Boeing says problem with 737 MAX warning signal slipped through the cracks

Boeing says problem with 737 MAX warning signal slipped through the cracks

1:07pm, 6th May, 2019
Boeing’s first 737 MAX 9 jet makes its appearance at the company’s Renton plant in 2017. (Boeing Photo) Boeing says a warning alert system that figures in the investigation of two catastrophic 737 MAX crashes didn’t work the way it was supposed to because of a software flaw that engineers identified a year before the accidents. The revelation adds a new twist to the debate over the company’s safety practices. In this case, the debate focuses on a feature known as the “AOA Disagree” alert, which is supposed to light up in the cockpit if there’s a mismatch in data coming from two angle-of-attack sensors on the plane. Investigators suggest that bad sensor data played a key role in October’s Lion Air crash in Indonesia, which killed all 189 people aboard the plane; and March’s Ethiopian Airlines crash, which killed 157. Within days of the Ethiopian crash, all 737 MAX airplanes were grounded worldwide. Boeing engineers knew about a problem with the “AOA Disagree” alert well before that. The alert was originally intended to be a standard feature on the 737 MAX and the previous generation of 737 planes, known as the 737 NG (for “Next Generation”). But in a , Boeing said that in 2017, several months after deliveries began, engineers became aware that the 737 MAX display system software didn’t meet the original requirements. “The software delivered to Boeing linked the AOA Disagree alert to the AOA indicator, which is an optional feature on the MAX and the NG. Accordingly, the software activated the AOA Disagree alert only if an airline opted for the AOA indicator,” Boeing said. The company said it followed standard procedure for reviewing the issue, and determined that neither the software-based angle-of-attack indicator nor the alert was necessary for safe operation of the airplane. “Accordingly, the review concluded, the existing functionality was acceptable until the alert and the indicator could be delinked in the next planned display system software update,” Boeing said. “Senior company leadership was not involved in the review and first became aware of this issue in the aftermath of the Lion Air accident.” That’s when Boeing discussed the issue with the Federal Aviation Administration. About a week after the Indonesia crash, Boeing and the FAA issued bulletins noting that both the angle-of-attack indicator and the alert system were optional. Last December, Boeing conducted a follow-up internal safety review, which confirmed the view that the absence of a warning alert did not present a safety issue. The findings of that review were shared with the FAA, Boeing said. Three months after the review, the Ethiopian crash occurred. In the wake of that crash, Boeing has said the “AOA Disagree” issue will be fixed before the 737 MAX returns to flight. “Boeing is issuing a display system software update, to implement the AOA Disagree alert as a standard, standalone feature before the MAX returns to service,” the company said in its statement. “When the MAX returns to service, all MAX production aircraft will have an activated and operable AOA Disagree alert and an optional angle of attack indicator. All customers with previously delivered MAX airplanes will have the ability to activate the AOA Disagree alert.” The statement adds context to earlier reports that the angle-of-attack alert system was available only as part of an optional software package. It’s debatable whether either of the crashes could have been avoided if the alert was available as a standard feature on the planes involved. In the Ethiopian case, the investigation suggests that the pilots knew about the issue surrounding the angle-of-attack sensors and their effect on the 737 MAX’s automatic flight control system — but were nevertheless unable to pull the plane out of its final dive. In any case, the questions surrounding what Boeing engineers knew and when they knew it seem sure to figure in the multiple investigations sparked by the crashes. U.S. Rep. Rick Larsen, D-Wash., told KOMO News that the FAA’s actions before and after the crashes will also be examined during a May 15 hearing before the House Subcommittee on Aviation, which he chairs. ”We need to first find answers to ensure the safety of the airplane, to ensure the FAA is doing the right thing, that Boeing is doing the right thing, and that’ll be our focus,” Larsen told KOMO on Saturday, a day before Boeing issued its statement.
Univ. of Washington spinout takes on $5.2B scheduling problem with custom AI analytics

Univ. of Washington spinout takes on $5.2B scheduling problem with custom AI analytics

12:00pm, 9th May, 2018
(Bigstock Photo)stock Hospitals have to solve a thousand logistical challenges every day, but perhaps none are more difficult than operating room schedules. Surgeries can be difficult to predict — in fact, less than half of surgeries in the U.S. start and end on time. That can create chaos for patients and doctors, and costs hospitals $5.2 billion every year, according to University of Washington . The startup, which develops a variety of technologies for hospitals, is taking aim at the operating room problem with a new AI technology that uses data on patients and surgeons to more accurately predict how long each surgery will take. The startup recently deployed the technology at a large academic medical institution in Seattle. So far, it has cut the number of surgeries that run over their scheduled time by 20 percent, a result that could save a hospital $1 million a year in staff overtime alone. Perimatics Co-Founder and CEO Kalyani Velagapudi. (Perimatics Photo) The startup is still studying how its technology affects underage, or the number of surgeries that end before the predicted time, and other elements including patient and employee satisfaction. Perimatics’ algorithm begins by looking at a patient’s data and seeking out information that will affect how long the surgery takes, like the patient’s prior surgeries and their age. , Perimatics co-founder and CEO, told GeekWire that the surgeons themselves also have a big impact on how long a surgery takes. Each surgeon approaches an operation differently and will bring in various factors that affect the length of the operation. “That was a surprise,” said , Perimatics’ chief solutions architect and co-founder. “We had to build machine learning models customized for each surgeon.” The algorithm also takes into account the staff that will work on the procedure, like anesthesiologists. It can also suggest last-minute scheduling adjustments when operating rooms are needed for emergency procedures. Bala Nair, Perimatics’ co-Founder and chief solutions architect. (Perimatics Photo) The end goal is to help hospitals cut down the $5.2 billion a year that results from overage and underage in surgeries. In addition to staff overtime costs, operation rooms cost an estimated to run, so any variation from the set schedule can quickly become extortionate. That’s not to mention factors like patient and employee dissatisfaction, which is also a common side effect of scheduling challenges. Although this is the first time the technology has been deployed in a hospital system, Nair said it is easily scalable. Now that Perimatics has worked out which factors impact surgery length, the basic framework can be applied to almost any hospital, he said. Velagapudi said the startup is continuing work on its other AI technologies, including its Smart Anaesthesia Manager. That program, invented by Bala, analyzes a patient’s health metrics in real-time during surgery and helps doctors make decisions that have a big impact on a patient’s health when they are recovering. She also said the company is working on new solutions for post-surgery problems and surgical supplies. “It is quite different from the data science that is being done on the market today because it is real time,” Velagapudi said of the startup’s work. Perimatics spun out from the University of Washington last year and currently employs 7 at its headquarters in Bellevue, Wash. It is also a partner of , the tech giant’s startup assistance program.