the direction axis by the corresponding reference value, obtain the axis base ratio ZB;

[0032] After normalizing the failure initiation rate GY, the average repair time XF and the axis-to-base ratio ZB, the formula is used: 集中 =GY×f1+XF×f2+ZB×f3, get the centralized priority value P 集中 , where f1, f2, and f3 are preset weight coefficients;

[0033] The centralized priority sequence is obtained by sorting the risk vectors corresponding to each direction axis according to the centralized priority value.

[0034] Preferably, the analysis process of the adjacent difference sequence is:

[0035] For each risk vector, obtain the values ​​of each vector component in the risk vector at each detection time in this cycle up to the current detection time;

[0036] Construct the component data matrix: Where T is the total number of detection moments that occurred in the current detection cycle up to the current moment; n is the total number of components in the risk vector;

[0037] For each vector component, read the historical normal data statistics, namely: mean μd,j and standard deviation σd,j; use the formula: dth,j = μd,j + 3σd,j to obtain the vector component threshold dth,j; where j is the index of the vector component, j = 1, 2, ..., n;

[0038] For each vector component, extract the value of the vector component at all times to obtain the component time series: Xj = [x1, j, x2, j, ... xT, j];

[0039] Calculate the numerical difference between adjacent moments: dt,j = |xt,jx(t-1),j|, and obtain the component adjacent difference sequence: Dj = [d2,j, d3,j, ... dT,j]; where the length is T-1;

[0040] Get the mean of the difference series The specific calculation process is:

[0041] Preferably, the specific process of determining the abnormal difference and the total number of abnormal times and calculating the component priority value is as follows:

[0042] For each vector component, obtain the aggregation degree Cj of the vector component time series. The specific calculation process is: Where exp is the symbol of the natural exponential function. The smaller the degree of aggregation, the more dispersed the data is and the higher the probability of abnormality.

[0043] Extract the differences that exceed the threshold of the corresponding vector component from the component adjacent difference sequence: Dj = [d2, j, d3, j, ... dT, j] and mark them as abnormal differences; calculate the sum of abnormal differences to obtain the abnormal difference sum YZj; and count the total number of abnormal differences to obtain the abnormal number sum YCj;

[0044] Using the formula: Obtain the component priority value FYj; where max(Dj) represents the maximum adjacent difference value selected from the component adjacent difference sequence; PV is the priority value of the risk vector corresponding to the vector component; q1 and q2 are preset weight coefficients.

[0045] Preferably, the specific process of integrating and marking the priority values ​​after determining the abnormal components is as follows:

[0046] For each vector component, if one of the following conditions is met, it is determined to be an abnormal component:

[0047] The adjacent differences of H consecutive components: dt,j ≥ dth,j; where H is the preset number of times;

[0048] Total number of exceptions:

[0049] All abnormal components are collected, integrated, and marked with corresponding component priority values ​​before being sent to the fault location allocation module.

[0050] Preferably, the specific process of generating the fault feature cluster is:

[0051] Extract the time series of all abnormal components in the current detection period and standardize each component series;

[0052] The Pearson correlation coefficient method is used to calculate the correlation coefficient of any two abnormal components. A correlation coefficient threshold is preset, and abnormal component pairs whose absolute correlation values ​​reach the correlation coefficient threshold are retained. These abnormal component pairs are converted into connecting edges in an undirected graph, with each abnormal component as a node in the graph.

[0053] Using the fully connected clustering algorithm, each abnormal component is initially treated as a cluster, and then the maximum correlation between all cluster pairs is calculated; the cluster pairs whose maximum correlation reaches the correlation coefficient threshold are merged;

[0054] When any cluster pair is merged, it is ensured that the correlation of all abnormal component pairs in the new cluster is not lower than the correlation coefficient threshold, or when there is no cluster pair that can be merged, clustering is stopped and several fault feature clusters are formed.

[0055] Preferably, the specific process of calculating the processing priority value corresponding to each fault type, sorting it into a priority sequence and sending it to the operation and maintenance terminal is as follows:

[0056] Construct a mapping table of fault feature clusters and campus equipment fault types; then substitute the fault feature clusters found in this detection into the mapping table of fault feature clusters and campus equipment fault types for matching, and output the corresponding fault type;

[0057] For each fault type that occurs, the priority values ​​corresponding to each abnormal component of the fault feature cluster corresponding to the fault type are averaged to obtain the fault type processing priority value;

[0058] Sort all the fault types that occur on campus equipment according to the corresponding fault type processing priority values ​​to obtain a fault type processing priority sequence;

[0059] The fault type processing priority sequence corresponding to the campus equipment is sent to the operation and maintenance terminal. The operation and maintenance terminal dispatch staff will handle each fault type of the campus equipment in turn according to the fault type processing priority sequence.

[0060] Compared with the prior art, the present invention has the following beneficial effects:

[0061] (1) This campus equipment operation and maintenance management platform based on intelligent control, by constructing a spider web coordinate system containing various risk vectors, converts the equipment status into a visual spider web diagram, judges whether the equipment has abnormal risks through the spider web area and axis value dispersion, and dynamically starts balanced detection or centralized detection mode according to the risk distribution characteristics; the balanced mode identifies the risk transmission hub through parameters such as axis correlation and abnormal risk rate, and blocks the multi-dimensional risk linkage; the centralized mode locks the single-point high-risk axis based on the fault initiation rate and repair time, realizes the precise deployment of detection resources, and improves the comprehensiveness of equipment risk assessment and the adaptability of detection strategy.

[0062] (2) This campus equipment operation and maintenance management platform based on intelligent control can accurately identify abnormal fluctuations by constructing a component data matrix, calculating vector component thresholds, and combining component time series with adjacent difference series analysis; introducing aggregation calculation to quantify the degree of data dispersion, combining the abnormal difference sum, abnormal number of times and continuous abnormal conditions, and determining abnormal components in multiple dimensions; fusing the difference sequence characteristics with the corresponding risk vector priority value, calculating the component priority value and marking it, providing a reliable basis for subsequent fault location, and improving the accuracy of anomaly detection and the scientific nature of priority assessment.

[0063] (3) This is a campus equipment operation and maintenance management platform based on intelligent control. It uses the Pearson correlation coefficient to screen highly correlated abnormal component pairs, constructs an undirected graph, and generates fault feature clusters through full-connection clustering to ensure the homology of component faults within the cluster; it realizes fault type matching based on the fault feature cluster and fault type mapping table, generates a fault type processing priority sequence through mean calculation, and drives the operation and maintenance terminal to dispatch orders according to priority; this mechanism realizes topological positioning from abnormal components to fault types and scientific scheduling of operation and maintenance decisions, thereby improving fault location accuracy and maintenance resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 It is a flowchart of the present invention. DETAILED DESCRIPTION

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0066] Example 1

[0067] See also Figure 1 ,The present invention provides a campus equipment operation and maintenance management platform based on intelligent control, including: a detection module, an abnormality analysis module and a fault location processing module;

[0068] The detection module constructs risk vectors for campus operation and maintenance equipment, sets detection cycles, analyzes the risk vector values ​​at each detection moment, constructs a spider web coordinate system to generate an operation and maintenance spider web diagram, and activates different detection modes based on the spider web area and axis value dispersion to achieve accurate assessment and graded detection of equipment risks. The specific process is as follows:

[0069] Obtain equipment on campus that requires operation, maintenance, and control. Build a risk vector for each device. The risk vectors include: operational anomaly risk vector, load pressure accumulation vector, environmental erosion risk vector, maintenance hazard accumulation vector, and lifespan degradation risk vector.

[0070] Abnormal operation risk vectors include: current harmonic distortion rate, vibration phase difference constants in different parts of the equipment, speed fluctuation rate exceeding the limit, etc.

[0071] The load pressure accumulation vector includes: load entropy value, peak load duration, number of load cycles within a certain period, overload ratio, etc.

[0072] Environmental erosion risk vectors include: environmental corrosiveness equivalent, electromagnetic interference intensity index, dust deposition rate, temperature and humidity fluctuation hazard value, etc.

[0073] The maintenance hidden danger accumulation vector includes: maintenance intervention complexity, fault recurrence risk index, maintenance plan lag rate, etc.;

[0074] The life attenuation risk vector includes: material microscopic damage degree, remaining life warning value, key component aging rate, etc.;

[0075] For each risk vector, there are several vector components contained; set the detection period, and obtain the values of the vector components at each detection moment within the detection period;

[0076] According to the logical relationship between the vector components and the corresponding risk vectors; divide them into positively correlated components and negatively correlated components; after normalizing each vector component, use the formula: Obtain the risk vector value V; where Xi is the number of the positively correlated component; i = 1, 2,..., m; m is the total number of positively correlated components; yg is the number of the negatively correlated component; g = 1, 2,..., k; k is the total number of negatively correlated components; ai and bg are the preset weight coefficients assigned to each positively correlated component and negatively correlated component respectively;

[0077] Taking the plane geometric center as the origin, evenly distribute five direction axes along the circumference, and each direction axis corresponds to a risk vector. Construct a cobweb coordinate system. For each detection moment, after normalizing the values of the corresponding risk vectors at this detection moment, map them to the corresponding direction axes in the cobweb coordinate system to obtain the corresponding numerical points. Connect the adjacent data points in the clockwise direction to obtain the operation and maintenance cobweb diagram;

[0078] Calculate the area of the operation and maintenance cobweb diagram at the current detection moment to obtain the cobweb area ZS; at the same time, calculate the standard deviation of the values of the five direction axes in the operation and maintenance cobweb diagram to obtain the axis value dispersion degree ZL;

[0079] Set the cobweb area threshold SY and the axis value dispersion degree threshold LY;

[0080] If ZS ≥ SY and ZL < LY at the detection moment, start the balanced detection mode, and perform detections on each direction axis in sequence according to the balanced priority sequence;

[0081] The process of constructing the balanced priority sequence is:

[0082] For each direction axis in the operation and maintenance cobweb diagram, use the Pearson correlation coefficient algorithm to analyze the correlation coefficient between the current direction axis and the other direction axes; and perform mean calculation to obtain the axis average correlation degree XG;

[0083] Set the numerical threshold for the direction axis. If the value of the direction axis is greater than or equal to the corresponding threshold, it is recorded as an abnormal direction axis. Count the number of times the direction axis is abnormal at the monitoring moment within the current cycle, which is recorded as the abnormal detection count. Divide the abnormal detection count by the total number of detection moments up to the current moment within the current cycle to obtain the abnormal risk rate FG.

[0084] Obtain the risk vector value V corresponding to each detection moment within the current detection cycle up to the current moment. Use the formula: to obtain the risk growth rate FZ; where s is the label of the detection moment, t = 1, 2,..., T; T is the total number of detection moments that have occurred within the current detection cycle up to the current moment.

[0085] After normalizing the axis average correlation degree XG, the abnormal risk rate FG, and the risk growth rate FZ, use the formula: P 均衡 = XG × w1 + FG × w2 + FZ × w3 to obtain the balanced priority value P 均衡 ; where w1, w2, and w3 are preset weight coefficients.

[0086] Sort the risk vectors corresponding to each direction axis according to the balanced priority value to obtain the balanced priority sequence.

[0087] It should be noted that if the detection moment ZS ≥ SY and ZL < LY, it means that the comprehensive risk of the equipment is high but the distribution is balanced, and the risks of each direction axis deteriorate synergistically, which may cause systemic hidden dangers due to equipment aging or environmental factors. Calculating the priority using the axis average correlation degree, abnormal risk rate, and risk growth rate can identify the risk conduction hub axis, lock the high-frequency abnormal direction axis, warn of the accelerating deterioration risk, and block the systemic failure from the risk network level.

[0088] If the detection moment ZS ≥ SY and ZL ≥ LY, start the centralized detection mode; and detect the vector components corresponding to each direction axis according to the centralized priority sequence.

[0089] The construction process of the centralized priority sequence is as follows:

[0090] For each direction axis in the operation and maintenance cobweb diagram, count the number of historical abnormal direction axes and the number of times of equipment failures caused after the direction axis is abnormal; and divide the number of times of equipment failures caused after the historical abnormal direction axis by the number of historical abnormal direction axes to obtain the failure initiation rate GY.

[0091] Calculate the average value of the repair duration for each equipment failure repair after the direction axis is abnormal to obtain the average repair duration XF.

[0092] Preset the reference value for the direction axis. Divide the current value of the direction axis by the corresponding reference value to obtain the axis base ratio ZB.

[0093] After normalizing the failure initiation rate GY, the average repair time XF and the axis-to-base ratio ZB, the formula is used: 集中 =GY×f1+XF×f2+ZB×f3, get the centralized priority value P 集中 , where f1, f2, and f3 are preset weight coefficients;

[0094] The centralized priority sequence is obtained by sorting the risk vectors corresponding to each direction axis according to the centralized priority value.

[0095] It should be noted that if the detection time ZS ≥ SY and ZL ≥ LY, it indicates that the overall risk of the equipment is high and concentrated in a certain directional axis. The single-point anomaly dominates the overall risk and is prone to causing cascading failures. Using the failure initiation rate, average repair time, and axis-to-axis ratio to calculate priority, we can accurately identify high-risk axes that deviate from the benchmark, optimize resources based on failure probability and repair efficiency, and curb the spread of failures at the level of single-point breakthroughs.

[0096] Based on two detection models and priority parameters, precise operation and maintenance can be achieved: the balanced mode locates systemic risk hubs through correlation, anomaly rate, and growth rate, blocking multi-dimensional risk linkage; the centralized mode uses fault initiation rate, repair time, and axis-to-axis ratio to lock single-point high-risk axes, and allocates resources according to the urgency of the risk; the combination of the two can greatly improve detection efficiency and ensure the safe and efficient operation of campus equipment.

[0097] The anomaly analysis module monitors each risk vector for campus equipment that executes the detection mode according to the priority sequence corresponding to the detection mode; obtains the value of each component in the risk vector during the detection cycle, constructs a component data matrix, and calculates the vector component threshold. By analyzing the component time series and adjacent difference series, it determines the abnormal difference and the total number of abnormalities, calculates the component priority value, and integrates and labels the abnormal components after determining the abnormal components. The specific process is as follows:

[0098] For campus equipment in detection mode, monitor each risk vector in the equipment operation and maintenance spider diagram in sequence according to the priority sequence corresponding to the detection mode enabled on the equipment. The specific process is as follows:

[0099] For each risk vector, obtain the values ​​of each vector component in the risk vector at each detection time in this cycle up to the current detection time;

[0100] Construct the component data matrix: Where T is the total number of detection moments that occurred in the current detection cycle up to the current moment; n is the total number of components in the risk vector;

[0101] For each vector component, read the historical normal data statistics, namely: mean μd,j and standard deviation σd,j; use the formula: dth,j = μd,j + 3σd,j to obtain the vector component threshold dth,j; where j is the index of the vector component, j = 1, 2, ..., n;

[0102] For each vector component, the following calculations are performed independently:

[0103] Extract the values ​​of the vector components at all times to obtain the component time series: Xj = [x1, j, x2, j, ... xT, j];

[0104] Calculate the numerical difference between adjacent moments: dt,j = |xt,jx(t-1),j|, and obtain the component adjacent difference sequence: Dj = [d2,j,d3,j,...dT,j]; where the length is T-1;

[0105] Get the mean of the difference series The specific calculation process is:

[0106] Get the aggregation degree Cj of the vector component time series. The specific calculation process is: Where exp is the symbol of the natural exponential function. The smaller the degree of aggregation, the more dispersed the data is and the higher the probability of abnormality.

[0107] Extract the differences that exceed the threshold of the corresponding vector component from the component adjacent difference sequence: Dj = [d2,j,d3,j,...dT,j] and mark them as abnormal differences; calculate the sum of abnormal differences to obtain the abnormal difference sum YZj; at the same time, count the total number of abnormal differences to obtain the abnormal number sum YCj;

[0108] Using the formula: Obtain the component priority value FYj; where max(Dj) represents the maximum adjacent difference value selected from the component adjacent difference sequence; PV is the priority value of the risk vector corresponding to the vector component; q1 and q2 are preset weight coefficients;

[0109] For each vector component, if one of the following conditions is met, it is determined to be an abnormal component:

[0110] The adjacent differences of H consecutive components: dt,j ≥ dth,j; where H is the preset number of times;

[0111] Total number of exceptions: (the number of abnormalities exceeds one-third of the detection time);

[0112] All abnormal components are collected, integrated, and marked with corresponding component priority values ​​before being sent to the fault location allocation module.

[0113] It should be noted that the above process can accurately identify abnormal fluctuations by constructing a component data matrix and calculating vector component thresholds based on historical normal data statistics. The analysis of component time series and adjacent difference series can capture the dynamic characteristics of data changes, and the concentration calculation can quantify the degree of data dispersion, providing a multi-dimensional basis for abnormality determination. The calculation of the sum of abnormal difference values ​​and the sum of abnormal times, combined with the condition of continuous abnormal times, can effectively distinguish between accidental fluctuations and real faults. The calculation of component priority values ​​combines the characteristics of the difference sequence with the corresponding risk vector priority value, making the priority assessment of abnormal components more comprehensive. This process achieves accurate determination and priority labeling of abnormal components, providing a reliable basis for subsequent fault location, improving the accuracy and efficiency of campus equipment operation and maintenance, and can timely discover potential equipment faults, avoid fault expansion, and ensure safe and efficient operation of equipment.

[0114] The fault location processing module calculates the correlation coefficient of any two abnormal components detected, retains the component pairs whose absolute correlation values ​​meet the threshold and converts them into connecting edges of an undirected graph, and uses a fully connected clustering algorithm to generate fault feature clusters. It then constructs a mapping table between fault feature clusters and fault types, substitutes the current feature cluster into the mapping table to match the fault type, calculates the processing priority value corresponding to each fault type, sorts the priority sequence, and sends it to the operation and maintenance terminal. The specific process is as follows:

[0115] Extract the time series of all abnormal components in the current detection period and standardize each component series;

[0116] The Pearson correlation coefficient method is used to calculate the correlation coefficient of any two abnormal components. A correlation coefficient threshold is preset, and abnormal component pairs whose absolute correlation values ​​reach the correlation coefficient threshold are retained. These abnormal component pairs are converted into connecting edges in an undirected graph, with each abnormal component as a node in the graph.

[0117] Using the fully connected clustering algorithm, each abnormal component is initially treated as a cluster, and then the maximum correlation between all cluster pairs is calculated; the cluster pairs whose maximum correlation reaches the correlation coefficient threshold are merged;

[0118] When any cluster pair is merged, it is ensured that the correlation of all abnormal component pairs in the new cluster is not less than the correlation coefficient threshold, or when there is no cluster pair that can be merged, clustering is stopped and several fault feature clusters are formed;

[0119] Construct a mapping table of fault feature clusters and campus equipment fault types; then substitute the fault feature clusters found in this detection into the mapping table of fault feature clusters and campus equipment fault types for matching, and output the corresponding fault type;

[0120] For each fault type that occurs, the priority values ​​corresponding to each abnormal component of the fault feature cluster corresponding to the fault type are averaged to obtain the fault type processing priority value;

[0121] Sort all the fault types that occur on campus equipment according to the corresponding fault type processing priority values ​​to obtain a fault type processing priority sequence;

[0122] The fault type processing priority sequence corresponding to the campus equipment is sent to the operation and maintenance terminal. The operation and maintenance terminal dispatch staff will handle each fault type of the campus equipment in turn according to the fault type processing priority sequence.

[0123] It should be noted that the Pearson correlation coefficient is used to quantify the linear correlation between abnormal components, and highly correlated component pairs are screened to construct an undirected graph, providing topological support for fully connected clustering; fully connected clustering uses the maximum correlation between clusters as the basis for merging to ensure strong correlation between components within the cluster, and the generated fault feature clusters can accurately reflect the homology of faults; mapping table matching realizes the transformation of feature clusters to fault types, and the fault type processing priority value is calculated and sorted by mean value to form a scientific processing priority sequence; this process realizes the precise positioning and priority sorting from abnormal components to fault types, provides a basis for the dispatch of operation and maintenance terminals, improves the efficiency and pertinence of campus equipment fault handling, and ensures the orderliness and effectiveness of equipment operation and maintenance.

[0124] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A campus equipment operation and maintenance management platform based on intelligent control, including: A detection module, an anomaly analysis module, and a fault location and handling module, characterized in that: The detection module: constructs a risk vector for campus operation and maintenance equipment, sets a detection period, analyzes the risk vector values at each detection moment, constructs a cobweb coordinate system to generate an operation and maintenance cobweb diagram, and starts corresponding detection modes based on the cobweb area and the axis value dispersion; The anomaly analysis module: monitors each risk vector according to the priority sequence corresponding to the detection mode; obtains the values of each component in the risk vector during the detection period, constructs a component data matrix, calculates the vector component threshold, determines the abnormal difference and the sum of abnormal times by analyzing the component time series and the adjacent difference series, calculates the component priority value, and integrates and marks the priority value after determining the abnormal component; The fault location and handling module: calculates the correlation coefficient between any two abnormal components, retains the component pairs whose absolute value of the correlation satisfies the threshold and converts them into the connection edges of an undirected graph, and uses a fully connected clustering algorithm to generate a fault feature cluster; constructs a mapping table between the fault feature cluster and the fault type, substitutes the current feature cluster into the mapping table to match the fault type, calculates the handling priority value corresponding to each fault type, sorts to form a priority sequence, and sends it to the operation and maintenance terminal.

2. The campus equipment operation and maintenance management platform based on intelligent control according to claim 1 is characterized by: The specific process of constructing a cobweb coordinate system to generate an operation and maintenance cobweb diagram is as follows: Obtain the equipment that needs to be operation and maintenance controlled on campus. For each type of equipment, construct a risk vector, which includes: an operation anomaly risk vector, a load pressure accumulation vector, an environmental erosion risk vector, a maintenance hidden danger accumulation vector, and a life attenuation risk vector; For each risk vector, it contains several vector components; set a detection period and obtain the values of the vector components at each detection moment during the detection period; According to the logical relationship between the vector components and the corresponding risk vectors, they are divided into positive correlation components and negative correlation components. After normalizing each vector component, the formula is used: Obtain a risk vector value V; wherein Xi is the number of the positive correlation component; i = 1, 2, ..., m; m is the total number of positive correlation components; yg is the number of the negative correlation component; g = 1, 2, ..., k; k is the total number of negative correlation components; ai and bg are the preset weight coefficients assigned to each positive correlation component and negative correlation component respectively; Take the plane geometric center as the origin, evenly distribute five direction axes along the circumference, each direction axis corresponds to a risk vector, construct a cobweb coordinate system, and after normalizing the risk vector values corresponding to each detection moment, map them to the corresponding direction axes in the cobweb coordinate system to obtain the corresponding numerical points, and connect the adjacent data points in a clockwise direction to obtain the operation and maintenance cobweb diagram.

3. The campus equipment operation and maintenance management platform based on intelligent control according to claim 2 is characterized by: The specific process of starting the corresponding detection mode based on the cobweb area and the axis value dispersion is as follows: Calculate the area of the operation and maintenance cobweb diagram at the current detection moment to obtain the cobweb area ZS; at the same time, calculate the standard deviation of the values of the five direction axes in the operation and maintenance cobweb diagram to obtain the axis value dispersion ZL; Set the cobweb area threshold SY and the axis value dispersion threshold LY; If at the detection moment ZS≥SY and ZL<LY, start the balanced detection mode, and detect each direction axis in turn according to the balanced priority sequence; The process of constructing the balanced priority sequence is as follows: For each direction axis in the operation and maintenance cobweb diagram, analyze the correlation coefficient between the current direction axis and the other direction axes; and perform a mean calculation to obtain the axis average correlation degree XG; If the value of the direction axis is greater than or equal to the corresponding threshold, it is recorded as the direction axis being abnormal, and count the number of times the direction axis is abnormal at the monitoring moment during the current period, which is recorded as the abnormal detection times; By dividing the abnormal detection times by the total number of detection moments up to the current moment during the current period, obtain the abnormal risk rate FG; Obtain the risk vector value V corresponding to each detection moment in the current detection cycle up to the current detection moment; use the formula: Get the risk growth rate FZ; Where s is the number of the detection moment, t = 1, 2, ..., T; T is the total number of detection moments that occurred in the current detection cycle up to the current moment; After normalizing the axis average correlation XG, abnormal risk rate FG and risk growth rate FZ, the formula is used: 均衡 =XG×w1+FG×w2+FZ×w3, and get the balanced priority value P 均衡 ;Where w1, w2, w3 are preset weight coefficients; The equilibrium priority sequence is obtained by sorting the risk vectors corresponding to each direction axis according to the equilibrium priority value.

4. The campus equipment operation and maintenance management platform based on intelligent control according to claim 3 is characterized by: If the detection time ZS≥SY and ZL≥LY, start the centralized detection mode; and perform detection on each direction axis according to the centralized priority sequence; The construction process of the centralized priority sequence is: For each directional axis in the operation and maintenance spider web diagram, count the number of historical directional axis anomalies and the number of equipment failures caused by directional axis anomalies. Then, divide the number of equipment failures caused by historical directional axis anomalies by the number of historical directional axis anomalies to obtain the failure initiation rate GY. Calculate the average repair time after the steering axis abnormality causes a fault, and get the average repair time XF; The axis-to-base ratio ZB is obtained by dividing the current direction axis value by the corresponding reference value; After normalizing the failure initiation rate GY, the average repair time XF and the axis-to-base ratio ZB, the formula is used: 集中 =GY×f1+XF×f2+ZB×f3, get the centralized priority value P 集中 , where f1, f2, and f3 are preset weight coefficients; The centralized priority sequence is obtained by sorting the risk vectors corresponding to each direction axis according to the centralized priority value.

5. The campus equipment operation and maintenance management platform based on intelligent control according to claim 4 is characterized by: The analysis process of adjacent difference sequences is: For each risk vector, obtain the values ​​of each vector component in the risk vector at each detection time in this cycle up to the current detection time, and construct a component data matrix; For each vector component, read the historical normal data statistics, namely: mean μd,j and standard deviation σd,j; use the formula: dth,j = μd,j + 3σd,j to obtain the vector component threshold dth,j; where j is the index of the vector component, j = 1, 2, ..., n; For each vector component, extract the value of the vector component in the component data matrix at all detection moments to obtain the component time series; Calculate the numerical difference between adjacent moments to obtain a sequence of component adjacent difference values; Calculate the mean of the adjacent difference sequence of the components to obtain the mean of the difference sequence 6. The campus equipment operation and maintenance management platform based on intelligent control according to claim 5 is characterized by: The specific process of determining the abnormal difference and the total number of abnormal times and calculating the component priority value is as follows: For each vector component, obtain the aggregation degree Cj of the vector component time series. The specific calculation process is: Where exp is the symbol of natural exponential function; Extract the differences that exceed the threshold of the corresponding vector component from the component adjacent difference sequence and mark them as abnormal differences; Calculate the total of abnormal differences to obtain the total abnormal difference value YZj; at the same time, count the total number of abnormal differences to obtain the total number of abnormal times YCj; Using the formula: Obtain the component priority value FYj; where max(Dj) represents the maximum adjacent difference value selected from the component adjacent difference sequence; PV is the priority value of the risk vector corresponding to the vector component; q1 and q2 are preset weight coefficients.

7. The campus equipment operation and maintenance management platform based on intelligent control according to claim 6 is characterized by: The specific process of integrating and marking the priority values ​​after determining the abnormal components is as follows: For each vector component, if one of the following conditions is met, it is determined to be an abnormal component: H consecutive component adjacent differences: dt,j ≥ dth,j; where H is the preset number of times, dt,j is the component adjacent difference; Total number of exceptions: All abnormal components are collected, integrated, and marked with corresponding component priority values ​​before being sent to the fault location allocation module.

8. The campus equipment operation and maintenance management platform based on intelligent control according to claim 7 is characterized by: The specific process of generating fault feature clusters is as follows: Extract the time series of all abnormal components in the current detection period and standardize each component series; The Pearson correlation coefficient method is used to calculate the correlation coefficient of any two abnormal components. A correlation coefficient threshold is preset, and abnormal component pairs whose absolute correlation values ​​reach the correlation coefficient threshold are retained. These abnormal component pairs are converted into connecting edges in an undirected graph, with each abnormal component as a node in the graph. The fully connected clustering algorithm is used. Initially, each abnormal component is treated as a cluster separately, and then the maximum correlation between all cluster pairs is calculated. The cluster pairs whose maximum correlation reaches the correlation coefficient threshold are merged; When any cluster pair is merged, it is ensured that the correlation of all abnormal component pairs in the new cluster is not lower than the correlation coefficient threshold, or when there is no cluster pair that can be merged, clustering is stopped and several fault feature clusters are formed.

9. The campus equipment operation and maintenance management platform based on intelligent control according to claim 8 is characterized by: The specific process of calculating the processing priority value corresponding to each fault type, sorting it into a priority sequence, and sending it to the operation and maintenance terminal is as follows: Construct a mapping table of fault feature clusters and campus equipment fault types; then substitute the fault feature clusters found in this detection into the mapping table of fault feature clusters and campus equipment fault types for matching, and output the corresponding fault type; For each fault type that occurs, the priority values ​​corresponding to each abnormal component of the fault feature cluster corresponding to the fault type are averaged to obtain the fault type processing priority value; Sort all the fault types that occur on campus equipment according to the corresponding fault type processing priority values ​​to obtain a fault type processing priority sequence; The fault type processing priority sequence corresponding to the campus equipment is sent to the operation and maintenance terminal. The operation and maintenance terminal dispatch staff will handle each fault type of the campus equipment in turn according to the fault type processing priority sequence.

Images