Intelligent operation and maintenance system of digital laboratory based on internet of things and ai

Abstract

The present application relates to the technical field of maintenance operation management, in particular to a digital laboratory intelligent operation and maintenance system based on Internet of Things and AI dual drive, which comprises: a device state sensing module, which is used for collecting real-time power readings and rated power parameters of intelligent power meters connected to refrigerators and centrifuges, and calculating energy consumption and wear efficiency ratio values. In the present application, the energy efficiency decay and hidden wear of the device in the incomplete shutdown state are identified, and energy waste and sudden failure risks in the sub-health state are avoided. By traversing the connection flow relationship between the sample pretreatment unit and the downstream analytical instrument, the device associated blocking accumulation effect value is calculated and generated, the isolated device state is placed in the topology network of the overall experimental process for weighted operation, the chain blocking influence of single point failure on upstream and downstream sample flow is quantified, and the maintenance resources are preferentially inclined to the key node with the greatest influence on global flux.

Description

Technical Field

[0001] This invention relates to the field of maintenance, repair, operation and management technology, and in particular to a digital intelligent laboratory operation and maintenance system based on the dual engines of the Internet of Things and AI. Background Technology

[0002] Maintenance, repair, and operation management technology involves monitoring, maintaining, repairing, and optimizing the operation of physical assets, production equipment, and infrastructure throughout their entire lifecycle to ensure the continuity, security, and efficiency of core business processes.

[0003] Existing maintenance and operation management technologies often rely on fixed time cycles for preventative maintenance or reactive repairs after equipment experiences substantial functional failure. This management model struggles to detect early signs of gradual equipment performance degradation, leading to equipment operating in a state of high energy consumption and low efficiency for extended periods. This not only results in continuous energy waste but also increases the risk of experimental samples being damaged by environmental fluctuations. When dealing with complex laboratory equipment networks, current technologies typically treat each piece of equipment as an independent entity for status assessment, lacking a comprehensive analysis of upstream and downstream dependencies and sample flow. This can easily lead to over-maintenance of non-critical path equipment while neglecting critical bottleneck nodes, resulting in localized failures causing widespread congestion in experimental processes and sample accumulation. Therefore, improvements are needed. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies and propose a digital intelligent laboratory operation and maintenance system based on the dual engines of IoT and AI.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: a digital intelligent laboratory operation and maintenance system based on the dual engines of IoT and AI includes:

[0006] The equipment status sensing module is used to collect real-time power readings and rated power parameters of the smart power meters connected to refrigerators and centrifuges, and to calculate the energy consumption and wear efficiency ratio.

[0007] The impact propagation analysis module is used to traverse the connection flow relationship between the sample pretreatment unit and the downstream analytical instrument based on the energy consumption and wear efficiency ratio value, statistically generate the equipment-related blockage and accumulation effect value, and calculate the energy consumption and wear efficiency ratio value and the equipment-related blockage and accumulation effect value to generate the laboratory global maintenance impact factor.

[0008] The maintenance value assessment module is used to divide the laboratory's overall maintenance impact factor by the spare parts delivery time obtained from the external supply chain system, generate a spare parts response weighted maintenance urgency, calculate the difference between the expected electricity cost savings after maintenance and the cost of the required repair materials, and calculate the energy efficiency optimized maintenance investment return value in combination with the spare parts response weighted maintenance urgency.

[0009] The response decision scheduling module is used to sort the energy efficiency optimization maintenance investment return values ​​in descending order, match the corresponding laboratory equipment codes, generate a laboratory intelligent operation and maintenance response sequence table, extract the first-ranked equipment item in the laboratory intelligent operation and maintenance response sequence table, retrieve the corresponding emergency standby machine scheduling plan, and generate a hierarchical maintenance execution work order.

[0010] Preferably, the step of obtaining the energy consumption and wear efficiency ratio is as follows:

[0011] Based on the real-time power readings and rated power parameters of the smart power meters of refrigerators and centrifuges, they are synchronized and paired according to the device number and timestamp, power signal missing points and outlier points are eliminated, the difference ratio between the real-time power reading and the rated power parameter is calculated and arranged in chronological order to generate a power difference ratio sequence.

[0012] Based on the power difference ratio sequence, the RMS sequence of vibration velocity effective values ​​within the same time period is extracted from the IoT vibration sensor using the timestamp as the matching index. Sensor interference segments and signal drift segments are filtered out to generate a power difference ratio and vibration velocity effective value pairing sequence.

[0013] The energy consumption and wear efficiency ratio is calculated based on the pairing sequence of the power difference ratio and the effective value of vibration velocity.

[0014] Preferably, the step of obtaining the device-related blocking accumulation effect value is as follows:

[0015] Target equipment whose energy consumption and wear efficiency ratio exceeds the shutdown threshold is screened, the connection flow between the sample preprocessing unit and the downstream analytical instrument is traversed, and a connection flow relationship topology matrix and a shutdown target equipment unit indicator vector are generated based on the equipment port mapping to form a connection flow relationship topology matrix and a shutdown target equipment unit indicator vector.

[0016] Based on the connection flow relationship topology matrix and the shutdown target equipment unit indication vector, calculate the equipment-related obstruction and accumulation effect value.

[0017] Preferably, the steps for obtaining the laboratory global maintenance impact factor are as follows:

[0018] The energy consumption and wear efficiency ratio calculated for each target device and the associated resistance and accumulation effect value of the device are normalized to the minimum and maximum values ​​within the set of all candidate devices. The normalized values ​​are then synthesized to generate the laboratory global maintenance impact factor.

[0019] Preferably, the step of obtaining the weighted maintenance urgency of the spare parts response is as follows:

[0020] Based on the laboratory global maintenance impact factor, the spare parts arrival time field of the external supply chain system is called, and the two fields are aligned according to the equipment code and the unified time benchmark to generate a pairing list of laboratory global maintenance impact factor and spare parts arrival time.

[0021] Based on the pairing list of laboratory global maintenance impact factor and spare parts delivery time, records with spare parts delivery time of zero are removed and the decimal places of spare parts delivery time are standardized. For each device, the laboratory global maintenance impact factor is multiplied by the spare parts delivery time to calculate a single value and the device code is marked to generate a spare parts response weighted maintenance urgency.

[0022] Preferably, the steps for obtaining the return on investment for energy efficiency optimization and maintenance are as follows:

[0023] Based on the weighted maintenance urgency of the spare parts response, the estimated electricity cost savings after maintenance and the cost of required repair materials are aggregated. The difference between the estimated electricity cost savings and the cost of required repair materials is calculated according to the equipment code. The basic return on investment is then calculated by dividing the difference by the cost of required repair materials. The basic return on investment is then multiplied by the corresponding weighted maintenance urgency of the spare parts response to generate an energy-efficient optimized maintenance return on investment value.

[0024] Preferably, the steps for obtaining the laboratory intelligent operation and maintenance response sequence list are as follows:

[0025] The records of energy efficiency optimization and maintenance investment return values ​​are internally linked with the laboratory equipment code directory based on the equipment code field. Missing records of energy efficiency optimization and maintenance investment return values ​​are cleaned up. The records are sorted in descending order by energy efficiency optimization and maintenance investment return values, and the parallel items are sorted in lexicographical order by laboratory equipment code to generate a laboratory intelligent operation and maintenance response sequence table.

[0026] Preferably, the steps for obtaining the hierarchical maintenance execution work order are as follows:

[0027] Based on the laboratory intelligent operation and maintenance response sequence table, extract the first and most listed equipment item and read the corresponding laboratory equipment code. Call the emergency standby machine scheduling scheme index table to locate the record according to the laboratory equipment code and verify that the scheme status field is available. Merge the emergency standby machine model parameters and the switching step list to generate an emergency standby machine scheduling scheme.

[0028] According to the emergency standby machine scheduling scheme, the work unit data is filled in according to the laboratory equipment code and the work order priority is set as the first level of the laboratory intelligent operation and maintenance response sequence list. The switching operation sequence and maintenance inspection sequence are compiled and the list of responsible teams is listed. The switching step list of the emergency standby machine scheduling scheme is used to form a hierarchical maintenance execution work order.

[0029] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0030] In this invention, real-time power readings from intelligent power meters connected to refrigerators and centrifuges are collected and compared with rated power parameters to calculate energy consumption and wear efficiency ratios. This allows for the identification of energy efficiency degradation and hidden wear in equipment operating without complete shutdown, avoiding energy waste and the risk of sudden failures in sub-optimal operating conditions. By traversing the connection flow relationships between sample preprocessing units and downstream analytical instruments, the invention statistically generates equipment-related bottleneck accumulation effect values. Isolated equipment states are placed within the topological network of the overall experimental process for weighted calculations, quantifying the cascading bottleneck impact of single-point failures on upstream and downstream sample flow. This ensures that maintenance resources are prioritized for critical nodes with the greatest impact on overall throughput. Furthermore, by introducing spare parts arrival time data from external supply chain systems, a spare parts response-weighted maintenance urgency level is generated. This, combined with the difference between the expected electricity savings and repair material costs after maintenance, calculates the return on investment for energy efficiency optimization maintenance. This achieves a multi-dimensional integration of technological urgency, supply chain feasibility, and economic benefits, ensuring that the generated maintenance strategy aligns with logistical realities. Furthermore, it retrieves the emergency backup machine scheduling plan and generates hierarchical maintenance execution work orders, which can establish a response mechanism between the switching of old and new equipment and fault handling, reducing the duration of experimental interruptions caused by equipment downtime. Attached Figure Description

[0031] Figure 1 This is a system flowchart of the present invention. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0033] Please see Figure 1 This invention provides a technical solution: a digital intelligent laboratory operation and maintenance system based on the dual engines of IoT and AI, comprising:

[0034] The equipment status sensing module is used to collect real-time power readings and rated power parameters of the smart power meters connected to refrigerators and centrifuges, and to calculate the energy consumption and wear efficiency ratio.

[0035] The impact propagation analysis module is used to traverse the connection flow relationship between the sample pretreatment unit and the downstream analytical instrument based on the energy consumption and wear efficiency ratio value, statistically generate the equipment-related blockage and accumulation effect value, and calculate the energy consumption and wear efficiency ratio value and the equipment-related blockage and accumulation effect value to generate the laboratory global maintenance impact factor.

[0036] The maintenance value assessment module is used to divide the overall maintenance impact factor of the laboratory by the delivery time of spare parts obtained from the external supply chain system, generate the spare parts response weighted maintenance urgency, calculate the difference between the expected electricity cost savings after maintenance and the cost of the required repair materials, and calculate the return on investment of energy efficiency optimization maintenance in combination with the spare parts response weighted maintenance urgency.

[0037] The response decision scheduling module is used to sort the energy efficiency optimization and maintenance investment return values ​​in descending order, match the corresponding laboratory equipment codes, generate a laboratory intelligent operation and maintenance response sequence list, extract the first and first equipment item in the laboratory intelligent operation and maintenance response sequence list, retrieve the corresponding emergency standby machine scheduling plan, and generate a hierarchical maintenance execution work order.

[0038] The steps to obtain the energy consumption and wear efficiency ratio are as follows:

[0039] Based on the real-time power readings and rated power parameters of the smart power meters of refrigerators and centrifuges, they are synchronized and paired according to the device number and timestamp, power signal missing points and outlier points are eliminated, the difference ratio between the real-time power reading and the rated power parameter is calculated and arranged in chronological order to generate a power difference ratio sequence.

[0040] Based on the power difference ratio sequence, the RMS sequence of vibration velocity effective values ​​within the same time period is extracted from the IoT vibration sensor using the timestamp as the matching index. Sensor interference segments and signal drift segments are filtered out to generate a power difference ratio and vibration velocity effective value pairing sequence.

[0041] Based on the pairing sequence of power difference ratio and effective vibration velocity value, the energy consumption wear efficiency ratio is calculated using the following formula:

[0042] ;

[0043] in, This is the energy consumption and wear efficiency ratio value. For the first The power difference ratio at each time point is the ratio of the difference between the real-time power reading and the rated power parameter to the rated power parameter. For the first The effective value of vibration velocity at each time point represents the intensity of vibration energy. This represents the peak value of the maximum vibration velocity observed throughout the entire time series. This represents the total number of samples in the power difference ratio and vibration velocity effective value paired sequence.

[0044] Specifically, based on the intelligent power meter connecting the refrigerator and centrifuge, real-time power readings are acquired via RS485 or wireless communication protocols at a set sampling frequency (e.g., once per second). Simultaneously, the rated power parameters of the device are retrieved from the device nameplate or the device management database. The real-time power readings and rated power parameters are mapped according to the device's unique MAC address or asset number, and uniformly aligned to the millisecond-level timestamp of the network time protocol server. For the acquired raw power data stream, data cleaning is performed to identify and remove null values ​​(NaN) caused by communication packet loss and abnormal peak values ​​caused by circuit transient surges. The criteria for judging outliers are set as follows: when the power reading of a single point exceeds three times the standard deviation of the average of the five adjacent points, or when the power reading is negative, it is judged as an outlier. For the missing positions after removal, cubic spline interpolation is used to fit the theoretical power value at that moment using three normal data points before and after to fill in the gaps, maintaining the continuity of the time series. Subsequently, a difference ratio calculation logic is constructed to extract the cleaned real-time power readings at each time point. With rated power parameters Calculate the difference between the two and divide by the rated power parameter. The calculation expression is as follows: The calculation result reflects the degree of deviation of the equipment under the current load. A positive result indicates overload operation, while a negative result indicates low load operation. Finally, all the calculated time point difference ratios are indexed and arranged in ascending order of timestamps to form an ordered data set containing the time dimension, which is the generation of the power difference ratio sequence.

[0045] Based on the power difference ratio sequence generated in the preceding steps, the timestamp list contained therein is read as the primary key index. A data request is initiated through the IoT gateway to the piezoelectric vibration sensor installed on the compressor or motor housing of the device, retrieving the original waveform data of vibration acceleration within that time period. The original waveform data is then converted into vibration velocity data through time-domain integration. The root mean square (RMS) value is calculated according to a set time window (e.g., a 1-second window synchronized with the power sampling frequency), thereby extracting the effective value sequence of vibration velocity representing the vibration energy intensity. Before data pairing, the vibration data needs to undergo quality control to filter out sensor interference segments and signal drift segments. The identification criteria for interference segments are: the kurtosis index of the detected vibration signal. If the kurtosis value within a certain time window is greater than a preset impact threshold (e.g., an empirical value of 5.0, which is obtained by artificially applying a mechanical impact of known intensity to the device while it is stationary and recording the result), the interference segment is identified. (Based on statistical analysis of response data), if the duration of the high-frequency signal is less than 0.1 seconds, it is determined to be external impact interference and is removed. The identification criteria for signal drift segments are as follows: the signal is low-pass filtered to extract the trend term. If the monotonic change of the trend term within 1 minute exceeds 20% of the baseline (the average vibration value when the equipment is running stably under no-load), it is determined to be sensor temperature drift or zero-point drift. Polynomial fitting is required to remove the trend term for correction. After cleaning and correction, the closest effective vibration velocity (RMS) data point is searched within the allowable time deviation range (e.g., ±50 milliseconds) using the timestamp of the power difference ratio sequence as the benchmark. The two are matched one by one. If the corresponding vibration data cannot be matched at a certain time point, the power data at that time point is discarded to ensure strict synchronization of the two sets of data in the time dimension. Finally, the aligned data rows are merged to generate a power difference ratio and effective vibration velocity pairing sequence.

[0046] In the formula for calculating the energy consumption wear efficiency ratio, the wear efficiency of the equipment under non-ideal working conditions is quantified by combining the deviation of power fluctuations with the energy intensity of mechanical vibration. The first part of the formula uses a weighted structure similar to the correlation coefficient to evaluate the coupling degree between power anomalies (whether overload or underload, taking the absolute value) and vibration intensity, that is, whether high-intensity vibration is also present when the power deviation is large. The second part of the formula calculates the crest factor, that is, the ratio of the vibration peak value to the effective value, which is used to capture the impact characteristics in the vibration signal.

[0047] The total number of samples in the paired sequences of power difference ratio and effective vibration velocity value is obtained by counting the total number of data rows in the paired sequences generated in the preceding steps. It is a dimensionless integer value. In practical applications, a complete operating cycle or a fixed time period (e.g., 10 minutes) of equipment operation is typically selected as the observation window. If the sampling frequency is 1Hz, then... The value of is 600. This parameter is used to balance the influence of sample size in the calculation of the mean and weighting process, ensuring that the calculation results will not be biased by orders of magnitude due to the length of observation time. It is a basic dimension of statistical calculation.

[0048] For the first The power difference ratio at each time point represents the ratio of the difference between the real-time power reading and the rated power parameter to the rated power parameter. This parameter is a dimensionless floating-point number, expressed by the formula... The calculation yielded, where It is the first Real-time power (unit: watts) collected at each time point. This refers to the rated power of the equipment (unit: watts). For example, a refrigerator has a rated power of 500W. If the real-time power collected at any given time is 550W, then... This indicates that the power deviates from the rated value by 10% at this time, and the absolute value is taken. The parameter is used in the calculation to focus on the magnitude of the deviation rather than its direction; it directly quantifies the degree of abnormality in the electrical input.

[0049] For the first The effective value of vibration velocity at the nth time point represents the intensity of vibration energy, with units of millimeters per second (mm / s). This parameter is obtained by integrating the acceleration signal collected by the vibration sensor and calculating the root mean square (RMS). The specific acquisition steps are as follows: collect the effective value of vibration velocity at the nth time point. Within a time window Discrete vibration velocity data points The calculation formula is: This value reflects the device's state at a given time. The average vibration intensity.

[0050] The maximum vibration velocity peak observed throughout the entire time series is expressed in millimeters per second (mm / s). This parameter is within the current observation period (i.e., The maximum instantaneous absolute value of the vibration velocity signal in each sample is obtained by traversing the vibration waveform data throughout the entire time period and extracting the maximum absolute value. It reflects the strongest mechanical impact or transient oscillation that the equipment suffers during operation.

[0051] Calculations based on parameters:

[0052] There were a total of 5 sample points during the observation period, namely .

[0053] After data collection and calculation, the absolute value sequence of power difference ratios was obtained. (Dimensionless) is: [0.1, 0.2, 0.05, 0.3, 0.15].

[0054] The corresponding effective value sequence of vibration velocity (Unit: mm / s) is: [2.0, 4.0, 1.0, 8.0, 3.0].

[0055] Vibration peak detected throughout the observation period .

[0056] The first step is to calculate the weighted sum of the numerators. :

[0057] ;

[0058] ;

[0059] Multiply by the number of samples :

[0060] ;

[0061] The second step is to calculate the sum of the terms in the denominator:

[0062] (dimensionless);

[0063] ;

[0064] Product of denominators: ;

[0065] The third step is to calculate the left half of the formula (coupling coefficient):

[0066] ;

[0067] Step 4: Calculate the right half of the formula (peak factor term):

[0068] First calculate The root mean square value (denominator):

[0069] The sequence is: [4.0, 16.0, 1.0, 64.0, 9.0];

[0070] ;

[0071] Mean: ;

[0072] Square root: ;

[0073] Calculate the ratio of the right half:

[0074] ;

[0075] The fifth step is to calculate the final energy consumption and wear efficiency ratio. :

[0076] ;

[0077] The result shows that the calculated energy consumption-wear efficiency ratio is... The value is 3.746, which comprehensively reflects the severity of mechanical wear of the equipment under deviations in unit energy consumption. A higher value indicates that the equipment experiences high-intensity vibration energy during abnormal power fluctuations, and the vibration pattern has significant impact (high crest factor). If the health threshold is set to 2.5 (determined through statistical regression analysis of historical fault data), the current result of 3.746 significantly exceeds the threshold, indicating that there may be severe mechanical loosening or bearing pitting inside the equipment, leading to increased physical structural damage while consuming additional electrical energy. It is recommended that the system immediately trigger a red maintenance alarm.

[0078] The steps for obtaining the equipment-related hindrance accumulation effect value are as follows:

[0079] Screen target equipment whose energy consumption and wear efficiency ratio exceeds the shutdown threshold, traverse the connection flow between the sample pretreatment unit and the downstream analytical instrument, and generate a connection flow relationship topology matrix and a shutdown target equipment unit indicator vector based on the equipment port mapping.

[0080] Based on the topology matrix of connection flow direction and the unit indication vector of the shutdown target equipment, the equipment-related obstruction and accumulation effect value is calculated using the following formula:

[0081] ;

[0082] in, This represents the equipment-related resistance and accumulation effect value. Let be the node importance weight vector, where the _i_th ... element Indicates the first The importance of each piece of equipment is calculated based on its output throughput, uptime, and maintenance priority. The propagation attenuation factor is used to represent how the influence intensity decreases proportionally with each increase in path length. To connect the topological matrix of flow directions, the elements in the matrix... Indicates the first The device for the first The direct connection relationship between the devices. For matrix The transpose of is used to represent a reverse join. This is an upper bound on the path length, defined as the maximum order reachable in the topological matrix. For path order index, Topology matrix representing connection flow relationship The The power reflects the signal passing through the target device. The degree of indirect impact on downstream nodes after the first-level path. For the first Each device's unit indicator vector represents the position of the target device in the matrix.

[0083] Specifically, based on the energy consumption and wear efficiency ratio calculated above, a downtime threshold based on historical statistics is set. This threshold is determined by retrieving the peak energy consumption efficiency ratio data of all similar equipment in the laboratory over the past three years before downtime due to malfunction, calculating the 95th quantile of its distribution as a baseline. For example, if the calculated baseline value is 4.2, equipment exceeding this value is considered a high-risk target. Subsequently, a full-network topology scan is initiated, traversing the physical connections and logical data flows between sample pretreatment units (including cap openers, centrifuges, etc.) and downstream analytical instruments (including biochemical analyzers, immunoassay analyzers, etc.), using a depth-first search (DFS) algorithm. The device port mapping table in the LIMS system is parsed to identify the "output-input" relationship between each pair of devices, and a directed graph of laboratory equipment is constructed. Based on this, a connection flow relationship topology matrix is ​​generated. This matrix is ​​an N-order square matrix (N is the total number of devices). If device A has a sample flow to device B, the corresponding position in the matrix is ​​marked as 1; otherwise, it is marked as 0. At the same time, for each identified target device, a shutdown target device unit indicator vector is generated. This vector has a length of N and is set to 1 only at the index position corresponding to the target device, and 0 at the other positions. It is used to locate the fault source point in subsequent matrix operations. Finally, the connection flow relationship topology matrix and the shutdown target device unit indicator vector are summarized and output.

[0084] The formula for calculating the equipment-related blocking and accumulation effect simulates the bidirectional propagation process of faults in complex networks. Capture forward logistics disruptions (i.e., no samples available downstream). By capturing reverse logistics accumulation (i.e. upstream samples cannot be sent out), and quantifying the comprehensive obstruction pressure caused by the shutdown of the target equipment to other high-value nodes in the entire network through weighted summation, the local failure risk is mapped to the global maintenance urgency.

[0085] Let be the node importance weight vector, with dimension . , No. element Indicates the first To ensure consistency in measurement, the comprehensive business value of each device must undergo rigorous normalization processing. The steps are as follows: Collect three raw data items: output throughput. (Sample / hour), historical utilization rate (%), Maintenance Priority (Integers from 1 to 5), perform maximum-min normalization on these three data points across the entire range of laboratory equipment, and similarly obtain... and Finally, a weighted formula is used for synthesis: The weights of 0.5, 0.3, and 0.2 here are set based on the laboratory's "efficiency-first" operational strategy to ensure... It is a dimensionless value between 0 and 1.

[0086] The propagation attenuation factor, a dimensionless coefficient between 0 and 1, is used to simulate the physical law that the impact of a fault decreases with increasing network distance. This parameter is set based on: simulating a single-point outage in a simulation environment and observing the growth rate of the queue length of first-order and second-order adjacent nodes. If the growth rate of the first-order node is 100% and that of the second-order node is 60%, then this parameter is set... The value is usually between 0.5 and 0.7.

[0087] To connect the topological matrix of flow directions, binary matrix, elements This indicates the existence of a device. To the equipment The direct sample flow direction, this matrix directly maps the physical connection relationship, and is dimensionless.

[0088] For matrix The transpose of the element In mathematics, it represents a reverse connection; in physics, it is used to calculate the "back pressure" or "cumulative effect" of a fault on an upstream node.

[0089] This is the upper bound of the path length, an integer representing the maximum number of stages for calculating the cascading effect. It is typically set based on the average cascading length of a laboratory production line; for example, if the longest production line contains 5 devices, then... Set to 3 or 4 to ignore minor effects that are too far away.

[0090] For the path order index, summation variable, from 1 to... Calculate the first-order direct effects and the second-order indirect effects, respectively.

[0091] Representation matrix of Power, element Indicates from arrive The length is The number of paths, used here to quantify the impact pathways of multiple downstream stages.

[0092] For the first Unit indicator vector of each device, dimension Only the first Each element is 1, used to extract the target device during matrix operations. Related column vectors.

[0093] Calculations based on parameters:

[0094] Building a 3-node network: Device 1 Equipment 2 Equipment 3.

[0095] The target device is device 2 (intermediate node). ).

[0096] Parameter preparation:

[0097] After normalizing the throughput of all network devices, for example, device 1 (sampling). Equipment 2 (Centrifuge) Equipment 3 (Analysis) ,but .

[0098] Topological matrix (1 in a row, 2 in a row, 3 in a row).

[0099] transpose matrix .

[0100] Let the attenuation factor be... Upper bound of the path .

[0101] Target vector .

[0102] Matrix summation operation ( ):

[0103] .

[0104] Extract the target column:

[0105] .

[0106] The first element in the result vector is 1, indicating that the shutdown of device 2 directly blocked the upstream device 1 (because...). The function of the third element is 1, indicating that the shutdown of device 2 directly cuts off the downstream device 3 (because...). (its function).

[0107] Weighted assessment:

[0108] .

[0109] .

[0110] Calculated equipment-related hindrance stacking effect value The score is 1.3, which clearly indicates that device 2, as the central node, will cause a failure that simultaneously impacts upstream device 1 (importance 0.6) and downstream device 3 (importance 0.7), resulting in a cumulative importance loss of 1.3 units across the entire network. Compared to another edge device (such as device 0, which only connects to device 1 and has a weight of 0.5), its... The value may be only 0.5 (affecting only downstream device 1), so the value of 1.3 reveals the critical position of device 2 in the topology. The system should list it as a priority maintenance target to prevent a single point of failure from spreading into a line-wide failure.

[0111] The steps for obtaining the laboratory's overall maintenance impact factor are as follows:

[0112] The energy consumption and wear efficiency ratio values ​​and the equipment-related hindrance and accumulation effect values ​​calculated for each target equipment are normalized to the minimum and maximum values ​​within the set of all candidate equipment. The normalized values ​​are then synthesized to generate the laboratory global maintenance impact factor.

[0113] Specifically, the energy consumption and wear efficiency ratio values ​​calculated according to the aforementioned steps (denoted as...) The associated resistance and accumulation effect value of the equipment (denoted as) Before performing global synthesis, the differences in numerical distribution between the two need to be eliminated. All candidate devices within the current maintenance cycle are traversed, and energy efficiency ratio sets are constructed for each device. With the set of blocking effect values Extract their respective maximum values. and minimum value Apply the minimum-maximum normalization formula Each device Value and Values ​​are all mapped to The dimensionless interval is used to ensure that the two indicators are comparable on the same order of magnitude. Then, composite weights are defined; for example, the weight of the device health dimension is set to 0.4, and the weight of the network influence dimension is set to 0.6. The two normalized indicators are then linearly weighted and summed according to these weights. Ultimately, a laboratory-wide maintenance impact factor is generated for each piece of equipment, which serves as the sorting basis for generating maintenance work orders.

[0114] The steps for obtaining the weighted maintenance urgency of spare parts response are as follows:

[0115] Based on the laboratory's overall maintenance impact factor, the spare parts arrival time field of the external supply chain system is called, and the two fields are aligned according to the equipment code and the unified time benchmark to generate a pairing list of laboratory overall maintenance impact factor and spare parts arrival time.

[0116] Based on the pairing list of laboratory global maintenance impact factors and spare parts delivery time, records with spare parts delivery time of zero are removed and the decimal places of spare parts delivery time are standardized. For each device, the laboratory global maintenance impact factor is multiplied by the spare parts delivery time to calculate the unit value and the device code is marked to generate the spare parts response weighted maintenance urgency.

[0117] Specifically, based on the laboratory's global maintenance impact factors, an application programming interface (API) connection is established with the external supply chain management system (SCM). A query request containing the current equipment model and a list of faulty spare parts is sent to obtain the spare parts inventory status and estimated delivery time (in hours) fields in the feedback data packet. Using the equipment code in the laboratory equipment management database as the primary key, the logistics information of the corresponding spare parts is parsed from the SCM feedback data to ensure that each maintenance impact factor record can find the corresponding supply chain response data. If a piece of equipment involves multiple spare parts, the longest delivery time is selected as the final delivery time parameter for that equipment to reflect the actual situation of maintenance activities being constrained by the bottleneck effect. Subsequently, the generation time of the maintenance impact factors and the acquisition time of the supply chain data are calibrated according to the unified Network Time Protocol (NTP) timestamp to ensure that the two reflect the operation and maintenance status under the same time. Outdated data with a time deviation of more than 1 hour is removed. Finally, the two sets of cleaned data are merged line by line according to the equipment code to generate a pairing list of laboratory global maintenance impact factors and spare parts delivery times.

[0118] Based on the pairing list of laboratory-wide maintenance impact factors and spare parts delivery times, each record in the list is iterated through. The spare parts delivery time field is checked, and records with a value of zero are directly removed (usually indicating missing data or system errors). For valid records, considering that spare parts delivery times are typically in hours or days and may contain decimals (e.g., 1.5 days), they are uniformly converted to hours and rounded to one decimal place. For example, 1.5 days is converted to 36.0 hours. Then, a spare parts response weighting calculation logic is defined, and the corresponding laboratory-wide maintenance impact factor (denoted as...) is extracted for each device. ) and the standardized spare parts delivery time (denoted as The product of the two is calculated as an indicator of the urgency of the equipment's operation and maintenance. The calculation formula is as follows: ,in The weighted maintenance urgency for spare parts response is calculated, reflecting the coupling relationship between risk and response time: even if the impact factor of equipment failure is high, if spare parts can arrive promptly ( If the urgency is relatively low, then the overall urgency is relatively controllable; conversely, if high-impact factor equipment faces a long lead time (…), then the overall urgency is relatively manageable. If the urgency level is relatively high, then the calculated urgency level is magnified exponentially, and the final result will be... The value is marked in the corresponding device record to generate a weighted maintenance urgency level for spare parts response.

[0119] The steps to obtain the return on investment for energy efficiency optimization and maintenance are as follows:

[0120] Based on the weighted maintenance urgency of spare parts response, the estimated electricity cost savings after maintenance and the cost of required repair materials are aggregated. The difference between the estimated electricity cost savings and the cost of required repair materials is calculated according to the equipment code. The basic return on investment is calculated by dividing the difference by the cost of required repair materials. The basic return on investment is then multiplied by the corresponding spare parts response weighted maintenance urgency to generate the energy efficiency optimized maintenance return on investment value.

[0121] Specifically, based on the weighted maintenance urgency of spare parts response, the financial management module is queried to obtain the expected energy efficiency improvement data for each piece of equipment after maintenance and repair. Combined with the local industrial electricity price (e.g., 0.8 yuan / kWh), the estimated electricity cost savings due to energy efficiency restoration within a future maintenance cycle (e.g., 365 days) are calculated (denoted as...). Simultaneously, retrieve the Bill of Materials (BOM) for repair, add up the purchase price of all replacement parts and labor service costs, and calculate the required cost of repair materials (denoted as...). Perform the difference calculation according to the device code: The difference This reflects the net financial return, followed by the calculation of the underlying rate of return on investment. This ratio quantifies the energy efficiency benefit multiple generated by a unit maintenance investment. To incorporate the urgency of maintenance into decision-making, the basic return on investment is further weighted with the spare parts response calculated above to determine the maintenance urgency. To perform a product operation, that is... ,in The system calculates the final energy efficiency optimization maintenance return on investment. The higher the value, the more economical the maintenance of the equipment will be, and the more urgent the maintenance bottleneck will be. Based on this, the system prioritizes all equipment to be maintained and generates the energy efficiency optimization maintenance return on investment.

[0122] The steps for obtaining the laboratory intelligent operation and maintenance response sequence list are as follows:

[0123] The records of energy efficiency optimization and maintenance investment return values ​​are internally linked with the laboratory equipment code directory based on the equipment code field. Missing records of energy efficiency optimization and maintenance investment return values ​​are cleaned up. The records are sorted in descending order by energy efficiency optimization and maintenance investment return values ​​and the parallel items are sorted in lexicographical order by laboratory equipment code. A laboratory intelligent operation and maintenance response sequence table is generated.

[0124] Specifically, an inner join is performed between the records of energy efficiency optimization and maintenance investment return values ​​and the laboratory equipment code directory based on the equipment code field. Using a hash join strategy in a relational database engine, the "equipment code" is used as the hash key to construct an in-memory hash table for efficient matching of the two datasets. Each joined record is traversed, and a rigorous data cleaning operation is performed on the "energy efficiency optimization and maintenance investment return value" field, removing all records marked as NULL, NaN (not a number), or negative infinity values ​​resulting from calculation errors, ensuring that all data participating in the sorting has actual physical meaning. Subsequently, a multi-level sorting logic is initiated, first setting "energy efficiency optimization and maintenance investment return value" as the primary sorting key and employing the Quick Sort algorithm. The `Sort` function sorts the entire dataset in descending order, placing the equipment with the highest return on investment (ROI) at the top of the list, reflecting a "efficiency-first" operation and maintenance strategy. To address the possibility of identical values ​​in the sorting process, the "laboratory equipment code" is introduced as a secondary sorting key, and the equipment is sorted in ascending order according to the ASCII code table. For example, when two devices both have an ROI of 12.5, the device with the code "L-01" will be placed before "L-02". This deterministic sorting rule eliminates the influence of randomness on the operation and maintenance order. Each item in the list is assigned a unique integer index that increments from 1. The final output is a structured dataset containing the equipment code, ROI value, and sorting index, generating a laboratory intelligent operation and maintenance response sequence list.

[0125] The steps for obtaining hierarchical maintenance work orders are as follows:

[0126] Based on the laboratory intelligent operation and maintenance response sequence list, extract the first and most listed equipment item and read the corresponding laboratory equipment code. Call the emergency standby machine scheduling scheme index table to locate the record according to the laboratory equipment code and verify that the scheme status field is available. Merge the emergency standby machine model parameters and the switching step list to generate an emergency standby machine scheduling scheme.

[0127] Based on the emergency standby machine scheduling plan, the work unit data is filled in according to the laboratory equipment code and the work order priority is set as the first level of the laboratory intelligent operation and maintenance response sequence list. The switching operation sequence and maintenance inspection sequence are compiled and the list of responsible teams is listed. The switching step list of the emergency standby machine scheduling plan is used to form a hierarchical maintenance execution work order.

[0128] Specifically, based on the laboratory intelligent operation and maintenance response sequence table, the first record in the list is accessed directly through the index pointer. The "laboratory equipment code" corresponding to this record is extracted as the core retrieval key. The emergency standby machine scheduling scheme index table stored in the configuration database is then called. This index table is a key-value pair structure that maps the relationship between the primary equipment and the standby resources. A binary search method is used to quickly locate the corresponding configuration record in the index table. The "scheme status" field in the record is read and compared with the predefined enumerated value "Status_Ready" (indicating readiness and availability). If the status value does not match (e.g., displayed as "Status_Maintenance" or...), the system will process the query. If the status is "Status_Occupied", the system will automatically redirect to query the second-best backup machine or trigger a stockout alarm. After confirming that the status verification is successful, the system will read the static attribute data of the backup machine from the records, including the equipment model, rated power, interface type and storage location coordinates. At the same time, based on the "Operation Process ID" field in the records, the system will retrieve the corresponding structured text data from the Standard Operating Procedure (SOP) library, which includes detailed shutdown and locking steps, pipeline disconnection steps, backup machine connection steps and initialization and debugging parameters. These scattered attribute data and process texts will be serialized and merged to construct a JSON format data packet containing complete scheduling instructions, and an emergency backup machine scheduling plan will be generated.

[0129] Based on the emergency standby machine scheduling plan, a new maintenance work order object is instantiated. The JSON content in the plan data packet is parsed, and the code of the primary device, the model of the standby machine, and the location coordinates of the fault are automatically mapped and filled into the "metadata" part of the work order. According to the first position of the device in the response sequence table, the "urgency" attribute of the work order is directly assigned to the highest level defined by the system (e.g., "P0 level - immediate response"). Then, the time planning stage begins. The preset standard working time parameters in the plan are read (e.g., 30 minutes for switching and 15 minutes for self-test). Using the work order generation time as the base point (T0), the time addition operation is used to deduce the various key parameters. Based on the estimated completion time of key nodes, a switching operation sequence and maintenance inspection sequence including "T0+30min to complete physical switching" and "T0+45min to complete functional verification" are compiled. Then, the scheduling management system is accessed through the API interface. According to the skill tags required by the work order (such as "centrifuge repair" and "high voltage electrician"), the skill certificates of the current on-duty personnel are matched to filter out the list of qualified and currently available technicians, and add them to the "responsible team" field of the work order. Finally, the standard operating procedure (SOP) text referenced in the solution is directly embedded into the execution description area of ​​the work order for maintenance personnel to refer to on-site, forming a hierarchical maintenance execution work order.

Claims

1. A digital and intelligent laboratory operation and maintenance system based on the dual engines of IoT and AI, characterized in that: The system includes: The equipment status sensing module is used to collect real-time power readings and rated power parameters of the smart power meters connected to refrigerators and centrifuges, and to calculate the energy consumption and wear efficiency ratio. The impact propagation analysis module is used to traverse the connection flow relationship between the sample pretreatment unit and the downstream analytical instrument based on the energy consumption and wear efficiency ratio value, statistically generate the equipment-related blockage and accumulation effect value, and calculate the energy consumption and wear efficiency ratio value and the equipment-related blockage and accumulation effect value to generate the laboratory global maintenance impact factor. The maintenance value assessment module is used to multiply the laboratory's global maintenance impact factor by the spare parts delivery time obtained from the external supply chain system to generate a spare parts response weighted maintenance urgency, calculate the difference between the expected electricity cost savings after maintenance and the cost of the required repair materials, and calculate the energy efficiency optimized maintenance investment return value in combination with the spare parts response weighted maintenance urgency. The response decision scheduling module is used to sort the energy efficiency optimization maintenance investment return value in descending order, match the corresponding laboratory equipment code, generate a laboratory intelligent operation and maintenance response sequence table, extract the first and first equipment item in the laboratory intelligent operation and maintenance response sequence table, retrieve the corresponding emergency standby machine scheduling plan, and generate a hierarchical maintenance execution work order. The steps for obtaining the energy consumption and wear efficiency ratio are as follows: Based on the real-time power readings and rated power parameters of the smart power meters of refrigerators and centrifuges, they are synchronized and paired according to the device number and timestamp, power signal missing points and outlier points are eliminated, the difference ratio between the real-time power reading and the rated power parameter is calculated and arranged in chronological order to generate a power difference ratio sequence. Based on the power difference ratio sequence, the RMS sequence of vibration velocity values ​​within the same time period is extracted from the IoT vibration sensor using the timestamp as the matching index. Sensor interference segments and signal drift segments are filtered out to generate a power difference ratio and vibration velocity RMS pairing sequence. The energy consumption wear efficiency ratio is calculated based on the pairing sequence of the power difference ratio and the effective value of vibration velocity. The steps for obtaining the device-related hindrance and accumulation effect value are as follows: Target equipment whose energy consumption and wear efficiency ratio exceeds the shutdown threshold is screened, the connection flow between the sample preprocessing unit and the downstream analytical instrument is traversed, and a connection flow relationship topology matrix and a shutdown target equipment unit indicator vector are generated based on the equipment port mapping to form a connection flow relationship topology matrix and a shutdown target equipment unit indicator vector. Based on the connection flow relationship topology matrix and the shutdown target equipment unit indication vector, calculate the equipment-related obstruction and accumulation effect value.

2. The intelligent laboratory operation and maintenance system based on IoT and AI dual engines as described in claim 1, characterized in that, The steps for obtaining the global maintenance impact factor of the laboratory are as follows: The energy consumption and wear efficiency ratio values ​​calculated for each target device and the associated resistance and accumulation effect values ​​of the device are normalized to the minimum and maximum values ​​within the set of all candidate devices. The normalized values ​​are then synthesized to generate the laboratory global maintenance impact factor.

3. The intelligent laboratory operation and maintenance system based on IoT and AI dual engines as described in claim 1, characterized in that, The steps for obtaining the weighted maintenance urgency of the spare parts response are as follows: Based on the laboratory global maintenance impact factor, the spare parts arrival time field of the external supply chain system is called, and the two fields are aligned according to the equipment code and the unified time benchmark to generate a pairing list of laboratory global maintenance impact factor and spare parts arrival time. Based on the pairing list of laboratory global maintenance impact factor and spare parts delivery time, records with spare parts delivery time of zero are removed and the decimal places of spare parts delivery time are standardized. For each device, the laboratory global maintenance impact factor is multiplied by the spare parts delivery time to calculate a single value and the device code is marked to generate a spare parts response weighted maintenance urgency.

4. The intelligent laboratory operation and maintenance system based on IoT and AI dual engines as described in claim 1, characterized in that, The steps for obtaining the return on investment for energy efficiency optimization and maintenance are as follows: Based on the weighted maintenance urgency of the spare parts response, the estimated electricity cost savings after maintenance and the cost of required repair materials are aggregated. The difference between the estimated electricity cost savings and the cost of required repair materials is calculated according to the equipment code. The basic return on investment is then calculated by dividing the difference by the cost of required repair materials. The basic return on investment is then multiplied by the corresponding weighted maintenance urgency of the spare parts response to generate an energy-efficient optimized maintenance return on investment value.

5. The intelligent laboratory operation and maintenance system based on IoT and AI dual engines as described in claim 1, characterized in that, The steps for obtaining the laboratory intelligent operation and maintenance response sequence list are as follows: The records of energy efficiency optimization and maintenance investment return values ​​are internally linked with the laboratory equipment code directory based on the equipment code field. Missing records of energy efficiency optimization and maintenance investment return values ​​are cleaned up. The records are sorted in descending order by energy efficiency optimization and maintenance investment return values, and the parallel items are sorted in lexicographical order by laboratory equipment code to generate a laboratory intelligent operation and maintenance response sequence table.

6. The intelligent laboratory operation and maintenance system based on IoT and AI dual engines as described in claim 1, characterized in that, The steps for obtaining the hierarchical maintenance execution work order are as follows: Based on the laboratory intelligent operation and maintenance response sequence table, extract the first and second equipment item and read the corresponding laboratory equipment code. Call the emergency standby machine scheduling scheme index table to locate the record according to the laboratory equipment code and verify that the scheme status field is available. Merge the emergency standby machine model parameters and the switching step list to generate an emergency standby machine scheduling scheme. According to the emergency standby machine scheduling scheme, the work unit data is filled in according to the laboratory equipment code and the work order priority is set as the first level of the laboratory intelligent operation and maintenance response sequence list. The switching operation sequence and maintenance inspection sequence are compiled and the list of responsible teams is listed. The switching step list of the emergency standby machine scheduling scheme is used to form a hierarchical maintenance execution work order.

Images